Navigating Jev for Regulated RAG
Moving PII masking from an NER model to Jev turned custom categories into plain-language descriptions, and lifted built-in redaction from 71.2% to 92.9%.
4 min read
Resources · Blog
Field notes
on retrieval.
How we build search that agents can trust: the feature releases and engineering write-ups along the way.
- 8 articles
- Updated weekly
- Latest · 22 Sep 2026
01Featured
Edge Routing for RAG
Serving international customers on low latency semantic search.
3 min read
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
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
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
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
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
2 more