Captain
ActiveSelf-tuning file search for AI agents
About
Captain syncs complex, multimodal files and cloud storage from sources like S3, SharePoint, and Google Drive, and makes that knowledge searchable for your agents. Instead of stitching together parsers, embeddings, vector databases, rerankers, and retrieval infrastructure, Captain self-tunes the retrieval pipeline to your data and workloads. On benchmarks, this improves accuracy from roughly 78% with standard RAG to over 97% by tuning retrieval to the unique structure and content of your data. Captain is purpose-built for complex, regulated, and high-stakes file search workloads. Learn more at https://captain.dev
Founders
Lewis Polansky· CEO/Co-FounderCEO @ Captain, Prev. IEEE, Founded CyberSpace (CTF hacking group), Recognized by the U.S. Congress for leadership in community software projects, Avid designer, Dropped out of Purdue
Edgar Babajanyan· Co-Founder and CTOCTO @ Captain | Published AI NLP Researcher | Built OCR engines @ Boar's Head | Scaled high-performance RAG pipelines for the past 4 years | Built a Cross Region L2 Datacenter
Product launches · 1 launch
Search files with much higher accuracy than RAG (Avg improves 78% → 95%)
Change history · 10 recorded
- August 27, 2026
- Description rewritten07:00 PM
- Pitch updated07:00 PM
- August 11, 2026
- Website updated07:00 PM
- August 6, 2026
- Pitch updated07:00 PM
- July 5, 2026
- Launches refreshed08:01 PM
- YC partner updated08:01 PM
- Founder profile updated08:01 PM
- June 21, 2026
- Launches refreshed08:01 PM
- Founder profile updated08:01 PM
- YC partner updated08:01 PM