# Captain (full site text) > Self-tuning file search for AI agents. This file is the complete text of > captain.dev, one section per page, generated from the rendered site. > Do not edit by hand: run `npm run llms:generate` in frontend/runcaptain. > The short index lives at https://captain.dev/llms.txt. Pages: https://captain.dev/, https://captain.dev/pricing, https://captain.dev/book-a-demo, https://captain.dev/security, https://captain.dev/blog, https://captain.dev/privacy-policy, https://captain.dev/terms-of-use, https://captain.dev/blog/edge-routing/, https://captain.dev/blog/captain-vs-elasticsearch/, https://captain.dev/blog/captain-vs-cloudflare-ai-search/, https://captain.dev/blog/captain-vs-google-rag-engine/, https://captain.dev/blog/copy-collections/, https://captain.dev/blog/ragie-to-captain-migration/, https://captain.dev/blog/captain-v2-launch/ Docs: https://docs.captain.dev. Support: humans@captain.dev. --- # Captain - Self-tuning file search for AI agents · Captain Source: https://captain.dev/ Description: Self-tuning file search for AI agents. Captain syncs scanned DOCX, complex PDFs, and video from sources like S3, SharePoint, and Google Drive, and makes complex files searchable with one API call, self-tuned towards your accuracy and latency targets. [ NOW SELF-TUNING CAPTAIN_EVAL ] ## Retrieval your agents can trust. The complete file search platform. Synced with cloud storage, fast and accurate, and optimized for complex retrieval. [Get API key](https://captain.dev/signup) [Book a demo](https://captain.dev/book-a-demo) [ BACKED AND USED BY ] ## One platform from raw files to ranked answers. Powerful ingestion and self-tuning retrieval, behind one query API, ready for production scale. Sync files and self-improve search as one platform Every layer above ships together, on one index. Nothing to wire and nothing to keep aligned. [ 01 SEARCH ] ### Search Sub-second queries through a deterministic API, with filters, rerank and candidate depth all yours to configure. ### Iterate Keep search in line with ever-changing data. One MCP tool call runs evals on your own files and tunes retrieval toward your targets. [ CAPTAIN_EVAL ] ### Process Index what DIY RAG can’t: scans, handwriting, tables, screenshots, recordings. Captain turns each one into clean, structured, searchable text, more carefully than you would by hand. ### Engine Unify a fragmented, multi-provider pipeline into one engine: pre-filtered vector search, embeddings and vector storage on a clean data model and serverless infrastructure, behind a drop-in API. ### Sync Change events update the index as files change, and a scheduled sweep catches anything an event missed. [ S3 ] [ R2 ] [ GCS ] [ SUPABASE ] [ BACKBLAZE ] [ TERRAFORM ] [ 01 SEARCH ] [ 02 ITERATE ] [ 03 PROCESS ] [ 04 ENGINE ] [ 05 SYNC ] [ HOW IT WORKS ] ## Files in. Answers out. ### Add Captain to your coding agent. [MCP SOURCE CODE](https://github.com/runcaptain/captain-mcp) Claude Code Codex Cursor GitHub Copilot Devin Any MCP client ``` claude mcp add --transport http captain https://mcp.captain.dev/mcp \ --header "Authorization: Bearer cap_..." ``` [ CASE STUDY ] ## Built for teams that depend on every answer. Used by Y Combinator, compliance teams, and engineers building agents that need reliable answers. Alan Yao Co-Founder & CTO, AthenaHQ The accuracy was noticeably better. Setup took 5 minutes, and it scaled to thousands of docs a day. [VIEW THE POST ON LINKEDIN](https://www.linkedin.com/feed/update/urn:li:activity:7445525818107228161/) Garry Tan President & CEO, Y Combinator Captain is a step function increase in capability compared to out-of-box RAG pipelines. [VIEW THE POST ON LINKEDIN](https://www.linkedin.com/posts/garrytan_captain-isa-step-function-increase-in-capability-activity-7393798234730713088-s4F9) [ BENCHMARKS ] ## Your data is the benchmark. A public benchmark tells you how a system ran on someone else's corpus. Run captain_eval with Captain's MCP and Captain builds hundreds of Q&A evals from your own files, scores retrieval against them, and tunes until it hits your target. [ COVERAGE: QUERIES ANSWERED ] Captain [ 100% ] Gemini File Search [ ~66% ] When evaluated against other leading file-search APIs on production queries, alternatives fail to answer about one in three questions. +43% [ HIGHER ACCURACY ] VS LEADING ALTERNATIVES · BEIR NDCG@10 108× [ FASTER INDEXING ] 18 HRS → 10 MIN 7.5× [ FASTER SEARCH ] 1,500MS → 100MS [ OBSERVABILITY 01 ] ### Usage insights See what people search for, and exactly where answers fall short. The feedback loop makes retrieval better over time. [ OBSERVABILITY 02 ] ### Knowledge gap discovery See the questions your data has yet to answer, surfaced automatically, so you know exactly where to close the gaps. [ OBSERVABILITY 03 ] ### Retrieval attack detection Catch black-hole vector attacks (arXiv:2604.05480) before they reach production, a failure mode most DIY search layers never see. [ WHY CAPTAIN ] ## The accuracy is not a model. It is one index, an eval loop, and parsing that keeps every word. ### Advanced search controls Metadata filters, semantic ratio tuning, boosts and chunk relations, all through one query API. The lever you need is a request parameter, not a fork of the pipeline. ### Multimodal & video One index across text, documents and video. Ask where the Q3 margin chart appears and get the file, the page and the timestamp. ### Cross-cloud indexing Index straight from object storage and cloud drives. One platform across every source, not a collection per silo. ### PII masking built in Redact sensitive customer data at index time with one flag, before it reaches your models or logs. ## Everything search needs, tuned to your data. [ FLAGSHIP ] ### Captain Search The fully-managed file search API. Point it at your files and search them. Parsing, embeddings, vector DB and evaluation, all managed for you. OCR → EMBED → VECTOR DB → EVALS [ ONE MANAGED ENGINE ] [ MAIN INTERFACE ] ### Captain Evals The main interface for Captain. Call captain_eval from the hosted MCP server and it scores retrieval on evals written from your own files, then tunes toward the accuracy or latency target you set. INSPECT EVAL TUNE REVIEW [ MANAGED SYNC ] ### Captain Sync Bucket change notifications drive the index in near real time, and scheduled reconciliation jobs sweep for anything a notification dropped. Your buckets remain the source of truth. S3 R2 GCS SUPABASE BACKBLAZE TERRAFORM [ PARSING ] ## Search fails at the parser, not at the embedding. A DOCX or a scanned PDF is not text yet. Whatever the parser drops, no search can find. DOCX XML fragments in a zip, with tables that only exist as formatting. Captain's parser was tuned on the ugliest DOCX files our customers could find. PDF Clean PDFs parse anywhere. Captain also reads the rotated scan and the handwritten margin note. VIDEO + AUDIO Transcribed, described and indexed at ingest. The chart on slide 12 is a query, not a scrubbing session. ## Enterprise-grade by default. [ SECURITY ] TLS in transit, encryption at rest, and opt-in PII masking so sensitive data is hidden from your agents. Need a specific framework? [Talk to us](https://captain.dev/book-a-demo) --- # Pricing · Captain Source: https://captain.dev/pricing Description: 500 free indexing credits a month, then $0.02 a credit. Each file type has its own credit rate. No per-seat pricing. 1,000 free queries a month on Developer, then $0.005 each. ## Pricing that scales with your search. ### Developer [ GET STARTED WITH USAGE PRICING ] $0/mo [Get started free](https://captain.dev/signup?ref=paygo) - 500 indexing credits/mo - $0.02 per overage credit - 1,000 queries/mo included - Then $0.005 per query - No commitment, cancel anytime ### Scale [ SAVE WITH BULK CREDITS ] $1,600/mo [Get started](https://captain.dev/signup?ref=startup) - 83,000 credits/mo - $0.015 per overage credit - Unlimited queries - Production-ready infrastructure - Compliance-ready infrastructure - Background backup protection - Slack support ### Enterprise [ FOR CUSTOM ARRANGEMENTS ] Custom pricing [Contact us](https://captain.dev/book-a-demo) - BYOC (On-Premise) available - AWS PrivateLink - GCP Private Service Connect - Custom Deployment Options - Dedicated support - White-Glove Onboarding - Unlimited queries ## Credit Pricing Each unit of work costs a fixed number of credits. Chat with our team to discuss bulk discounts. [ TYPE ] [ CREDITS ] [ EQUIVALENT AT $0.02/CREDIT ] [ WHAT'S INCLUDED ] Text Page 0.5 credits $0.01/page Text files (.txt, .md, code), web page text and YouTube captions: 3,000 characters per page, rounded up per file, so a non-empty file is at least one page Spreadsheet Page 0.5 credits $0.01/page Spreadsheets (.xlsx, .xls, .csv, .tsv): 3,000 characters of the table text Captain indexes, which repeats the column headers in every block of rows. Billed exactly, not rounded up. Pictures in a workbook bill as Images Basic Page 1 credit $0.02/page PDF and Word pages parsed with processing_type basic, or picked by auto for files with no photos, drawings, tables or scans. Reads the text layer; pages without one go to a vision model Advanced Page 2.5 credits $0.05/page PDF and Word pages parsed with processing_type advanced, or picked by auto for files with photos, drawings, tables or scans. A full-page vision model reads text, table structure, figures and layout Image 0.5 credits $0.01/image PNG, JPG, GIF and the rest; the chart in a screenshot becomes text you can query. Also each picture in a workbook, and each image on a web page indexed with advanced or auto Audio 5 credits / minute $0.10/minute MP3, WAV, FLAC and more, transcribed and indexed for semantic search. Billed by the second, no minimum Video 20 credits / minute $0.40/minute MP4, MOV, AVI, multimodal indexing covering frames, audio, and transcripts. Billed by the second, no minimum Email Text Page rate (plus each attachment at its own rate) $0.01 per 3,000 characters .msg and .eml: the message body with its From, To, Date and Subject lines bills as text. Each attachment bills at its type's rate, once for every email it is attached to. Inline images, unsupported files, and anything past 200 attachments, 250 MB or one level of forwarding are skipped and not billed Copy Collection 10 credits (same price at any collection size) $0.20/copy Clone a collection into another environment or a test run without re-indexing Query 1 query credit (Developer only, first 1,000/mo free) $0.005/query One search request against a collection from the API, SDK, MCP or Playground. An evaluation bills one query credit per test case per configuration; errored cases are not billed. Query credits are separate from indexing credits; Scale and Enterprise include unlimited queries. ## Frequently Asked Questions All plans include secure data handling, regular backups, and 24/7 monitoring. ### Does my processing credit allocation reset? Yes, credits reset every billing cycle. Run past your allocation and the job still finishes; the extra credits bill at your plan's per-credit rate. ### How are text files like .txt, .md, and code billed? Files without page breaks (.txt, .md, source code) bill at 0.5 credits per 3,000 characters, $0.01 each, rounded up per file: a 200-character file and a 3,000-character file both bill one page. No OCR or vision pass runs, so the same file always costs the same amount. ### How is my data stored and retained? Your indexed data lives in an encrypted environment scoped to your organization and stays there for the life of your subscription. Cancel and it is held 30 days, then permanently deleted. You can delete any document or collection yourself at any time, via API or dashboard. Captain is SOC 2 Type II certified and undergoes regular independent security audits. ### Can I upgrade or downgrade my plan mid-cycle? Yes. Upgrades take effect immediately: your credit allocation increases right away and billing is prorated for the remainder of the current cycle. Downgrades take effect at the start of your next billing cycle, so you keep your current allocation until then. If you need to adjust usage limits urgently, contact our team at humans@captain.dev and we can accommodate custom arrangements. ### Who can I contact for support? The fastest way to reach us is through Intercom, the messenger in the bottom right of the app. An AI assistant is available around the clock, and you can request a human team member at any point in the conversation. You can also email humans@captain.dev directly. We respond within 60 minutes during business hours. --- # Book a demo · Captain Source: https://captain.dev/book-a-demo Description: Tell us what you're building and see how teams like yours use Captain. [ NOW SELF-TUNING CAPTAIN_EVAL ] ## Let's talk search. Tell us what you're building and see how teams like yours use Captain. [ BACKED AND USED BY ] First name * Last name * Work email * Company * Role * Phone number * Company size * Tell us about your needs * Submit request By submitting, you agree to our Privacy Policy and to emails from us. --- # Security · Captain Source: https://captain.dev/security Description: How Captain protects the files you index: encryption in transit and at rest, tenant isolation, SOC 2 and HIPAA attestation, our subprocessor list, and how to reach the security team. [ LEGAL · SECURITY ] ## Security. - [ LAST UPDATED · 12 AUGUST 2026 ] - [ VERSION · 3.2 ] - [ OWNER · SECURITY & COMPLIANCE ] Read the document This document describes how Captain protects the files you index, the queries you run, and the results we return. It applies to every Captain service, in every region, on every plan. Where a term is defined in the Terms of Use, it carries the same meaning here. [ 01 SCOPE ] ## Who and what this covers. This policy applies to Captain as we operate it today and to every deployment model we offer. Where you hold a signed agreement with us and the two differ, the agreement controls. - The Captain API and the dashboard, on every plan, free through Enterprise. - Captain's managed cloud, where every tenant runs inside its own isolation boundary. - Every dataset indexed through either surface: source files, derived embeddings and the query logs that sit alongside them. Not covered: third-party tools you connect on your own account. Once data leaves Captain for a service you authorised, that service’s terms govern what happens to it. [ 02 DATA HANDLING ] ## Your files stay your files. We index your content. We do not train on it. Customer data is never used to build, fine-tune or evaluate a shared model, and it is never pooled with another customer’s corpus. Content is processed for exactly two purposes: producing the embeddings and search indices that make retrieval work, and returning the results you asked for. Delete a collection and its index goes with it: the vectors, the extracted text and the cached page renders, in the same operation. [ 03 ENCRYPTION ] ## Encrypted in transit, encrypted at rest. Every byte is encrypted on the wire and on disk, with no plaintext hop in between, including the hops between our own services. - TLS 1.3 for all traffic, terminated at the edge and re-established internally. - AES-256 at rest across object storage, block storage, backups and index shards. - Keys are rotated on a fixed schedule and held in a dedicated KMS. Customer-managed keys are available on Enterprise. [ 04 ACCESS CONTROL ] ## Least privilege, enforced by default. SSO and MFA are mandatory for every Captain employee and contractor. There are no shared credentials, and nobody holds standing access to production. Production access is role-scoped, time-bound and logged: an engineer requests the role the task needs, the grant expires on its own, and every action taken under it is written to an audit trail we retain for twelve months. Roles are reviewed quarterly and revoked the day somebody changes team. [ 05 INFRASTRUCTURE ] ## Isolated tenants on audited infrastructure. Each tenant is logically isolated: separate index namespaces, separate storage prefixes and separate keys, enforced at the service layer rather than by convention. You pin your data to a region, US or EU, and it does not leave it. For the strictest environments we ship a full BYOC deployment: Captain runs inside your own cloud account, on your own network, and nothing but licence telemetry ever leaves it. [ 06 AVAILABILITY ] ## Backups, recovery and uptime. Captain runs multi-zone with continuous backup and point-in-time restore. Recovery is rehearsed rather than assumed. - Recovery point objective: 15 minutes. - Recovery time objective: 4 hours. - Restore drills run twice a year against production-sized data, and their results feed the next audit window. Live and historical availability is published on the status page, and incidents are posted there before they are resolved rather than after. [ 07 INCIDENT RESPONSE ] ## What happens when something goes wrong. Security engineering is on call 24/7. Every alert is triaged within one hour of detection and a named incident commander owns it until it closes. If we confirm a breach affecting your data we notify you within 72 hours with what we know, what we have already done, and what you need to do. A written post-incident review follows within ten business days, whether or not you ask for