# Captain

> Captain is a managed retrieval-augmented generation (RAG) platform out of Y Combinator's Winter 2026 batch. It lets developers connect data sources - S3, SharePoint, Google Drive, Slack, Notion and more - with a couple of API calls, then handles the full pipeline behind the scenes: OCR, chunking, embedding, vector storage, hybrid search, and re-ranking. The company claims roughly 95% retrieval accuracy on a published benchmark versus about 78% for hand-built pipelines, and positions itself as 'the Snowflake for unstructured data.' In March 2026 it added Odyssey, a proprietary private-market intelligence dataset queryable through the same API.

- **Founded:** 2025
- **Headquarters:** San Francisco, United States
- **Founders:** Lewis Polansky (CEO & Co-founder), Edgar Babajanyan (CTO & Co-founder)
- **Team size:** 4 (approx.)
- **Products:** Captain (Managed RAG API), Captain Collections, Agentic + Hybrid Search, Role-Based Access Control, Odyssey
- **Notable:** Accepted into Y Combinator's Winter 2026 batch., Claims ~95% retrieval accuracy on MRAG-Bench (an ICLR-published benchmark) versus ~78% for typical DIY pipelines., SOC2 Type II certified.

## Products & services

- **Captain (Managed RAG API)** — An API-first managed retrieval pipeline. Connect data sources with a couple of API calls; Captain handles OCR, chunking, embedding, vector storage, hybrid search, and re-ranking, returning results with automatic citations.
- **Captain Collections** — Managed vector storage with built-in OCR and embeddings, plus universal indexing that converts and embeds files automatically.
- **Agentic + Hybrid Search** — Weighted keyword and semantic search combined via reciprocal rank fusion, then cross-encoder re-ranking from 50 candidates down to the top 15 results.
- **Role-Based Access Control** — Granular, metadata-based governance and filtering so agents only retrieve what a given user is permitted to see.
- **Odyssey** — A proprietary private-market intelligence dataset - VC deals, fund performance, LP profiles, company financials, exit-probability predictions and patent filings - queryable through the same API. Repositions Captain from infrastructure to data provider.

## Achievements

- Accepted into Y Combinator's Winter 2026 batch.
- Claims ~95% retrieval accuracy on MRAG-Bench (an ICLR-published benchmark) versus ~78% for typical DIY pipelines.
- SOC2 Type II certified.
- Garry Tan (YC) described the product as 'a step function increase vs existing RAG pipelines.'
- Launched Odyssey, a proprietary private-market dataset, within months of founding.

## Latest updates

- **2026-03** — Launched Odyssey, a proprietary private-market intelligence dataset queryable via the Captain API, shifting from pure infrastructure toward a data moat.
- **2026-03** — Public Launch HN / launch as an automated managed-RAG platform for enterprise AI agents.
- **2026-01** — Joined Y Combinator's Winter 2026 batch.

## Links

- Website: https://runcaptain.com
- LinkedIn: https://www.linkedin.com/company/runcaptain
- Twitter/X: https://x.com/runcaptainrag
- GitHub: https://github.com/runcaptain

---

Profile page: https://yespress.io/captain-yc-w26
Published by YesPress — https://yespress.io
Last updated: 2026-07-31