one. [ 08 RETENTION ] ## Retention, deletion and export. You control the lifecycle of everything you send us, and nothing outlives the schedule below. - Content is deleted within 30 days of a delete request or of account closure. - Backups purge on their own 35-day cycle; nothing survives past it. - Export runs through the API for as long as the account is open, returning the files you supplied plus the metadata we derived. [ 09 PERSONNEL ] ## The people with access. Background checks are run wherever local law allows. Everyone completes security training at onboarding and again every year, and confidentiality obligations survive the end of employment. Access is granted on the first day it is needed and removed on the last. [ 10 YOUR RESPONSIBILITIES ] ## What we need from you. Security is shared. Three things sit on your side of the line. - Keep API keys secret, scope each one to a single workload, and rotate them on a schedule you set. - Use SSO and role assignment for your own team rather than one key passed around. - Tell us at the address below the moment you think a key is exposed. We will revoke it with you on the call. [ 11 CHANGES ] ## How this document changes. Material changes are announced 30 days before they take effect, by email to account owners and on the changelog. The version and date at the top of this page are authoritative; earlier versions are available on request. [ CONTENTS ] [ SUBPROCESSORS ] ## Who touches your data, and why. Every third party in the path, the region it runs in, and the category of data it can see. We give 30 days notice before this list changes. Captain subprocessors, their purpose, the region they run in and the category of data each can see. [ SUBPROCESSOR ] [ PURPOSE ] [ REGION ] [ DATA ] Amazon Web Services Primary compute, storage and backups US, EU Indexed content, embeddings Google Cloud Platform Overflow inference capacity US Derived embeddings only Cloudflare Edge routing, TLS termination, DDoS Global Request metadata Anthropic Vision and language models for indexing US Document content at index time Stripe Billing and payment processing US, EU Billing contact, payment method Datadog Application logging and monitoring US Operational metadata, no content Postmark Transactional email US Email address, message body [ CERTIFICATIONS ] ## Controls you can test, not badges you can admire. SOC 2 Type II and HIPAA attested, GDPR aligned, and encrypted at rest by default. Reports are available under NDA. [ DISCLOSURE ] ## Report a vulnerability. Send us the details and a way to reproduce it. We acknowledge every report within one business day and will not take legal action against good-faith research. [security@captain.dev](mailto:security@captain.dev) [ ASSURANCE ] ## Ask us the hard questions in writing. Type II report, penetration test summary and architecture overview, available to customers and prospects under NDA. [Talk to us](https://captain.dev/book-a-demo) [ MORE LEGAL ] [[ 01 PRIVACY ] Privacy Policy What personal data we collect, why we hold it, and the rights you have over it. Read](https://captain.dev/privacy-policy) [[ 02 TERMS ] Terms of Use The agreement that governs your use of Captain, plan by plan. Read](https://captain.dev/terms-of-use) [[ 03 DATA ] Data Processing Addendum The GDPR-ready DPA, including standard contractual clauses for transfers out of the EU. Read](https://captain.dev/dpa) --- # Blog · Captain Source: https://captain.dev/blog Description: Write-ups from the team building Captain: the latest on us, how we search the world's hardest files, and the challenges we've overcome along the way. [ RESOURCES · BLOG ] ## Field notes on retrieval. How we build search that agents can trust: the feature releases and engineering write-ups along the way. - [ 7 ARTICLES ] - [ UPDATED WEEKLY ] - [ LATEST · 10 SEP 2026 ] [RSS feed](https://captain.dev/blog/rss.xml) [ 01 FEATURED ] ## Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 [Read the article](https://captain.dev/blog/edge-routing/) [ ALL POSTS ] ## Writing from the team. Benchmarks, engineering write-ups, and launch notes. ### Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 COMPARISON ### Captain vs. Elasticsearch Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. 5 min read 7 Sep 2026 COMPARISON ### Captain vs. Cloudflare AI Search Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. 6 min read 7 Sep 2026 COMPARISON ### Captain vs. Google RAG Engine Google's RAG Engine ships the parts: a layout parser, an embedding model, a vector store and a reranker, each set up, billed and maintained on its own. Hybrid search needs sparse vectors you compute yourself, and import is a batch job with no rollback. Captain does all of it in one call from your bucket. 5 min read 7 Sep 2026 ### Copy Collections One API call duplicates a collection's documents, chunks, embeddings and custom metadata under a new name, reusing the index you already built. 5 min read 18 Aug 2026 ### Migrating from Ragie to Captain Ragie's hosted service will end on Sunday, July 19, 2026. To help customers keep their applications running, many Ragie customers have been migrating to Captain. 9 min read 14 Jul 2026 [ 1 MORE ] Load more articles --- # Privacy Policy · Captain Source: https://captain.dev/privacy-policy Description: What personal data Captain collects, why we hold it, who else can see it, how long we keep it, and the rights you have over it - including how to exercise them. [ LEGAL · PRIVACY ] ## Privacy Policy. - [ LAST UPDATED · JUNE 9, 2025 ] - [ OWNER · CAPTAIN TECHNOLOGIES, INC. ] Read the policy Captain Technologies, Inc. (the “Company”) is committed to maintaining robust privacy protections for its users. Our Privacy Policy (“Privacy Policy”) is designed to help you understand how we collect, use and safeguard the information you provide to us and to assist you in making informed decisions when using our Service. [ 00 INTRODUCTION ] ## Captain Technologies, Inc. Privacy Policy For purposes of this Agreement, the “Site” refers to the Company’s website located at runcaptain.com and its subdomains. The “Service” refers to the Company’s software platform accessible via the Site, through which users can connect business data sources (including cloud file storage systems and a variety of software tools), interact with an AI chatbot, and explore connected files and data. The terms “we,” “us,” and “our” refer to the Company. The term “you” refers to you, as a user of our Site or Service. By accessing our Site or our Service, you accept our Privacy Policy (found here: https://captain.dev/privacy) and Terms of Use (found here: https://captain.dev/terms), and you consent to our collection, storage, use and disclosure of your Personal Information as described in this Privacy Policy. [ 01 COLLECTION ] ## Information We Collect We collect “Non-Personal Information” and “Personal Information.” Non-Personal Information includes information that cannot be used to personally identify you, such as anonymous usage data, general demographic information we may collect, referring/exit pages and URLs, platform types, preferences you submit and preferences that are generated based on the data you submit and number of clicks. Personal Information includes your email, full name, company name, IP address, usage history, and any files or data you upload or connect to the Site. This may include financial records, structured and unstructured documents, metadata from connected integrations, and service preferences, which you submit to us through the registration process or use of the Site. 1. Information collected via Technology. To activate the Service you do not need to submit any Personal Information other than your email address. To use the Service thereafter, you do need to submit further Personal Information which may include: your name, company affiliation, account credentials for third-party platforms (e.g., Google, QuickBooks), usage logs, AI interaction history, and content you upload or link through integrations. However, in an effort to improve the quality of the Service, we track information provided to us by your browser or by our software application when you view or use the Service, such as the website you came from (known as the “referring URL”), the type of browser you use, the device from which you connected to the Service, the time and date of access, and other information that does not personally identify you. We track this information using cookies, or small text files which include an anonymous unique identifier. Cookies are sent to a user’s browser from our servers and are stored on the user’s computer hard drive. Sending a cookie to a user’s browser enables us to collect Non-Personal information about that user and keep a record of the user’s preferences when utilizing our services, both on an individual and aggregate basis. For example, the Company may use cookies to collect the following information: - Authentication status - Preferred integrations or workflows - Feature usage patterns - Session length and behavior - Site interaction history The Company may use both persistent and session cookies; persistent cookies remain on your computer after you close your session and until you delete them, while session cookies expire when you close your browser. For example, “We store a persistent cookie to remember your preferred account and maintain your login session.” 2. Information you provide us by registering for an account. In addition to the information provided automatically by your browser when you visit the Site, to become a subscriber to the Service you will need to create a personal profile. You can create a profile by registering with the Service and entering your email address, and creating a username and a password. By registering, you are authorizing us to collect, store and use your email address in accordance with this Privacy Policy. 3. Children’s Privacy. The Site and the Service are not directed to anyone under the age of 13. The Site does not knowingly collect or solicit information from anyone under the age of 13, or allow anyone under the age of 13 to sign up for the Service. In the event that we learn that we have gathered personal information from anyone under the age of 13 without the consent of a parent or guardian, we will delete that information as soon as possible. If you believe we have collected such information, please contact us at humans@captain.dev. [ 02 USE AND SHARING ] ## How We Use and Share Information Personal Information: Except as otherwise stated in this Privacy Policy, we do not sell, trade, rent or otherwise share for marketing purposes your Personal Information with third parties without your consent. We do not sell your personal information as defined under the California Consumer Privacy Act (CCPA). We do share Personal Information with vendors who are performing services for the Company, such as the servers for our email communications who are provided access to user’s email address for purposes of sending emails from us. Those vendors use your Personal Information only at our direction and in accordance with our Privacy Policy. In general, the Personal Information you provide to us is used to help us communicate with you. For example, we use Personal Information to contact users in response to questions, solicit feedback from users, provide technical support, and inform users about promotional offers. We may share Personal Information with outside parties if we have a good-faith belief that access, use, preservation or disclosure of the information is reasonably necessary to meet any applicable legal process or enforceable governmental request; to enforce applicable Terms of Service, including investigation of potential violations; address fraud, security or technical concerns; or to protect against harm to the rights, property, or safety of our users or the public as required or permitted by law. Non-Personal Information: In general, we use Non-Personal Information to help us improve the Service and customize the user experience. We also aggregate Non-Personal Information in order to track trends and analyze use patterns on the Site. This Privacy Policy does not limit in any way our use or disclosure of Non-Personal Information and we reserve the right to use and disclose such Non-Personal Information to our partners, advertisers and other third parties at our discretion. In the event we undergo a business transaction such as a merger, acquisition by another company, or sale of all or a portion of our assets, your Personal Information may be among the assets transferred. You acknowledge and consent that such transfers may occur and are permitted by this Privacy Policy, and that any acquirer of our assets may continue to process your Personal Information as set forth in this Privacy Policy. If our information practices change at any time in the future, we will post the policy changes to the Site so that you may opt out of the new information practices. We suggest that you check the Site periodically if you are concerned about how your information is used. [ 03 PROTECTION ] ## How We Protect Information We implement security measures designed to protect your information from unauthorized access. Your account is protected by your account password and we urge you to take steps to keep your personal information safe by not disclosing your password and by logging out of your account after each use. We further protect your information from potential security breaches by implementing certain technological security measures including encryption, firewalls and secure socket layer technology. However, these measures do not guarantee that your information will not be accessed, disclosed, altered or destroyed by breach of such firewalls and secure server software. By using our Service, you acknowledge that you understand and agree to assume these risks. [ 04 YOUR RIGHTS ] ## Your Rights Regarding the Use of Your Personal Information You have the right at any time to prevent us from contacting you for marketing purposes. When we send a promotional communication to a user, the user can opt out of further promotional communications by following the unsubscribe instructions provided in each promotional e-mail. You can also indicate that you do not wish to receive marketing communications from us in the Account Settings section of the Site. Please note that notwithstanding the promotional preferences you indicate by either unsubscribing or opting out in the Account Settings of the Site, we may continue to send you administrative emails including, for example, periodic updates to our Privacy Policy. [ 05 LINKS ] ## Links to Other Websites As part of the Service, we may provide links to or compatibility with other websites or applications. However, we are not responsible for the privacy practices employed by those websites or the information or content they contain. This Privacy Policy applies solely to information collected by us through the Site and the Service. Therefore, this Privacy Policy does not apply to your use of a third party website accessed by selecting a link on our Site or via our Service. To the extent that you access or use the Service through or on another website or application, then the privacy policy of that other website or application will apply to your access or use of that site or application. We encourage our users to read the privacy statements of other websites before proceeding to use them. [ 06 CHANGES ] ## Changes to Our Privacy Policy The Company reserves the right to change this policy and our Terms of Service at any time. We will notify you of significant changes to our Privacy Policy by sending a notice to the primary email address specified in your account or by placing a prominent notice on our site. Significant changes will go into effect 30 days following such notification. Non-material changes or clarifications will take effect immediately. You should periodically check the Site and this privacy page for updates. [ 07 CALIFORNIA ] ## California Privacy Rights If you are a California resident, you have the right to request certain information about our collection and use of your personal information over the past 12 months. These rights include: - The right to know what personal information we collect, use, disclose, and sell. - The right to request deletion of your personal information. - The right to opt out of the sale or sharing of your personal information (we do not sell your data). - The right to non-discrimination for exercising your privacy rights. - You or your authorized agent may submit a request by contacting us at humans@captain.dev. We may ask for verification of your identity before fulfilling your request. - We do not knowingly collect personal information from individuals under 16 years of age. The Company does not sell or share your personal information with third parties for monetary gain or cross-context behavioral advertising. [ 08 CONTACT ] ## Contact Us If you have any questions regarding this Privacy Policy or the practices of this Site, please contact us by sending an email to humans@captain.dev. Last Updated: This Privacy Policy was last updated on June 9, 2025. [ CONTENTS ] [ REQUESTS ] ## Exercise a right. Write from the address on the account and tell us which right you are using. We verify, then act, and confirm in writing within 30 days. [humans@captain.dev](mailto:humans@captain.dev) [ QUESTIONS ] ## Ask our DPO. Our Data Protection Officer answers questions about this policy, our transfer safeguards and our subprocessors - including before you sign. [humans@captain.dev](mailto:humans@captain.dev) [ MORE LEGAL ] [[ 01 SECURITY ] Security Where your indexed files live, who can reach them, and the subprocessors we let near them. Read](https://captain.dev/security) [[ 02 TERMS ] Terms of Use The agreement that governs your use of Captain, plan by plan. Read](https://captain.dev/terms-of-use) [[ 03 DATA ] Data Processing Addendum The GDPR-ready DPA, including standard contractual clauses for transfers out of the EU. Read](https://captain.dev/dpa) --- # Terms of Use · Captain Source: https://captain.dev/terms-of-use Description: The agreement that governs your use of Captain: plans and credits, payment, acceptable use, who owns what, availability, liability and how either side can end it. [ LEGAL · TERMS ] ## Terms of Use. - [ LAST UPDATED · JUNE 9, 2025 ] - [ VERSION · 1.0 ] - [ OWNER · CAPTAIN TECHNOLOGIES, INC. ] Read the terms CAPTAIN TECHNOLOGIES, INC. WEBSITE TERMS OF SERVICE - VERSION 1.0. The website located at runcaptain.com and its subdomains (collectively, the “Site”) is a copyrighted work belonging to Captain Technologies, Inc. (“Company”, “us”, “our”, and “we”). Certain features of the Site may be subject to additional guidelines, terms, or rules, which will be posted on the Site in connection with such features. All such additional terms, guidelines, and rules are incorporated by reference into these Terms. [ 00 NOTICE ] ## Binding terms, arbitration and class waiver THESE TERMS OF SERVICE (THESE “TERMS”) SET FORTH THE LEGALLY BINDING TERMS AND CONDITIONS THAT GOVERN YOUR USE OF THE SITE. BY ACCESSING OR USING THE SITE, YOU ARE ACCEPTING THESE TERMS (ON BEHALF OF YOURSELF OR THE ENTITY THAT YOU REPRESENT), AND YOU REPRESENT AND WARRANT THAT YOU HAVE THE RIGHT, AUTHORITY, AND CAPACITY TO ENTER INTO THESE TERMS (ON BEHALF OF YOURSELF OR THE ENTITY THAT YOU REPRESENT). YOU MAY NOT ACCESS OR USE THE SITE OR ACCEPT THE TERMS IF YOU ARE NOT AT LEAST 18 YEARS OLD. IF YOU DO NOT AGREE WITH ALL OF THE PROVISIONS OF THESE TERMS, DO NOT ACCESS AND/OR USE THE SITE. PLEASE BE AWARE THAT SECTION 10.2 CONTAINS PROVISIONS GOVERNING HOW TO RESOLVE DISPUTES BETWEEN YOU AND COMPANY. AMONG OTHER THINGS, SECTION 10.2 INCLUDES AN AGREEMENT TO ARBITRATE WHICH REQUIRES, WITH LIMITED EXCEPTIONS, THAT ALL DISPUTES BETWEEN YOU AND US SHALL BE RESOLVED BY BINDING AND FINAL ARBITRATION. SECTION 10.2 ALSO CONTAINS A CLASS ACTION AND JURY TRIAL WAIVER. PLEASE READ SECTION 10.2 CAREFULLY. UNLESS YOU OPT OUT OF THE AGREEMENT TO ARBITRATE WITHIN 30 DAYS: (1) YOU WILL ONLY BE PERMITTED TO PURSUE DISPUTES OR CLAIMS AND SEEK RELIEF AGAINST US ON AN INDIVIDUAL BASIS, NOT AS A PLAINTIFF OR CLASS MEMBER IN ANY CLASS OR REPRESENTATIVE ACTION OR PROCEEDING AND YOU WAIVE YOUR RIGHT TO PARTICIPATE IN A CLASS ACTION LAWSUIT OR CLASS-WIDE ARBITRATION; AND (2) YOU ARE WAIVING YOUR RIGHT TO PURSUE DISPUTES OR CLAIMS AND SEEK RELIEF IN A COURT OF LAW AND TO HAVE A JURY TRIAL. [ 01 ACCOUNTS ] ## Accounts 1.1 Account Creation. In order to use certain features of the Site, you must register for an account (“Account”) and provide certain information about yourself as prompted by the account registration form. You represent and warrant that: (a) all required registration information you submit is truthful and accurate; (b) you will maintain the accuracy of such information. You may delete your Account at any time, for any reason, by following the instructions on the Site. Company may suspend or terminate your Account in accordance with Section 8. 1.2 Account Responsibilities. You are responsible for maintaining the confidentiality of your Account login information and are fully responsible for all activities that occur under your Account. You agree to immediately notify Company of any unauthorized use, or suspected unauthorized use of your Account or any other breach of security. Company cannot and will not be liable for any loss or damage arising from your failure to comply with the above requirements. [ 02 ACCESS ] ## Access to the Site 2.1 License. Subject to these Terms, Company grants you a non-transferable, non-exclusive, revocable, limited license to use and access the Site solely for your own personal, noncommercial use. 2.2 Certain Restrictions. The rights granted to you in these Terms are subject to the following restrictions: (a) you shall not license, sell, rent, lease, transfer, assign, distribute, host, or otherwise commercially exploit the Site, whether in whole or in part, or any content displayed on the Site; (b) you shall not modify, make derivative works of, disassemble, reverse compile or reverse engineer any part of the Site; (c) you shall not access the Site in order to build a similar or competitive website, product, or service; (d) you agree not to use the Site or any of its features, logic, or content for the purpose of designing, developing, or training a competing software product, whether directly or indirectly; and (e) except as expressly stated herein, no part of the Site may be copied, reproduced, distributed, republished, downloaded, displayed, posted or transmitted in any form or by any means. Unless otherwise indicated, any future release, update, or other addition to functionality of the Site shall be subject to these Terms. All copyright and other proprietary notices on the Site (or on any content displayed on the Site) must be retained on all copies thereof. 2.3 Modification. Company reserves the right, at any time, to modify, suspend, or discontinue the Site (in whole or in part) with or without notice to you. You agree that Company will not be liable to you or to any third party for any modification, suspension, or discontinuation of the Site or any part thereof. 2.4 No Support or Maintenance. You acknowledge and agree that Company will have no obligation to provide you with any support or maintenance in connection with the Site. 2.5 Ownership. Excluding any User Content that you may provide (defined below), you acknowledge that all the intellectual property rights, including copyrights, patents, trade marks, and trade secrets, in the Site and its content are owned by Company or Company’s suppliers. Neither these Terms (nor your access to the Site) transfers to you or any third party any rights, title or interest in or to such intellectual property rights, except for the limited access rights expressly set forth in Section 2.1. Company and its suppliers reserve all rights not granted in these Terms. There are no implied licenses granted under these Terms. (a) Early Adopter Agreement. Users who subscribe to the Early Adopter plan must accept and sign the Company’s Early Adopter Agreement as a condition of access to Early Adopter features and services. This agreement includes specific terms such as license restrictions, confidentiality obligations, limitations on liability, disclaimers of warranties, and provisions governing the use and evaluation of the Service. The Early Adopter Agreement is incorporated by reference into these Terms of Service and is available at https://captain.dev/terms#EAA. Failure to accept or comply with the Early Adopter Agreement may result in immediate suspension or termination of access to Early Adopter features. The Company may update the Early Adopter Agreement at any time with prior notice, and continued use of Early Adopter features after such updates constitutes acceptance of the revised terms. 2.6 Feedback. If you provide Company with any feedback or suggestions regarding the Site (“Feedback”), you hereby assign to Company all rights in such Feedback and agree that Company shall have the right to use and fully exploit such Feedback and related information in any manner it deems appropriate. Company will treat any Feedback you provide to Company as non-confidential and non-proprietary. You agree that you will not submit to Company any information or ideas that you consider to be confidential or proprietary. 2.7 Trade Secrets. Certain workflows, methods, interfaces, and integrations accessible via the Site are proprietary trade secrets of the Company. Accessing or viewing these materials does not grant any license or right to use, disclose, or replicate them. Unauthorized use, disclosure, or duplication of these materials for commercial purposes is strictly prohibited and may subject you to legal action under trade secret, contract, and unfair competition laws. [ 03 USER CONTENT ] ## User Content 3.1 User Content. “User Content” means any and all information and content that a user submits to, or uses with, the Site (e.g., content in the user’s profile or postings). You are solely responsible for your User Content. You assume all risks associated with use of your User Content, including any reliance on its accuracy, completeness or usefulness by others, or any disclosure of your User Content that personally identifies you or any third party. You hereby represent and warrant that your User Content does not violate our Acceptable Use Policy (defined in Section 3.3). You may not represent or imply to others that your User Content is in any way provided, sponsored or endorsed by Company. Since you alone are responsible for your User Content, you may expose yourself to liability if, for example, your User Content violates the Acceptable Use Policy. Company is not obligated to backup any User Content, and your User Content may be deleted at any time without prior notice. You are solely responsible for creating and maintaining your own backup copies of your User Content if you desire. 3.2 License. You hereby grant (and you represent and warrant that you have the right to grant) to Company an irrevocable, nonexclusive, royalty-free and fully paid, worldwide license to reproduce, distribute, publicly display and perform, prepare derivative works of, incorporate into other works, and otherwise use and exploit your User Content, and to grant sublicenses of the foregoing rights, solely for the purposes of including your User Content in the Site. You hereby irrevocably waive (and agree to cause to be waived) any claims and assertions of moral rights or attribution with respect to your User Content. 3.3 Acceptable Use Policy. The following terms constitute our “Acceptable Use Policy”: (a) You agree not to use the Site to collect, upload, transmit, display, or distribute any User Content (i) that violates any third-party right, including any copyright, trademark, patent, trade secret, moral right, privacy right, right of publicity, or any other intellectual property or proprietary right, (ii) that is unlawful, harassing, abusive, tortious, threatening, harmful, invasive of another’s privacy, vulgar, defamatory, false, intentionally misleading, trade libelous, pornographic, obscene, patently offensive, promotes racism, bigotry, hatred, or physical harm of any kind against any group or individual or is otherwise objectionable, (iii) that is harmful to minors in any way, or (iv) that is in violation of any law, regulation, or obligations or restrictions imposed by any third party. (b) In addition, you agree not to: (i) upload, transmit, or distribute to or through the Site any computer viruses, worms, or any software intended to damage or alter a computer system or data; (ii) send through the Site unsolicited or unauthorized advertising, promotional materials, junk mail, spam, chain letters, pyramid schemes, or any other form of duplicative or unsolicited messages, whether commercial or otherwise; (iii) use the Site to harvest, collect, gather or assemble information or data regarding other users, including e-mail addresses, without their consent; (iv) interfere with, disrupt, or create an undue burden on servers or networks connected to the Site, or violate the regulations, policies or procedures of such networks; (v) attempt to gain unauthorized access to the Site (or to other computer systems or networks connected to or used together with the Site), whether through password mining or any other means; (vi) harass or interfere with any other user’s use and enjoyment of the Site; or (vii) use software or automated agents or scripts to produce multiple accounts on the Site, or to generate automated searches, requests, or queries to (or to strip, scrape, or mine data from) the Site (provided, however, that we conditionally grant to the operators of public search engines revocable permission to use spiders to copy materials from the Site for the sole purpose of and solely to the extent necessary for creating publicly available searchable indices of the materials, but not caches or archives of such materials, subject to the parameters set forth in our robots.txt file). 3.4 Enforcement. We reserve the right (but have no obligation) to review, refuse and/or remove any User Content in our sole discretion, and to investigate and/or take appropriate action against you in our sole discretion if you violate the Acceptable Use Policy or any other provision of these Terms or otherwise create liability for us or any other person. Such action may include removing or modifying your User Content, terminating your Account in accordance with Section 8, and/or reporting you to law enforcement authorities. [ 04 INDEMNIFICATION ] ## Indemnification You agree to indemnify and hold Company (and its officers, employees, and agents) harmless, including costs and attorneys’ fees, from any claim or demand made by any third party due to or arising out of (a) your use of the Site, (b) your violation of these Terms, (c) your violation of applicable laws or regulations or (d) your User Content. Company reserves the right, at your expense, to assume the exclusive defense and control of any matter for which you are required to indemnify us, and you agree to cooperate with our defense of these claims. You agree not to settle any matter without the prior written consent of Company. Company will use reasonable efforts to notify you of any such claim, action or proceeding upon becoming aware of it. [ 05 THIRD PARTIES ] ## Third-Party Links & Ads; Other Users 5.1 Third-Party Links & Ads. The Site may contain links to third-party websites and services, and/or display advertisements for third parties (collectively, “Third-Party Links & Ads”). Such Third-Party Links & Ads are not under the control of Company, and Company is not responsible for any Third-Party Links & Ads. Company provides access to these Third-Party Links & Ads only as a convenience to you, and does not review, approve, monitor, endorse, warrant, or make any representations with respect to Third-Party Links & Ads. You use all Third-Party Links & Ads at your own risk, and should apply a suitable level of caution and discretion in doing so. When you click on any of the Third-Party Links & Ads, the applicable third party’s terms and policies apply, including the third party’s privacy and data gathering practices. You should make whatever investigation you feel necessary or appropriate before proceeding with any transaction in connection with such Third-Party Links & Ads. 5.2 Other Users. Each Site user is solely responsible for any and all of its own User Content. Since we do not control User Content, you acknowledge and agree that we are not responsible for any User Content, whether provided by you or by others. We make no guarantees regarding the accuracy, currency, suitability, appropriateness, or quality of any User Content. Your interactions with other Site users are solely between you and such users. You agree that Company will not be responsible for any loss or damage incurred as the result of any such interactions. If there is a dispute between you and any Site user, we are under no obligation to become involved. 5.3 Release. You hereby release and forever discharge Company (and our officers, employees, agents, successors, and assigns) from, and hereby waive and relinquish, each and every past, present and future dispute, claim, controversy, demand, right, obligation, liability, action and cause of action of every kind and nature (including personal injuries, death, and property damage), that has arisen or arises directly or indirectly out of, or that relates directly or indirectly to, the Site (including any interactions with, or act or omission of, other Site users or any Third-Party Links & Ads). IF YOU ARE A CALIFORNIA RESIDENT, YOU HEREBY WAIVE CALIFORNIA CIVIL CODE SECTION 1542 IN CONNECTION WITH THE FOREGOING, WHICH STATES: “A GENERAL RELEASE DOES NOT EXTEND TO CLAIMS WHICH THE CREDITOR OR RELEASING PARTY DOES NOT KNOW OR SUSPECT TO EXIST IN HIS OR HER FAVOR AT THE TIME OF EXECUTING THE RELEASE, WHICH IF KNOWN BY HIM OR HER MUST HAVE MATERIALLY AFFECTED HIS OR HER SETTLEMENT WITH THE DEBTOR OR RELEASED PARTY.” [ 06 DISCLAIMERS ] ## Disclaimers [ DISCLAIMER ] THE SITE IS PROVIDED ON AN “AS-IS” AND “AS AVAILABLE” BASIS, AND COMPANY (AND OUR SUPPLIERS) EXPRESSLY DISCLAIM ANY AND ALL WARRANTIES AND CONDITIONS OF ANY KIND, WHETHER EXPRESS, IMPLIED, OR STATUTORY, INCLUDING ALL WARRANTIES OR CONDITIONS OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, QUIET ENJOYMENT, ACCURACY, OR NON-INFRINGEMENT. WE (AND OUR SUPPLIERS) MAKE NO WARRANTY THAT THE SITE WILL MEET YOUR REQUIREMENTS, WILL BE AVAILABLE ON AN UNINTERRUPTED, TIMELY, SECURE, OR ERROR-FREE BASIS, OR WILL BE ACCURATE, RELIABLE, FREE OF VIRUSES OR OTHER HARMFUL CODE, COMPLETE, LEGAL, OR SAFE. IF APPLICABLE LAW REQUIRES ANY WARRANTIES WITH RESPECT TO THE SITE, ALL SUCH WARRANTIES ARE LIMITED IN DURATION TO 90 DAYS FROM THE DATE OF FIRST USE. SOME JURISDICTIONS DO NOT ALLOW THE EXCLUSION OF IMPLIED WARRANTIES, SO THE ABOVE EXCLUSION MAY NOT APPLY TO YOU. SOME JURISDICTIONS DO NOT ALLOW LIMITATIONS ON HOW LONG AN IMPLIED WARRANTY LASTS, SO THE ABOVE LIMITATION MAY NOT APPLY TO YOU. [ 07 LIABILITY ] ## Limitation on Liability TO THE MAXIMUM EXTENT PERMITTED BY LAW, IN NO EVENT SHALL COMPANY (OR OUR SUPPLIERS) BE LIABLE TO YOU OR ANY THIRD PARTY FOR ANY LOST PROFITS, LOST DATA, COSTS OF PROCUREMENT OF SUBSTITUTE PRODUCTS, OR ANY INDIRECT, CONSEQUENTIAL, EXEMPLARY, INCIDENTAL, SPECIAL OR PUNITIVE DAMAGES ARISING FROM OR RELATING TO THESE TERMS OR YOUR USE OF, OR INABILITY TO USE, THE SITE, EVEN IF COMPANY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. ACCESS TO, AND USE OF, THE SITE IS AT YOUR OWN DISCRETION AND RISK, AND YOU WILL BE SOLELY RESPONSIBLE FOR ANY DAMAGE TO YOUR DEVICE OR COMPUTER SYSTEM, OR LOSS OF DATA RESULTING THEREFROM. TO THE MAXIMUM EXTENT PERMITTED BY LAW, NOTWITHSTANDING ANYTHING TO THE CONTRARY CONTAINED HEREIN, OUR LIABILITY TO YOU FOR ANY DAMAGES ARISING FROM OR RELATED TO THESE TERMS (FOR ANY CAUSE WHATSOEVER AND REGARDLESS OF THE FORM OF THE ACTION), WILL AT ALL TIMES BE LIMITED TO A MAXIMUM OF FIFTY US DOLLARS. THE EXISTENCE OF MORE THAN ONE CLAIM WILL NOT ENLARGE THIS LIMIT. YOU AGREE THAT OUR SUPPLIERS WILL HAVE NO LIABILITY OF ANY KIND ARISING FROM OR RELATING TO THESE TERMS. SOME JURISDICTIONS DO NOT ALLOW THE LIMITATION OR EXCLUSION OF LIABILITY FOR INCIDENTAL OR CONSEQUENTIAL DAMAGES, SO THE ABOVE LIMITATION OR EXCLUSION MAY NOT APPLY TO YOU. IF YOU HAVE SIGNED A SEPARATE WRITTEN AGREEMENT WITH THE COMPANY THAT SPECIFIES A DIFFERENT LIMITATION OF LIABILITY, THAT AGREEMENT SHALL CONTROL TO THE EXTENT OF ANY CONFLICT. [ 08 TERMINATION ] ## Term and Termination Subject to this Section, these Terms will remain in full force and effect while you use the Site. We may suspend or terminate your rights to use the Site (including your Account) at any time for any reason at our sole discretion, including for any use of the Site in violation of these Terms. Upon termination of your rights under these Terms, your Account and right to access and use the Site will terminate immediately. You understand that any termination of your Account may involve deletion of your User Content associated with your Account from our live databases. Company will not have any liability whatsoever to you for any termination of your rights under these Terms, including for termination of your Account or deletion of your User Content. Even after your rights under these Terms are terminated, the following provisions of these Terms will remain in effect: Sections 2.2 through 2.6, Section 3 and Sections 4 through 10. [ 09 COPYRIGHT ] ## Copyright Policy Company respects the intellectual property of others and asks that users of our Site do the same. In connection with our Site, we have adopted and implemented a policy respecting copyright law that provides for the removal of any infringing materials and for the termination, in appropriate circumstances, of users of our online Site who are repeat infringers of intellectual property rights, including copyrights. If you believe that one of our users is, through the use of our Site, unlawfully infringing the copyright(s) in a work, and wish to have the allegedly infringing material removed, the following information in the form of a written notification (pursuant to 17 U.S.C. § 512(c)) must be provided to our designated Copyright Agent: - 01 your physical or electronic signature; - 02 identification of the copyrighted work(s) that you claim to have been infringed; - 03 identification of the material on our services that you claim is infringing and that you request us to remove; - 04 sufficient information to permit us to locate such material; - 05 your address, telephone number, and e-mail address; - 06 a statement that you have a good faith belief that use of the objectionable material is not authorized by the copyright owner, its agent, or under the law; and - 07 a statement that the information in the notification is accurate, and under penalty of perjury, that you are either the owner of the copyright that has allegedly been infringed or that you are authorized to act on behalf of the copyright owner. Please note that, pursuant to 17 U.S.C. § 512(f), any misrepresentation of material fact (falsities) in a written notification automatically subjects the complaining party to liability for any damages, costs and attorney’s fees incurred by us in connection with the written notification and allegation of copyright infringement. The designated Copyright Agent for Company is: [Pending Registration]. Designated Agent: [Pending Registration]. Address of Agent: [Pending Registration]. Telephone: [Pending Registration]. Fax: [Pending Registration]. Email: humans@captain.dev (current contact for copyright complaints) Note: Company has not yet formally registered a DMCA Agent with the U.S. Copyright Office. Users may report potential copyright concerns to the email above, but formal DMCA takedown notices are not being processed under 17 U.S.C. § 512 until registration is complete. [ 10 GENERAL ] ## General 10.1 Changes. These Terms are subject to occasional revision, and if we make any substantial changes, we may notify you by sending you an e-mail to the last e-mail address you provided to us (if any), and/or by prominently posting notice of the changes on our Site. You are responsible for providing us with your most current e-mail address. In the event that the last e-mail address that you have provided us is not valid, or for any reason is not capable of delivering to you the notice described above, our dispatch of the e-mail containing such notice will nonetheless constitute effective notice of the changes described in the notice. Continued use of our Site following notice of such changes shall indicate your acknowledgement of such changes and agreement to be bound by the terms and conditions of such changes. 10.2 Dispute Resolution. Please read the following arbitration agreement in this Section (the “Arbitration Agreement”) carefully. It requires you to arbitrate disputes with Company, its parent companies, subsidiaries, affiliates, successors and assigns and all of their respective officers, directors, employees, agents, and representatives (collectively, the “Company Parties”) and limits the manner in which you can seek relief from the Company Parties. These Terms shall be governed by the laws of the State of Delaware. (a) Applicability of Arbitration Agreement. You agree that any dispute between you and any of the Company Parties relating in any way to the Site, the services offered on the Site (the “Services”) or these Terms will be resolved by binding arbitration, rather than in court, except that (1) you and the Company Parties may assert individualized claims in small claims court if the claims qualify, remain in such court and advance solely on an individual, non-class basis; and (2) you or the Company Parties may seek equitable relief in court for infringement or other misuse of intellectual property rights (such as trademarks, trade dress, domain names, trade secrets, copyrights, and patents). This Arbitration Agreement shall survive the expiration or termination of these Terms and shall apply, without limitation, to all claims that arose or were asserted before you agreed to these Terms (in accordance with the preamble) or any prior version of these Terms. This Arbitration Agreement does not preclude you from bringing issues to the attention of federal, state or local agencies. Such agencies can, if the law allows, seek relief against the Company Parties on your behalf. For purposes of this Arbitration Agreement, “Dispute” will also include disputes that arose or involve facts occurring before the existence of this or any prior versions of the Agreement as well as claims that may arise after the termination of these Terms. (b) Informal Dispute Resolution. There might be instances when a Dispute arises between you and Company. If that occurs, Company is committed to working with you to reach a reasonable resolution. You and Company agree that good faith informal efforts to resolve Disputes can result in a prompt, low-cost and mutually beneficial outcome. You and Company therefore agree that before either party commences arbitration against the other (or initiates an action in small claims court if a party so elects), we will personally meet and confer telephonically or via videoconference, in a good faith effort to resolve informally any Dispute covered by this Arbitration Agreement (“Informal Dispute Resolution Conference”). If you are represented by counsel, your counsel may participate in the conference, but you will also participate in the conference. The party initiating a Dispute must give notice to the other party in writing of its intent to initiate an Informal Dispute Resolution Conference (“Notice”), which shall occur within 45 days after the other party receives such Notice, unless an extension is mutually agreed upon by the parties. Notice to Company that you intend to initiate an Informal Dispute Resolution Conference should be sent by email to: humans@captain.dev, or by regular mail to 2235 3rd St, San Francisco, CA 94107. The Notice must include: (1) your name, telephone number, mailing address, e-mail address associated with your account (if you have one); (2) the name, telephone number, mailing address and e-mail address of your counsel, if any; and (3) a description of your Dispute. The Informal Dispute Resolution Conference shall be individualized such that a separate conference must be held each time either party initiates a Dispute, even if the same law firm or group of law firms represents multiple users in similar cases, unless all parties agree; multiple individuals initiating a Dispute cannot participate in the same Informal Dispute Resolution Conference unless all parties agree. In the time between a party receiving the Notice and the Informal Dispute Resolution Conference, nothing in this Arbitration Agreement shall prohibit the parties from engaging in informal communications to resolve the initiating party’s Dispute. Engaging in the Informal Dispute Resolution Conference is a condition precedent and requirement that must be fulfilled before commencing arbitration. The statute of limitations and any filing fee deadlines shall be tolled while the parties engage in the Informal Dispute Resolution Conference process required by this section. (c) Arbitration Rules and Forum. These Terms evidence a transaction involving interstate commerce; and notwithstanding any other provision herein with respect to the applicable substantive law, the Federal Arbitration Act, 9 U.S.C. § 1 et seq., will govern the interpretation and enforcement of this Arbitration Agreement and any arbitration proceedings. If the Informal Dispute Resolution Process described above does not resolve satisfactorily within 60 days after receipt of your Notice, you and Company agree that either party shall have the right to finally resolve the Dispute through binding arbitration. The Federal Arbitration Act governs the interpretation and enforcement of this Arbitration Agreement. The arbitration will be conducted by JAMS, an established alternative dispute resolution provider. Disputes involving claims and counterclaims with an amount in controversy under $250,000, not inclusive of attorneys’ fees and interest, shall be subject to JAMS’ most current version of the Streamlined Arbitration Rules and procedures available at http://www.jamsadr.com/rules-streamlined-arbitration/; all other claims shall be subject to JAMS’s most current version of the Comprehensive Arbitration Rules and Procedures, available at http://www.jamsadr.com/rules-comprehensive-arbitration/. JAMS’s rules are also available at www.jamsadr.com or by calling JAMS at 800-352-5267. A party who wishes to initiate arbitration must provide the other party with a request for arbitration (the “Request”). The Request must include: (1) the name, telephone number, mailing address, e-mail address of the party seeking arbitration and the account username (if applicable) as well as the email address associated with any applicable account; (2) a statement of the legal claims being asserted and the factual bases of those claims; (3) a description of the remedy sought and an accurate, good-faith calculation of the amount in controversy in United States Dollars; (4) a statement certifying completion of the Informal Dispute Resolution process as described above; and (5) evidence that the requesting party has paid any necessary filing fees in connection with such arbitration. If the party requesting arbitration is represented by counsel, the Request shall also include counsel’s name, telephone number, mailing address, and email address. Such counsel must also sign the Request. By signing the Request, counsel certifies to the best of counsel’s knowledge, information, and belief, formed after an inquiry reasonable under the circumstances, that: (1) the Request is not being presented for any improper purpose, such as to harass, cause unnecessary delay, or needlessly increase the cost of dispute resolution; (2) the claims, defenses and other legal contentions are warranted by existing law or by a nonfrivolous argument for extending, modifying, or reversing existing law or for establishing new law; and (3) the factual and damages contentions have evidentiary support or, if specifically so identified, will likely have evidentiary support after a reasonable opportunity for further investigation or discovery. Unless you and Company otherwise agree, or the Batch Arbitration process discussed in Subsection 10.2(h) is triggered, the arbitration will be conducted in the county where you reside. Subject to the JAMS Rules, the arbitrator may direct a limited and reasonable exchange of information between the parties, consistent with the expedited nature of the arbitration. If the JAMS is not available to arbitrate, the parties will select an alternative arbitral forum. Your responsibility to pay any JAMS fees and costs will be solely as set forth in the applicable JAMS Rules. You and Company agree that all materials and documents exchanged during the arbitration proceedings shall be kept confidential and shall not be shared with anyone except the parties’ attorneys, accountants, or business advisors, and then subject to the condition that they agree to keep all materials and documents exchanged during the arbitration proceedings confidential. (d) Authority of Arbitrator. The arbitrator shall have exclusive authority to resolve all disputes subject to arbitration hereunder including, without limitation, any dispute related to the interpretation, applicability, enforceability or formation of this Arbitration Agreement or any portion of the Arbitration Agreement, except for the following: (1) all Disputes arising out of or relating to the subsection entitled “Waiver of Class or Other Non-Individualized Relief,” including any claim that all or part of the subsection entitled “Waiver of Class or Other Non-Individualized Relief” is unenforceable, illegal, void or voidable, or that such subsection entitled “Waiver of Class or Other Non-Individualized Relief” has been breached, shall be decided by a court of competent jurisdiction and not by an arbitrator; (2) except as expressly contemplated in the subsection entitled “Batch Arbitration,” all Disputes about the payment of arbitration fees shall be decided only by a court of competent jurisdiction and not by an arbitrator; (3) all Disputes about whether either party has satisfied any condition precedent to arbitration shall be decided only by a court of competent jurisdiction and not by an arbitrator; and (4) all Disputes about which version of the Arbitration Agreement applies shall be decided only by a court of competent jurisdiction and not by an arbitrator. The arbitration proceeding will not be consolidated with any other matters or joined with any other cases or parties, except as expressly provided in the subsection entitled “Batch Arbitration.” The arbitrator shall have the authority to grant motions dispositive of all or part of any claim or dispute. The arbitrator shall have the authority to award monetary damages and to grant any non-monetary remedy or relief available to an individual party under applicable law, the arbitral forum’s rules, and these Terms (including the Arbitration Agreement). The arbitrator shall issue a written award and statement of decision describing the essential findings and conclusions on which any award (or decision not to render an award) is based, including the calculation of any damages awarded. The arbitrator shall follow the applicable law. The award of the arbitrator is final and binding upon you and us. Judgment on the arbitration award may be entered in any court having jurisdiction. (e) Waiver of Jury Trial. EXCEPT AS SPECIFIED IN SECTION 10.2(A) YOU AND THE COMPANY PARTIES HEREBY WAIVE ANY CONSTITUTIONAL AND STATUTORY RIGHTS TO SUE IN COURT AND HAVE A TRIAL IN FRONT OF A JUDGE OR A JURY. You and the Company Parties are instead electing that all covered claims and disputes shall be resolved exclusively by arbitration under this Arbitration Agreement, except as specified in Section 10.2(a) above. An arbitrator can award on an individual basis the same damages and relief as a court and must follow these Terms as a court would. However, there is no judge or jury in arbitration, and court review of an arbitration award is subject to very limited review. (f) Waiver of Class or Other Non-Individualized Relief. YOU AND COMPANY AGREE THAT, EXCEPT AS SPECIFIED IN SUBSECTION 10.2(H) EACH OF US MAY BRING CLAIMS AGAINST THE OTHER ONLY ON AN INDIVIDUAL BASIS AND NOT ON A CLASS, REPRESENTATIVE, OR COLLECTIVE BASIS, AND THE PARTIES HEREBY WAIVE ALL RIGHTS TO HAVE ANY DISPUTE BE BROUGHT, HEARD, ADMINISTERED, RESOLVED, OR ARBITRATED ON A CLASS, COLLECTIVE, REPRESENTATIVE, OR MASS ACTION BASIS. ONLY INDIVIDUAL RELIEF IS AVAILABLE, AND DISPUTES OF MORE THAN ONE CUSTOMER OR USER CANNOT BE ARBITRATED OR CONSOLIDATED WITH THOSE OF ANY OTHER CUSTOMER OR USER. Subject to this Arbitration Agreement, the arbitrator may award declaratory or injunctive relief only in favor of the individual party seeking relief and only to the extent necessary to provide relief warranted by the party’s individual claim. Nothing in this paragraph is intended to, nor shall it, affect the terms and conditions under the Subsection 10.2(h) entitled “Batch Arbitration.” Notwithstanding anything to the contrary in this Arbitration Agreement, if a court decides by means of a final decision, not subject to any further appeal or recourse, that the limitations of this subsection, “Waiver of Class or Other Non-Individualized Relief,” are invalid or unenforceable as to a particular claim or request for relief (such as a request for public injunctive relief), you and Company agree that that particular claim or request for relief (and only that particular claim or request for relief) shall be severed from the arbitration and may be litigated in the state or federal courts located in the State of Delaware. All other Disputes shall be arbitrated or litigated in small claims court. This subsection does not prevent you or Company from participating in a class-wide settlement of claims. (g) Attorneys’ Fees and Costs. The parties shall bear their own attorneys’ fees and costs in arbitration unless the arbitrator finds that either the substance of the Dispute or the relief sought in the Request was frivolous or was brought for an improper purpose (as measured by the standards set forth in Federal Rule of Civil Procedure 11(b)). If you or Company need to invoke the authority of a court of competent jurisdiction to compel arbitration, then the party that obtains an order compelling arbitration in such action shall have the right to collect from the other party its reasonable costs, necessary disbursements, and reasonable attorneys’ fees incurred in securing an order compelling arbitration. The prevailing party in any court action relating to whether either party has satisfied any condition precedent to arbitration, including the Informal Dispute Resolution Process, is entitled to recover their reasonable costs, necessary disbursements, and reasonable attorneys’ fees and costs. (h) Batch Arbitration. To increase the efficiency of administration and resolution of arbitrations, you and Company agree that in the event that there are 100 or more individual Requests of a substantially similar nature filed against Company by or with the assistance of the same law firm, group of law firms, or organizations, within a 30 day period (or as soon as possible thereafter), the JAMS shall (1) administer the arbitration demands in batches of 100 Requests per batch (plus, to the extent there are less than 100 Requests left over after the batching described above, a final batch consisting of the remaining Requests); (2) appoint one arbitrator for each batch; and (3) provide for the resolution of each batch as a single consolidated arbitration with one set of filing and administrative fees due per side per batch, one procedural calendar, one hearing (if any) in a place to be determined by the arbitrator, and one final award (“Batch Arbitration”). All parties agree that Requests are of a “substantially similar nature” if they arise out of or relate to the same event or factual scenario and raise the same or similar legal issues and seek the same or similar relief. To the extent the parties disagree on the application of the Batch Arbitration process, the disagreeing party shall advise the JAMS, and the JAMS shall appoint a sole standing arbitrator to determine the applicability of the Batch Arbitration process (“Administrative Arbitrator”). In an effort to expedite resolution of any such dispute by the Administrative Arbitrator, the parties agree the Administrative Arbitrator may set forth such procedures as are necessary to resolve any disputes promptly. The Administrative Arbitrator’s fees shall be paid by Company. You and Company agree to cooperate in good faith with the JAMS to implement the Batch Arbitration process including the payment of single filing and administrative fees for batches of Requests, as well as any steps to minimize the time and costs of arbitration, which may include: (1) the appointment of a discovery special master to assist the arbitrator in the resolution of discovery disputes; and (2) the adoption of an expedited calendar of the arbitration proceedings. This Batch Arbitration provision shall in no way be interpreted as authorizing a class, collective and/or mass arbitration or action of any kind, or arbitration involving joint or consolidated claims under any circumstances, except as expressly set forth in this provision. (i) 30-Day Right to Opt Out. You have the right to opt out of the provisions of this Arbitration Agreement by sending a timely written notice of your decision to opt out to the following address: 2235 3rd St, San Francisco, CA 94107, or email to humans@captain.dev, within 30 days after first becoming subject to this Arbitration Agreement. Your notice must include your name and address and a clear statement that you want to opt out of this Arbitration Agreement. If you opt out of this Arbitration Agreement, all other parts of these Terms will continue to apply to you. Opting out of this Arbitration Agreement has no effect on any other arbitration agreements that you may currently have with us, or may enter into in the future with us. (j) Invalidity, Expiration. Except as provided in the subsection entitled “Waiver of Class or Other Non-Individualized Relief”, if any part or parts of this Arbitration Agreement are found under the law to be invalid or unenforceable, then such specific part or parts shall be of no force and effect and shall be severed and the remainder of the Arbitration Agreement shall continue in full force and effect. You further agree that any Dispute that you have with Company as detailed in this Arbitration Agreement must be initiated via arbitration within the applicable statute of limitation for that claim or controversy, or it will be forever time barred. Likewise, you agree that all applicable statutes of limitation will apply to such arbitration in the same manner as those statutes of limitation would apply in the applicable court of competent jurisdiction. (k) Modification. Notwithstanding any provision in these Terms to the contrary, we agree that if Company makes any future material change to this Arbitration Agreement, you may reject that change within 30 days of such change becoming effective by writing Company at the following address: 2235 3rd St, San Francisco, CA 94107, or email to humans@captain.dev. Unless you reject the change within 30 days of such change becoming effective by writing to Company in accordance with the foregoing, your continued use of the Site and/or Services, including the acceptance of products and services offered on the Site following the posting of changes to this Arbitration Agreement constitutes your acceptance of any such changes. Changes to this Arbitration Agreement do not provide you with a new opportunity to opt out of the Arbitration Agreement if you have previously agreed to a version of these Terms and did not validly opt out of arbitration. If you reject any change or update to this Arbitration Agreement, and you were bound by an existing agreement to arbitrate Disputes arising out of or relating in any way to your access to or use of the Services or of the Site, any communications you receive, any products sold or distributed through the Site, the Services, or these Terms, the provisions of this Arbitration Agreement as of the date you first accepted these Terms (or accepted any subsequent changes to these Terms) remain in full force and effect. Company will continue to honor any valid opt outs of the Arbitration Agreement that you made to a prior version of these Terms. 10.3 Export. The Site may be subject to U.S. export control laws and may be subject to export or import regulations in other countries. You agree not to export, reexport, or transfer, directly or indirectly, any U.S. technical data acquired from Company, or any products utilizing such data, in violation of the United States export laws or regulations. 10.4 Disclosures. Company is located at the address in Section 10.8. If you are a California resident, you may report complaints to the Complaint Assistance Unit of the Division of Consumer Product of the California Department of Consumer Affairs by contacting them in writing at 400 R Street, Sacramento, CA 95814, or by telephone at (800) 952-5210. 10.5 Electronic Communications. The communications between you and Company use electronic means, whether you use the Site or send us emails, or whether Company posts notices on the Site or communicates with you via email. For contractual purposes, you (a) consent to receive communications from Company in an electronic form; and (b) agree that all terms and conditions, agreements, notices, disclosures, and other communications that Company provides to you electronically satisfy any legal requirement that such communications would satisfy if it were be in a hardcopy writing. The foregoing does not affect your non-waivable rights. 10.6 Entire Terms. These Terms constitute the entire agreement between you and us regarding the use of the Site. Our failure to exercise or enforce any right or provision of these Terms shall not operate as a waiver of such right or provision. The section titles in these Terms are for convenience only and have no legal or contractual effect. The word “including” means “including without limitation”. If any provision of these Terms is, for any reason, held to be invalid or unenforceable, the other provisions of these Terms will be unimpaired and the invalid or unenforceable provision will be deemed modified so that it is valid and enforceable to the maximum extent permitted by law. Your relationship to Company is that of an independent contractor, and neither party is an agent or partner of the other. These Terms, and your rights and obligations herein, may not be assigned, subcontracted, delegated, or otherwise transferred by you without Company’s prior written consent, and any attempted assignment, subcontract, delegation, or transfer in violation of the foregoing will be null and void. Company may freely assign these Terms. The terms and conditions set forth in these Terms shall be binding upon assignees. 10.7 Copyright/Trademark Information. Copyright © 2025 Captain Technologies, Inc. All rights reserved. All trademarks, logos and service marks (“Marks”) displayed on the Site are our property or the property of other third parties. You are not permitted to use these Marks without our prior written consent or the consent of such third party which may own the Marks. 10.8 Contact Information: Lewis Polansky. Address: 2235 3rd St, San Francisco, CA 94107. Telephone: 6266953954. Email: humans@captain.dev [ CONTENTS ] [ QUESTIONS ] ## Ask about these terms. Write to us before you sign if a clause does not fit how you work. We answer contract questions in two business days, in plain English. [humans@captain.dev](mailto:humans@captain.dev) [ ENTERPRISE ] ## Sign a custom agreement. Order forms, MSAs, security schedules and a DPA with standard contractual clauses - our team works from your paper or ours. [Talk to us](https://captain.dev/book-a-demo) [ MORE LEGAL ] [[ 01 SECURITY ] Security Where your indexed files live, who can reach them, and the subprocessors we let near them. Read](https://trust.runcaptain.com) [[ 02 PRIVACY ] Privacy Policy What personal data we collect, why we hold it, and the rights you have over it. Read](https://captain.dev/privacy-policy) [[ 03 DATA ] Data Processing Addendum The GDPR-ready DPA, including standard contractual clauses for transfers out of the EU. Read](https://captain.dev/dpa) --- # Edge Routing for RAG · Captain Source: https://captain.dev/blog/edge-routing/ Description: Serving international customers on low latency semantic search. [ BLOG ] ## Edge Routing for RAG Edgar Babajanyan [ CTO & CO-FOUNDER ] Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 ## What changed For developers connecting to our API from outside the United States, we realized the initial handshake with our servers was adding significant latency to every query. Requests to Captain’s API now connect to a local server near you, traveling over a private network backbone to reach us. This bypasses multiple long-distance round trips during the initial handshake. Up to 39% lower latency on international queries. To unlock these gains, we mapped out the journey of international customer queries. We built an edge routing mechanism that works seamlessly with the hostnames and configurations our customers already use. The improvement was immediate, particularly for 'cold' connections, which is how most agent-based tool calls interact with Captain. We measured these gains using median response times from 100 samples per major international geography, using a fresh connection for every request to simulate real-world usage. ## Why we built this When a customer starts an interaction like a RAG process or database retrieval, they initiate a cold connection to Captain. When the tool call fires, the client connects, sends a request, receives a response, and disconnects. Before any search or data processing happens, the connection requires several round trips to negotiate encryption and establish the session. Each round trip travels the full distance between the user and our server twice. From locations like Singapore, that latency adds up. A query that took a few hundred milliseconds of search work spent significantly more time on the handshake process, which carries no data. We realized that while our retrieval was fast, connection overhead was the primary bottleneck. Our new edge routing allows the client to complete these initial round trips with the nearest edge location. The request then travels to Captain over our private backbone on an already warm connection. This preserves our existing search infrastructure and data residency while bringing the connection point much closer to our customers. ## What we found We measured v3 Query end-to-end from seven cities, before and after the change, with 100 samples per city and a fresh connection for every request. Each figure is the median total time from sending the request to receiving the full response. [ CALLING FROM ] [ BEFORE (P50) ] [ AFTER (P50) ] [ CHANGE ] Singapore 1,136 ms 692 ms 39% lower Sydney 1,065 ms 661 ms 38% lower São Paulo 805 ms 590 ms 27% lower Frankfurt 738 ms 555 ms 25% lower Dublin 687 ms 529 ms 23% lower San Francisco 641 ms 516 ms 20% lower Portland 656 ms 551 ms 16% lower [ MEDIAN QUERY TIME ON FRESH CONNECTION * 100 SAMPLES / CITY ] With this improvement, the farther you are from us geographically, the more consistent the experience will be now. Even clients closer to us will see latency improvements (albeit smaller) because requests are still routed much more efficiently. Edge Routing is live and enabled for every API request, on every plan. No need to update API code. Edgar Babajanyan [ CTO & CO-FOUNDER · CAPTAIN ] Edgar is co-founder and CTO of Captain, building self-tuning file search for AI agents. [ CONTENTS ] [ SHARE ] [More posts](https://captain.dev/blog) ### Captain vs. Elasticsearch Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. 5 min read 7 Sep 2026 ### Captain vs. Cloudflare AI Search Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. 6 min read 7 Sep 2026 ### Captain vs. Google RAG Engine Google's RAG Engine ships the parts: a layout parser, an embedding model, a vector store and a reranker, each set up, billed and maintained on its own. Hybrid search needs sparse vectors you compute yourself, and import is a batch job with no rollback. Captain does all of it in one call from your bucket. 5 min read 7 Sep 2026 [ RSS ] Benchmarks, engineering write-ups and the occasional retraction, straight from the source. [Follow the RSS feed](https://captain.dev/blog/rss.xml) --- # Captain vs. Elasticsearch · Captain Source: https://captain.dev/blog/captain-vs-elasticsearch/ Description: Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. [ BLOG / COMPARISONS ] ## Captain vs. Elasticsearch Edgar Babajanyan [ CTO & CO-FOUNDER ] COMPARISON 5 min read 7 Sep 2026 ## One component, or the whole platform Elasticsearch indexes the text Tika hands it. It does not read a scanned page, label a chunk as a table or a footnote, describe a figure, mask a name, or promote a collection from staging to production. Its multimodal field is a technical preview, not recommended for production. Teams cover each gap with another vendor or a pipeline they own, and every seam between them is a contract, an integration and an on-call rotation. Captain runs the whole retrieval layer, from your bucket to the ranked result. Point Captain at the bucket and it takes over from there. It parses every file it finds, scans and handwriting included, chunks by layout, embeds, and keeps the index in step as files are added, changed or removed. PII is masked on the way in. Queries come back as reranked, cited chunks, and the tuning keeps up with the documents: evals drawn from your own files score every adjustment before it lands, so search gets better without a relevance project on your side. ### Why choose Captain over Elasticsearch? One platform covers what a team otherwise assembles around Elasticsearch: OCR and figure descriptions, layout-labeled chunks, cross-modal reranking, an entity model for PII, managed sync with rollback, and environment promotion. Parsing included Each file takes the pipeline it needs: text, page layout, or a vision model for scans and figures. A JavaScript parsing script for JSON files when you need one. Metadata at ingest Every chunk arrives with its layout role, page, bounding box and place in the document, with nothing for you to model. Layout-aware chunking Tables, headings and figures keep their shape through indexing. 20+ sources natively Indexed Search across S3, GCS, Azure, Drive, SharePoint, Notion, Dropbox and Snowflake; Live Search across Slack, Linear, Jira, Confluence, Gmail, HubSpot and NetSuite. Native multimodal Captain indexes images, audio and video directly and reranks across all of them. Operations included Sync keeps the index in step with your files. Jobs roll back, collections copy to production, and PII is masked before anything is embedded. ## How the platforms compare Capability Captain Elasticsearch Document parsing Text, layout and vision parsers, chosen per file Apache Tika text extraction through the attachment ingest processor. Text only, no OCR Scanned documents OCR on every scanned page, included Tesseract or an OCR service; or embed the page as an image with the semantic field, technical preview Figures, charts, complex tables A vision model reads figures, charts and complex tables A VLM pipeline you build; Jina omni embeddings can match visuals, technical preview Chunking Each chunk ends where the layout does: a table, a heading, a paragraph The semantic_text field's fixed-size default, or a chunking library you wire in Embeddings Embeddings chosen and run by Captain Default ELSER endpoint on EIS for English text; pick and configure a model for other languages or media Audio & video Indexed directly, with text and visual embeddings and cross-modal reranking Jina omni embeddings through the semantic field, technical preview; no segmentation or transcription Source connectors S3, GCS, Azure Blob, R2, Supabase Storage, Backblaze B2, Dropbox, Google Drive, SharePoint and OneDrive by API Elastic content connectors, self-managed or Elastic managed on Cloud, or your own ingest code Keeping it current Scheduled reconciliation by ETag, real-time events, deletion policy Scheduled full or incremental connector syncs; your own job for anything without a connector PII redaction Names, IDs and contact details masked before embedding, one flag at index time (mask_pii) Redact processor: Grok patterns, no entity model, paid license Index design One PUT creates the collection; chunk roles and metadata come from the parser Mappings, field types, analyzers Vendors to manage Captain One to several, depending on how much you self-host Parsing & structure PDFs, scans and images OCR, VLM and computer-vision pipelines, advanced or basic processing per job Apache Tika through the attachment processor; scans need Tesseract or an OCR service you run Custom parsing JavaScript parsing scripts for JSON files, validated through the API Write and host your own Layout awareness Every chunk labeled body, table, heading, header, footer, footnote, or figure Extraction flattens structure Layout exclusion Excluded during retrieval, before reranking Filter after the fact, if you indexed the signal Regions & bounding boxes Layout regions per page, returned on request Not produced Page-level access Retrieve any PDF page directly, text and regions Not produced Chunk metadata Set after indexing, filterable and boostable without a re-index A field you add to the mapping and maintain Graph relations Typed chunk relations (a claim linked to its risk statement, a figure to its caption), with direction control Join fields or a parent-child mapping you design Citation basis Page ranges, chunk index, media timestamps, sheet and row/column ranges Whatever fields you indexed and returned Retrieval Method Hybrid BM25 + dense vector, fused Keyword (BM25), dense vector and Elastic's ELSER sparse model, fused by reciprocal rank fusion Configuration One parameter, semantic_ratio, from pure keyword to pure semantic Retriever trees you assemble and tune Reranking On by default for multimodal collections, one flag for text, about 200 ms text_similarity_reranker retriever with a preconfigured Jina or Elastic Rerank endpoint Boosting Metadata boost rules that can outrank the reranker, with a guaranteed slot per rule Function score, query rules, or scoring you write Multimodal ranking Native cross-modal reranking across text, image, audio, video Available through Jina omni models and the semantic field, in technical preview and not recommended for production Effort to good results One query call returns ranked, cited chunks Mappings, analyzers, retriever tuning and a reranker: a relevance project Operations Infrastructure Hosted by Captain, no cluster to size or patch Cluster, shards, replicas, ML nodes; or Elastic Cloud Hosted or Serverless Indexing jobs Job status, cancel, and rollback built in Connector sync status and cancel in Kibana; no rollback Staging to production One call copies a collection into production Reindex or replicate yourself Multi-tenancy Collections per tenant plus metadata filters per query Indices, aliases, document-level security Access control Metadata filters scope every query to a user, team or tier Document level security roles; connector DLS in beta Relevance feedback loop Reviewer-tagged boosts with reserve, plus the MCP evaluate-and-tune loop Query rules to pin or exclude; analytics you build Agent integration Hosted MCP server, 48 tools Agent Builder MCP server in Kibana, API key or OAuth Compliance SOC 2, HIPAA, GDPR, more on request Elastic Cloud: SOC 2, HIPAA, ISO 27001; self-managed is yours Edgar Babajanyan [ CTO & CO-FOUNDER · CAPTAIN ] Edgar is co-founder and CTO of Captain, building self-tuning file search for AI agents. [ CONTENTS ] ### Which one fits your application? Copy prompt I'm deciding between Captain (captain.dev) and Elasticsearch for retrieval in this project. Look at my stack, my documents and what I need from search. If you can't see them, ask me before you answer. These claims are written by Captain, on its comparison page (https://www.captain.dev/blog/captain-vs-elasticsearch/). If you can open URLs, verify anything you rely on against both vendors' docs. If you cannot, say so in one line and answer from the claims below; do not describe fetching them, and do not ask me to paste documentation. Captain's docs index for agents is https://docs.captain.dev/llms.txt, Elastic's docs are at https://www.elastic.co/docs/. - Scope: Elasticsearch extracts text with its built-in Tika attachment processor and chunks and embeds with semantic_text and a default ELSER endpoint. It has no OCR, no layout roles on chunks, no figure descriptions, no entity model for PII, and its multimodal field is a technical preview not recommended for production. Captain includes OCR, VLM and vision parsing, layout-labeled chunks, cross-modal reranking, PII masking and continuous sync behind one index call. - Sources: Captain syncs from S3, GCS, Azure Blob, R2, Supabase Storage, Backblaze B2, Dropbox, Google Drive, SharePoint and OneDrive, with reconciliation, job status, cancel and rollback. Elasticsearch uses content connectors with scheduled syncs, or code the team writes. - File limits: Captain reads files straight from a cloud storage bucket, no upload step. PDF, Office, image, audio and video files have no size cap of their own; text, JSON, CSV and code files are capped at 250 MB; images at 200 megapixels. - Layout: Captain labels every chunk body, table, heading, header, footer, footnote or figure, and can exclude roles before reranking. Elasticsearch extraction flattens structure; filtering after the fact needs the signal to have been indexed. - Retrieval: Captain fuses BM25 and dense vectors with one parameter, semantic_ratio, reranks by default on multimodal collections, one flag on text collections, in about 200 ms, and supports metadata boost rules that can outrank the reranker. Elasticsearch offers BM25, dense kNN and ELSER sparse fused with RRF, configured through retriever trees the team assembles and tunes, with reranking through an inference endpoint the team wires in. - Metadata and relations: Captain sets chunk metadata after indexing, filterable and boostable without a re-index, and supports typed chunk-to-chunk relations. In Elasticsearch both are modelled in the index by the team. - Multimodal: Captain indexes images, audio and video natively with cross-modal reranking. Elasticsearch offers multimodal ranking through Jina omni models and the semantic field, in technical preview and not recommended for production. - PII: Captain masks PII at index time with an NER model, opt-in per job. Elasticsearch has a redact processor built on Grok patterns. - Operations: Captain is hosted, with job rollback, collection copy and environment promotion built in. Elasticsearch means a cluster with shards, replicas and ML nodes, or Elastic Cloud, with orchestration the team owns. - Compliance: Captain states SOC 2 Type II, HIPAA attestation and GDPR alignment on captain.dev/security. Elastic Cloud lists SOC 2, HIPAA and ISO 27001; self-managed compliance is the team's own. - Files in a code repository: Captain indexes from cloud storage and drives, not from GitHub directly; a repo is synced by mirroring it to a bucket. If something you need is not stated above (pricing numbers, hosting regions, whether Captain signs a BAA or DPA, latency figures beyond the rerank step), say that it is not stated and tell me to ask the vendor. Do not fill the gap with a guess, and do not estimate how long the Elasticsearch route would take to build. Tell me which one fits this project and why, what I'd give up with each, and which two claims to verify first for my case. If this project already runs Elasticsearch for logs or product search, the documents are clean text, and the team has a relevance engineer, say plainly that staying on Elasticsearch may be the right call. [ EXPAND ] [ SHARE ] [More posts](https://captain.dev/blog) ### Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 ### Captain vs. Cloudflare AI Search Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. 6 min read 7 Sep 2026 ### Captain vs. Google RAG Engine Google's RAG Engine ships the parts: a layout parser, an embedding model, a vector store and a reranker, each set up, billed and maintained on its own. Hybrid search needs sparse vectors you compute yourself, and import is a batch job with no rollback. Captain does all of it in one call from your bucket. 5 min read 7 Sep 2026 [ RSS ] Benchmarks, engineering write-ups and the occasional retraction, straight from the source. [Follow the RSS feed](https://captain.dev/blog/rss.xml) --- # Captain vs. Cloudflare AI Search · Captain Source: https://captain.dev/blog/captain-vs-cloudflare-ai-search/ Description: Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. [ BLOG / COMPARISONS ] ## Captain vs. Cloudflare AI Search Edgar Babajanyan [ CTO & CO-FOUNDER ] COMPARISON 6 min read 7 Sep 2026 ## What the platform decides for you Cloudflare AI Search indexes an R2 bucket, converts what it finds to Markdown, chunks it, embeds it with Workers AI, and answers from a Vectorize index. If your stack already runs on Workers and your content is Markdown and small PDFs, it gets a RAG pipeline running in an afternoon. Captain indexes the files you have across any cloud, any size, any layout. Optimized for your agent. ### Why choose Captain over Cloudflare AI Search? Captain reads files of any size from your bucket, chunks them by page layout and stores metadata of any shape. AI Search caps files at 4 MB, chunks by token count and allows five metadata fields, each cut at 64 bytes. Parsing that fits the file A scanned form and a Markdown file take different paths through parsing. Layout preserved Every chunk knows whether it came from a table, a heading or a footer. Every result knows its place Page range, region, spreadsheet cell or media timestamp come back with every result, ready to cite. Metadata of any shape Nested filters, boosts, and values you can set per chunk after indexing without a re-index. Reserved capacity Indexing runs on throughput reserved for you, so a big backfill never waits on a shared daily quota. Redaction before embedding PII is masked before anything is embedded. A file that cannot be masked is held back, never stored unmasked. ## How the platforms compare Capability Captain Cloudflare AI Search Maximum file size Read from your bucket, no upload step. PDF, Office, images, audio and video have no cap of their own; text, JSON and CSV files up to 250 MB each 4 MB on every plan Maximum size, text and data files 250 MB per file for Markdown, JSON, CSV, YAML and code 4 MB on every plan Chunk size ceiling Each chunk ends where the layout does: a table, a heading, a paragraph Token count, range varies by model, overlap capped at 30% Embedding model Chosen and managed by Captain, optimized for accuracy and speed Text embeddings only, fixed at creation: a Workers AI model (bge-m3, bge-large, qwen3-embedding, embeddinggemma), OpenAI text-embedding-3, or Google gemini-embedding-001 Changing the embedding model Captain re-embeds the collection when the model changes. Your data and your calls stay the same Not possible after creation LLM for generation Captain returns ranked chunks. Your AI system runs the generation Workers AI, or OpenAI and Anthropic through AI Gateway Data sources Any number per collection, added or changed at any time Built-in uploads plus one R2 bucket or one website Custom metadata fields Unlimited, at file and chunk level 5 per instance Metadata size Nested objects with a full operator set 10 KiB per vector Filterable string data Full value First 64 UTF-8 bytes Filter logic Nested composition to depth 10 One flat AND across keys with eight operators, no nesting Indexing at scale Compute source Flexible indexing capacity Your Workers AI allocation When capacity runs out Jobs keep running on capacity reserved for you Files error with workers_ai_out_of_capacity_error How changes are detected Webhook events from your bucket land within seconds, with scheduled reconciliation as the backstop A scheduled listing of the source What counts as a change Each object's content hash (ETag) against the one Captain last indexed, so only changed files re-index Not documented Reconciliation cadence As often as every 5 minutes, or manual only Every 6 hours by default, adjustable from 1 to 24 hours Manual sync On demand At most once every 30 seconds Deleted files Your policy per sync: mirror, archive, or ignore Removed on the next sync Sources per collection S3, GCS, Azure Blob, R2, Supabase Storage, Backblaze B2, Dropbox, Google Drive, SharePoint and OneDrive, several at once, each tracked on its own Built-in uploads plus one R2 bucket or one website Job control Status, cancel, rollback, reconcile Trigger, cancel, pause, resume, re-sync one file Files per instance Terabytes per collection 100,000 free, 1M paid, 500,000 if you use hybrid search Recovering a failed run Roll back the job Fix the item, then sync it again Understanding the document Parsing Each file takes the pipeline it needs: text, page layout, or vision Markdown conversion for every file type Images Indexed natively, with cross-modal reranking Object detection, then a caption is embedded Audio and video Indexed natively, with text and visual embeddings Not supported Layout roles Seven layout roles (body, table, heading, header, footer, footnote, figure), any of them excludable at query time None. Everything becomes Markdown Position in a document Page ranges, chunk index, sheet and cell ranges Filename and folder only Spatial grounding Bounding boxes and region mapping No Page retrieval Any page, fetched directly No Chunk relations Typed edges with direction control No Retrieval Method Hybrid keyword (BM25) and dense vector, fused. The file limit is the same either way Vector and BM25, fused. Hybrid halves your file limit to 500,000 Keyword control One parameter, semantic_ratio, from pure keyword to pure semantic Configurable fusion method Result count limit, 1 to 100 max_num_results, maximum 50 Score breakdown Vector, BM25, fusion, and rerank scores per result Vector, keyword and rerank scores when hybrid search is on Boosting Metadata boost rules that can outrank the reranker No Query enhancement Metadata boosts and reviewer feedback Rewriting through a Workers AI model Data protection PII masking At index time, opt-in per job No Masking coverage Parsed text, region text, and image pixels None Regulated-document recognizers NMLS IDs, surety bonds, carriers, and bond principals None When masking fails The file is held back, never stored unmasked None Healthcare and life sciences HIPAA-ready. Fair balance for FDA-regulated content through chunk relations: a benefit claim is linked to its risk statement, so retrieval returns both together Not covered in the AI Search docs Deployment Hosted, BYOC, or on-premise Cloudflare's network Maturity Generally available: stable v2 API since January 2026, SOC 2 Type II, published pricing Open beta, pricing not yet announced ## Where Cloudflare AI Search fits Cloudflare built a good on-ramp for existing users, but its architectural limitations keep the product from being truly dependable infrastructure. If you are already on Workers, your content is Markdown and small PDFs, and you want retrieval running today without choosing a vector database, it does that well and currently costs nothing beyond Workers AI usage. The ceiling arrives with the first document that doesn't fit. A 12 MB scanned contract gets rejected. A financial statement comes back as flat Markdown, so nobody can tell which table a number came from. A tenant filter over 64 bytes stops matching. A big backfill stalls the moment the account's Workers AI allocation runs out. Captain reads the contract from the bucket, keeps the table, matches the filter, and runs the backfill on capacity reserved for you. That is the day-one job for most real document sets. Edgar Babajanyan [ CTO & CO-FOUNDER · CAPTAIN ] Edgar is co-founder and CTO of Captain, building self-tuning file search for AI agents. [ CONTENTS ] ### Which one fits your application? Copy prompt I'm deciding between Captain (captain.dev) and Cloudflare AI Search for retrieval in this project. Look at my stack, my documents and what I need from search. If you can't see them, ask me before you answer. These claims are written by Captain, on its comparison page (https://www.captain.dev/blog/captain-vs-cloudflare-ai-search/). If you can open URLs, verify anything you rely on against both vendors' docs. If you cannot, say so in one line and answer from the claims below; do not describe fetching them, and do not ask me to paste documentation. Captain's docs index for agents is https://docs.captain.dev/llms.txt, Cloudflare's docs are at https://developers.cloudflare.com/ai-search/. - File size: Captain reads files straight from a cloud storage bucket, no upload step. PDF, Office, image, audio and video files have no size cap of their own; text, JSON, CSV and code files are capped at 250 MB; images at 200 megapixels. AI Search caps files at 4 MB on every plan. - Chunking and layout: Captain chunks by page layout and keeps seven layout roles that can be excluded at query time. AI Search converts every file to Markdown and chunks by token count. - Metadata and filters: Captain allows metadata of any shape with nested filters and boosts, settable per chunk after indexing. AI Search allows five custom fields, filters strings on their first 64 bytes, and supports one flat AND across keys. - Sync: Captain syncs from S3, GCS, Azure Blob, R2, Supabase Storage, Backblaze B2, Dropbox, Google Drive, SharePoint and OneDrive, several sources per collection, using webhook events plus reconciliation as often as every 5 minutes, with job status, cancel and rollback. AI Search syncs built-in uploads plus one R2 bucket or one website, every 6 hours by default, adjustable from 1 to 24 hours. - Embeddings and generation: Captain chooses and manages its own embeddings and returns ranked, cited chunks to whatever LLM the application runs. AI Search fixes one text embedding model at creation and can generate answers with Workers AI or with OpenAI and Anthropic through AI Gateway. - Modalities: Captain indexes images, audio, video and spreadsheets natively. AI Search indexes documents and images; audio and video are not supported. - PII: Captain masks PII at index time, opt-in per job, and holds back a file it cannot mask. AI Search has no masking. - Regulated content: Captain is HIPAA-ready and supports fair balance for FDA-regulated material through chunk relations, linking a benefit claim to its risk statement so retrieval returns both. AI Search's docs do not cover either. - Capacity and maturity: Captain runs indexing on capacity reserved per customer, is generally available with a stable v2 API since January 2026, SOC 2 Type II and published pricing. AI Search indexing draws on the account's Workers AI allocation and is in open beta with pricing not yet announced. - Files in a code repository: Captain indexes from cloud storage and drives, not from GitHub directly; a repo is synced by mirroring it to a bucket. AI Search indexes an R2 bucket or a website, so the same applies. If something you need is not stated above (pricing numbers, hosting regions, whether Captain signs a BAA or DPA, latency figures beyond the rerank step), say that it is not stated and tell me to ask the vendor. Do not fill the gap with a guess, and do not estimate how long the Cloudflare AI Search route would take to build. Tell me which one fits this project and why, what I'd give up with each, and which two claims to verify first for my case. If this project already runs on Cloudflare Workers and the files are small Markdown or PDFs, say plainly that AI Search may be enough. [ EXPAND ] [ SHARE ] [More posts](https://captain.dev/blog) ### Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 ### Captain vs. Elasticsearch Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. 5 min read 7 Sep 2026 ### Captain vs. Google RAG Engine Google's RAG Engine ships the parts: a layout parser, an embedding model, a vector store and a reranker, each set up, billed and maintained on its own. Hybrid search needs sparse vectors you compute yourself, and import is a batch job with no rollback. Captain does all of it in one call from your bucket. 5 min read 7 Sep 2026 [ RSS ] Benchmarks, engineering write-ups and the occasional retraction, straight from the source. [Follow the RSS feed](https://captain.dev/blog/rss.xml) --- # Captain vs. Google RAG Engine · Captain Source: https://captain.dev/blog/captain-vs-google-rag-engine/ Description: Google's RAG Engine ships the parts: a layout parser, an embedding model, a vector store and a reranker, each set up, billed and maintained on its own. Hybrid search only works through a Weaviate database you run yourself, and import is a batch job with no rollback. Captain does all of it in one call from your bucket. [ BLOG / COMPARISONS ] ## Captain vs. Google RAG Engine Edgar Babajanyan [ CTO & CO-FOUNDER ] COMPARISON 5 min read 7 Sep 2026 ## What you assemble, and what you get Google's RAG Engine hands you a corpus, a parser, an embedding model, a vector store and a reranker, each provisioned and billed on its own, with hybrid search only through a Weaviate database you run. Captain indexes straight from the GCS bucket you already have and gives you hybrid search, reranking and layout-aware parsing in one API call. Every control you would otherwise wire in yourself is already inside the query. ### Why choose Captain over Google RAG Engine? Captain ships hybrid retrieval, reranking, layout-aware parsing and continuous sync in one call. On RAG Engine each of those is a separate component: you wire them together, you pay for each one on its own line, and you keep them running. Hybrid built in BM25 and vectors fused in every query. RAG Engine gets hybrid search only through a Weaviate database you provision and run. Reranking included About 200 ms, inside the query. RAG Engine's rerankers are a second service, the ranking API or a Gemini call, each billed on its own. Layout on every chunk Seven roles, excludable at retrieval. RAG Engine's layout parser exposes none. Synced from your storage Continuous sync with reconciliation and rollback. RAG Engine copies files in by batch import, with no rollback. Multimodal and spreadsheets Images, audio, video and sheets indexed natively. RAG Engine lists documents only, images through the LLM parser; other types index with lower-quality results, in Google's words. Any model Ranked, cited chunks for any model. RAG Engine's Tool needs an Agent Platform model, and its LLM reranker and LLM parser need Gemini. ## How the platforms compare Capability Captain RAG Engine Product type Search API: index a bucket, query for ranked chunks Managed RAG pipeline: corpora, retrieveContexts, a retrieval Tool for Agent Platform models Returns Ranked chunks with scores and citations Contexts with text, source, one score and a page span Citation basis Page ranges, chunk index, media timestamps, sheet and cell ranges Source URI, file and chunk IDs, page span only Model compatibility Any model, any provider Any model for raw contexts; the Tool needs an Agent Platform model, the LLM reranker and LLM parser need Gemini Agent integration Any tool-call format, plus a hosted MCP server Retrieval Tool for generateContent and ADK; your own layer elsewhere Retrieval control Method Hybrid BM25 + dense, fused; keyword side built in Dense by default; hybrid only through a Weaviate database you provision (Preview) Keyword/semantic balance One parameter, semantic_ratio, from pure keyword at 0 to pure semantic at 1 hybrid_search.alpha 0 to 1, Weaviate corpora only Reranking Included, ~200 ms, inside the query Agent Platform ranking API (under 100 ms) or LLM reranker (1 to 2 s), set in the retrieval config, each billed on its own Result count limit, 1-100 top_k plus distance thresholds Boosting Up to 10 metadata boost rules per request, each raising or reserving matching chunks None Guaranteed slot A reserve on a boost rule keeps that chunk in the results even if the reranker scores it low N/A Score visibility Vector, BM25, fusion and rerank scores per result One score Indexing & structure Parsing Automatic OCR, VLM and computer vision pipelines Three parsers: default (free), Document AI layout and LLM, the last two billed to your project Chunking Layout-aware, automatic Fixed-size chunk_size and overlap; layout only with the layout parser Layout awareness Every chunk labeled: body, table, heading, header, footer, footnote, figure Chunks follow a layout entity; no role exposed Layout exclusion Any role dropped at query time, before reranking Not available Document metadata Nested filters to depth 10 with a full operator set metadata_filter on files, CEL expression over a typed schema; v1beta1 Preview, not in Serverless mode Chunk-level metadata Set after indexing without a re-index, used in filters and boosts No Graph relations Typed chunk-to-chunk edges No Bounding boxes Optional region data per chunk No Data & operations Ingest sources S3, GCS, Azure, R2, Supabase, Backblaze, Dropbox, Google Drive, SharePoint, OneDrive, URL, YouTube Cloud Storage, Drive, Slack, Jira, SharePoint; 25 MB direct upload Where data lives Indexed from your own storage Copied into a corpus on Spanner, Vector Search 1.0 or 2.0, Weaviate, Pinecone or Feature Store Sync Continuous, with reconciliation, rollback and webhooks Batch import via ragFiles.import; re-import skips unchanged files; no scheduled sync, no rollback Multi-tenancy Collections plus metadata-enforced scoping A corpus per tenant, or metadata_filter PII handling Text and image redaction before indexing None in RAG Engine; Sensitive Data Protection (Cloud DLP) is a separate product Deployment Hosted, BYOC or on-prem Google Cloud only; 4 GA regions (2 allowlisted), 18 in preview; no data residency Pricing model Indexing and query credits; reranking included Separate lines: database tier, embeddings, parsers, reranker Compliance SOC 2, HIPAA, GDPR Google Cloud terms; VPC-SC and CMEK (Spanner mode only) Coverage & limits Documents & code PDF, Office, spreadsheets, text, code and more PDF and DOCX to 50 MB; PPTX, HTML, JSON, Markdown and text to 10 MB Images Native, with cross-modal reranking LLM parser only Spreadsheets Native, with sheet and cell ranges Not in the supported list; other types 'can generate lower-quality responses' Audio & video Indexed natively, with text and visual embeddings Not in the supported list; other types 'can generate lower-quality responses' Per-file limit Reads from your bucket, no upload step; text and code to 250 MB, images to 200 megapixels 50 MB PDF and DOCX, 10 MB other text; 20 MB and 500 pages with the layout parser Corpus scale TB scale Spanner tiers up to 10 nodes; Vector Search beyond Edgar Babajanyan [ CTO & CO-FOUNDER · CAPTAIN ] Edgar is co-founder and CTO of Captain, building self-tuning file search for AI agents. [ CONTENTS ] ### Which one fits your application? Copy prompt I'm deciding between Captain (captain.dev) and Google's RAG Engine for retrieval in this project. RAG Engine is the one on the Gemini Enterprise Agent Platform, formerly Vertex AI RAG Engine. Look at my stack, my documents and what I need from search. If you can't see them, ask me before you answer. These claims are written by Captain, on its comparison page (https://www.captain.dev/blog/captain-vs-google-rag-engine/). If you can open URLs, verify anything you rely on against both vendors' docs. If you cannot, say so in one line and answer from the claims below; do not describe fetching them, and do not ask me to paste documentation. Captain's docs index for agents is https://docs.captain.dev/llms.txt, Google's docs are at https://docs.cloud.google.com/vertex-ai/generative-ai/docs/rag-engine/rag-overview. - Shape: Captain is a search platform and API that returns ranked chunks with scores and citations to any model. RAG Engine is a managed pipeline of corpora, retrieveContexts and a Gemini Tool; raw contexts work with any model, the Tool needs an Agent Platform model, the LLM reranker and LLM parser need Gemini. - Retrieval: Captain fuses BM25 and dense vectors with one parameter, semantic_ratio, reranks inside the query in about 200 ms, and supports up to 10 boost rules per request with a reserve that keeps a boosted chunk in. RAG Engine is dense by default; hybrid search works only through a Weaviate database the team provisions, and reranking is set in the retrieval config through the Agent Platform ranking API or an LLM reranker, each billed on its own. - Parsing and layout: Captain routes each file through OCR, VLM or vision pipelines by complexity, chunks by layout, and labels every chunk with a role that can be excluded before reranking. RAG Engine offers three parsers (default is free, Document AI layout and LLM are billed to the project), fixed-size chunking with overlap, and no exposed layout role. - Metadata and relations: Captain supports nested document metadata, chunk-level metadata set after indexing, typed chunk relations and optional bounding boxes. RAG Engine supports metadata_filter on documents only. - Sources and sync: Captain indexes straight from S3, GCS, Azure Blob, R2, Supabase Storage, Backblaze B2, Dropbox, Google Drive, SharePoint, OneDrive, URLs and YouTube, with scheduled reconciliation and webhook events on the bucket sources, rollback included. RAG Engine imports from Cloud Storage, Drive, Slack, Jira and SharePoint (25 MB direct upload) in batches, copying files into a corpus on Spanner, Vector Search 1.0 or 2.0, Weaviate, Pinecone or Feature Store, with no continuous sync and no rollback. - File limits: Captain reads files straight from a bucket, no upload step. PDF, Office, image, audio and video files have no size cap of their own; text, JSON, CSV and code files are capped at 250 MB; images at 200 megapixels. RAG Engine caps PDF and DOCX at 50 MB, other text formats at 10 MB, and the layout parser at 20 MB and 500 pages. - Modalities: Captain indexes images (with cross-modal reranking), spreadsheets (with sheet and cell ranges), audio and video natively. RAG Engine handles images through the LLM parser only; spreadsheets, audio and video are not on the supported list and Google says other types give lower-quality results. - PII: Captain redacts text and images before indexing, opt-in per job. RAG Engine has none; Cloud DLP is a separate product. - Deployment and compliance: Captain is hosted, BYOC or on-prem, SOC 2 Type II, HIPAA-ready, GDPR-ready. RAG Engine is Google Cloud only, 4 GA regions (2 allowlisted) and 18 in preview, under Google Cloud terms. - Pricing shape: Captain bills indexing and query credits with reranking included. RAG Engine bills separate lines for the database tier, embeddings, parsers and reranker. - Files in a code repository: Captain indexes from cloud storage and drives, not from GitHub directly; a repo is synced by mirroring it to a bucket. If something you need is not stated above (pricing numbers, hosting regions, whether Captain signs a BAA or DPA, latency figures beyond the rerank step), say that it is not stated and tell me to ask the vendor. Do not fill the gap with a guess, and do not estimate how long the RAG Engine route would take to build. Tell me which one fits this project and why, what I'd give up with each, and which two claims to verify first for my case. If this project is all-in on Gemini, the documents are clean PDFs under 50 MB in Cloud Storage, and the team wants one Google bill, say plainly that RAG Engine may be enough. [ EXPAND ] [ SHARE ] [More posts](https://captain.dev/blog) ### Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 ### Captain vs. Elasticsearch Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. 5 min read 7 Sep 2026 ### Captain vs. Cloudflare AI Search Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. 6 min read 7 Sep 2026 [ RSS ] Benchmarks, engineering write-ups and the occasional retraction, straight from the source. [Follow the RSS feed](https://captain.dev/blog/rss.xml) --- # Copy Collections · Captain Source: https://captain.dev/blog/copy-collections/ Description: You can now copy collections in Captain. One API call duplicates the documents, chunks, embeddings, and custom metadata under a new collection name, reusing the index you already built. [ BLOG ] ## Copy Collections Lewis Lien Polansky [ CEO & CO-FOUNDER ] You can now copy collections in Captain. One API call duplicates the documents, chunks, embeddings, and custom metadata under a new collection name, reusing the index you already built. 5 min read 18 Aug 2026 [ FIG. 00 · ONE API CALL DUPLICATES DOCUMENTS, CHUNKS, EMBEDDINGS AND METADATA ] You can now copy collections in Captain. One API call duplicates the documents, chunks, embeddings, and custom metadata under a new collection name, reusing the index you already built. ## One call, one copy [ COPY-COLLECTION.SH ] [ COPY COPIED ] ``` curl -X POST https://api.captain.dev/v2/collections/shipping_manuals/copy \ -H "Authorization: Bearer $CAPTAIN_API_KEY" \ -H "Content-Type: application/json" \ -d '{"target_name": "shipping_manuals_staging"}' ``` [ FIG. 01 · THE WHOLE OPERATION, IN ONE REQUEST ] Copied collections are fully independent. Writes and deletes stay scoped to the collection they were issued against. ## Why we built it Three requests kept coming up: ### One collection per customer. If you run retrieval for many end clients, each client's data belongs in its own collection: separate indexes and separate deletes. Standing up client number forty used to mean re-indexing a shared corpus for the fortieth time. Now you can index the base corpus once, then easily copy it per client. ### Staging copies. Sometimes a collection needs to branch. Production stays on the settings your users depend on while a copy absorbs the change you're not sure about yet: a different parsing configuration, a new chunk relationship setup, a different PII masking policy. Test against the copy with real data, and when the branch proves out, cut over. When it drifts too far, you can delete it and copy again. ### Experiments. Snapshot a collection before a risky change. If the experiment fails, delete the copy and the original is untouched. ## What it used to cost Before this endpoint, duplicating a collection meant re-indexing it from the source files: paying indexing credits on every document again, then waiting on the job queue, sometimes for hours, before the duplicate was usable. A copy is a flat 10 credits, billed once the copy succeeds. Because the vectors are copied rather than rebuilt, the operation completes in about a second. Both numbers hold at any collection size. Here it is against a real collection: [ REQUEST.SH ] [ COPY COPIED ] ``` curl -X POST https://api.captain.dev/v2/collections/blog_demo_shipping_manuals/copy \ -H "Authorization: Bearer $CAPTAIN_API_KEY" \ -H "Content-Type: application/json" \ -d '{"target_name": "blog_demo_shipping_manuals_staging"}' ``` [ FIG. 02 · THE REQUEST ] [ 200 OK · 1.28S ] [ COPY COPIED ] ``` { "success": true, "message": "Copied 'blog_demo_shipping_manuals' to 'blog_demo_shipping_manuals_staging' (6 documents)", "source_collection": "blog_demo_shipping_manuals", "collection_name": "blog_demo_shipping_manuals_staging", "collection_id": "01a01749-7d73-7401-89ec-8261383d631c", "documents_copied": 6, "files_copied": 6, "namespaces_copied": 1 } ``` [ FIG. 03 · THE RESPONSE, 1.28 SECONDS LATER ] ## Details - POST /v2/collections/{collection_name}/copy with a target_name in the body. - The target name must be unused in the collection's environment; a taken name returns a 409. - Copies land in the same environment as the source and behave like any other collection: query them, index into them, delete them. Reference documentation for the endpoint is at docs.captain.dev/reference/collections/copy. Lewis Lien Polansky [ CEO & CO-FOUNDER · CAPTAIN ] Lewis is co-founder and CEO of Captain, building self-tuning file search for AI agents. [ CONTENTS ] [ SHARE ] [More posts](https://captain.dev/blog) ### Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 ### Captain vs. Elasticsearch Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. 5 min read 7 Sep 2026 ### Captain vs. Cloudflare AI Search Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. 6 min read 7 Sep 2026 [ RSS ] Benchmarks, engineering write-ups and the occasional retraction, straight from the source. [Follow the RSS feed](https://captain.dev/blog/rss.xml) --- # Migrating from Ragie to Captain · Captain Source: https://captain.dev/blog/ragie-to-captain-migration/ Description: Ragie's hosted service will end on Sunday, July 19, 2026. To help customers keep their applications running, many Ragie customers have been migrating to Captain. [ BLOG ] ## Migrating from Ragie to Captain Lewis Lien Polansky [ CEO & CO-FOUNDER ] Ragie's hosted service will end on Sunday, July 19, 2026. To help customers keep their applications running, many Ragie customers have been migrating to Captain. 9 min read 14 Jul 2026 [ FIG. 00 · FOUR STEPS FROM A RAGIE INDEX TO A CAPTAIN COLLECTION ] Ragie's hosted service will end on Sunday, July 19, 2026. To help customers keep their applications running, many Ragie customers have been migrating to Captain. ## In short Captain provides managed multimodal indexing and retrieval for AI applications. Most customers with access to their original source data can begin setting up their migration in under 15 minutes. Need help migrating? Email humans@captain.dev with your company name, approximate data volume, and current Ragie integrations. ## Step 1: Locate your source data First, determine where your original documents and data are stored. If your data remains available in a source such as local storage, Amazon S3, Google Drive, Google Cloud Storage, Dropbox, or another supported storage system, you can connect that source directly to Captain. You do not need to move the original data through Ragie first. If the only copy of your data is stored in Ragie, email support@ragie.ai as soon as possible with: - The subject line “Data export request” - Your company name - The email address associated with your Ragie account - Any relevant partition or dataset information Ragie will provide current information about export availability, processing time, pricing, and the data included in the export. Because exports require manual processing, customers should submit requests as early as possible. ## Step 2: Create your Captain collection Captain organizes indexed data into collections. A Captain collection generally serves the same role as a Ragie partition: it provides a logical boundary for a particular application, customer, workspace, or dataset. Captain can index text, documents, images, audio, video, and other file types. It includes document parsing, hybrid search, reranking, relationships between related chunks, multimodal understanding, and built-in retrieval evaluations. To receive migration assistance, email humans@captain.dev with: - Your company name - Your approximate number of documents or total file volume - Your current Ragie integrations - Your target migration date (if you have one) - Any features or workflows that are critical to your application Captain is providing hands-on migration support and discounted pricing for Ragie customers. Using an AI coding assistant? Provide docs.runcaptain.com/llms.txt as context for current Captain API documentation and migration guidance. ## Step 3: Connect or upload your data Captain currently supports sources including: - Local files - Web pages and URLs - Amazon S3 - Google Cloud Storage - Azure Blob Storage - Cloudflare R2 - Dropbox - Supabase Storage - Backblaze B2 - Google Drive - Microsoft SharePoint - Microsoft OneDrive - Notion - Snowflake See Captain’s documentation for specific guides and endpoints. Some integrations are available through Captain Studio but do not yet support programmatic indexing through the Captain API. Captain’s team can confirm the best migration method for your particular sources. When migrating exported Ragie data, Captain will help determine whether the export should be uploaded directly, transformed, or reindexed from the underlying source documents. In most cases, Captain will generate a new index rather than relying on previously generated embeddings. ## Step 4: Update your application After your indexing jobs complete successfully, update your application to query the corresponding Captain collection through Captain’s v3 Query API. Before directing production traffic to the new collection, test a representative set of existing searches and application workflows. Compare the returned results, citations, metadata, filters, latency, and access-control behavior with your existing Ragie implementation. Once you have validated retrieval quality and application behavior, update your production credentials and endpoint configuration to direct traffic to Captain. Captain’s migration team is prioritizing Ragie customers during the transition. Contact humans@captain.dev for assistance mapping your existing implementation to Captain. ## Frequently asked questions ### Can my application remain online during the migration? In most cases, yes. You can build and test your Captain collection while your current Ragie integration remains active, then switch your application after validating the new setup. Because Ragie’s hosted service is scheduled to end on July 19, customers should begin the process immediately and allow enough time for indexing and testing. ### How long does indexing take? Indexing time depends on the number, size, and type of files being processed. Large initial migrations may require a temporary indexing-capacity increase. Contact Captain in advance if your initial migration is large so the team can help plan appropriate indexing capacity. ### How does pricing work? Captain is offering discounted pricing for transitioning Ragie customers. Contact humans@captain.dev with your company name and expected data volume to receive migration pricing. ### What if Captain does not support one of my Ragie integrations? Tell Captain which integration or workflow is blocking your migration. The team will assess the requirement and determine whether it can provide a workaround, migration service, or prioritized integration support. During the Ragie migration effort, Captain has already expanded support for capabilities including Dropbox API indexing, source change detection, Supabase Storage indexing, and improved transcription. ### Who should I contact? For questions about Ragie data exports or your existing Ragie account, contact support@ragie.ai. For Captain onboarding, indexing, API migration, or pricing assistance, contact humans@captain.dev. Lewis Lien Polansky [ CEO & CO-FOUNDER · CAPTAIN ] Lewis is co-founder and CEO of Captain, building self-tuning file search for AI agents. [ CONTENTS ] [ SHARE ] [More posts](https://captain.dev/blog) ### Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 ### Captain vs. Elasticsearch Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. 5 min read 7 Sep 2026 ### Captain vs. Cloudflare AI Search Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. 6 min read 7 Sep 2026 [ RSS ] Benchmarks, engineering write-ups and the occasional retraction, straight from the source. [Follow the RSS feed](https://captain.dev/blog/rss.xml) --- # Captain v2 API Launch · Captain Source: https://captain.dev/blog/captain-v2-launch/ Description: We've been busy this holiday season, shipping optimizations throughout the stack. I'm thrilled to announce the stable release of our v2 API, among other product updates. [ BLOG ] ## Captain v2 API Launch Lewis Lien Polansky [ CEO & CO-FOUNDER ] We've been busy this holiday season, shipping optimizations throughout the stack. I'm thrilled to announce the stable release of our v2 API, among other product updates. 4 min read 3 Jan 2026 [ FIG. 00 · THE V2 API, THE NEW DOCS SITE AND A 3X DROP IN SEARCH LATENCY ] We've been busy this holiday season, shipping optimizations throughout the stack. I'm thrilled to announce the stable release of our v2 API, among other product updates. ## In short We've been busy this holiday season, shipping optimizations throughout the stack. I'm thrilled to announce the stable release of our v2 API, among other product updates. TL;DR - Increased search precision for legal, healthcare, and financial datasets - Search latency slashed 3x - v2 REST API now stable - Brand new interactive documentation site: docs.runcaptain.com - Python & TypeScript SDKs out later this month - Hacker News RAG Search by Captain is underway ## New Interactive Docs We've invested in a beautiful new docs site with an interactive API explorer. You can now supply your API key and test out requests from within the docs! ## Interactive API Explorer In addition to the interactive docs, for on-the-fly API development, the Captain Playground has been redesigned for non-technical users to experience the power of high-accuracy RAG within a non-programmatic interface. ## Precision Optimizations Our retrieval precision has been further optimized for healthcare, legal, and financial RAG use cases. We have employed a number of techniques to increase accuracy, namely long-context document embedding and automatic domain detection. Long-context document embedding entails the embedding of the entire context of a file and supplementing it with the narrow chunk content. This provides both broad and narrow semantic value during similarity lookups. Automatic domain detection allows Captain to index domain-specific terms within a BM25 index (to supplement dense vector search). This development solves the long-standing issue within RAG (and search more broadly) of domain-specific terms getting "lost" without proper vector correlations. By combining these two techniques and weighing them, search results provide a better understanding of complex document narratives and niche industry terms like drug names or non-English legal terms. ## Latency Optimizations We have seamlessly migrated away from vector storage, resulting in an over 3x drop in latency. Our experimentation has also shown better recall when object storage search is used as opposed to leveraging vector databases. This past December we successfully transferred all non-textual knowledge data into object storage. There was no disruption to service uptime. We remain committed to leveraging state-of-the-art embedding models, but going forward, our embeddings will be stored as objects. ## What's next? Captain has partnered with the Hacker News team to develop an RAG forum search across the popular aggregator's over 19+ years of posts and comments. More on that in a few weeks. Our Python and TypeScript SDKs are underway; these will be out later this month. Happy Shipping! Lewis Lien Polansky [ CEO & CO-FOUNDER · CAPTAIN ] Lewis is co-founder and CEO of Captain, building self-tuning file search for AI agents. [ CONTENTS ] [ SHARE ] [More posts](https://captain.dev/blog) ### Edge Routing for RAG Serving international customers on low latency semantic search. 3 min read 10 Sep 2026 ### Captain vs. Elasticsearch Elasticsearch ships without parsing, OCR, chunking, embeddings, connectors or sync. Teams add four to seven vendors to cover the gaps, then own every seam between them. Captain includes all of it behind one index call. 5 min read 7 Sep 2026 ### Captain vs. Cloudflare AI Search Cloudflare AI Search caps files at 4 MB, chunks at a token count and metadata at five fields, because it runs on Workers and Vectorize. Captain has no file size cap, picks optimal chunk boundaries, and stores whatever metadata you send. 6 min read 7 Sep 2026 [ RSS ] Benchmarks, engineering write-ups and the occasional retraction, straight from the source. [Follow the RSS feed](https://captain.dev/blog/rss.xml)