Backed by investors from
Cursor 
Notion 
First Harmonic 
Front 
Weekend Fund 
Yelp 
Figma 
Cursor Notion First Harmonic Front Weekend Fund Yelp Figma Cursor Notion First Harmonic Front Weekend Fund Yelp Figma Cursor Notion First Harmonic Front Weekend Fund Yelp Figma Chunking. Reranking. Agent loops.
Complex queries still break. In legal, a missed exhibit. In construction, seven figures left on the table.
You're building retrieval infrastructure. You should be building your product.
From simple search to deep research. One API.
Charcoal scales with complexity. The same API handles instant lookups and exhaustive multi-step analysis across thousands of documents.
Deep research that gets smarter every week.
Charcoal uses RL directly on your data to learn how best to navigate it. Every production query, every correction, every flag feeds back into the model.
How it works
We ingest your query patterns
Charcoal learns from the real queries your agent makes, mapping them to the underlying terminology, aliases, and patterns unique to your corpus.
Any signal on wrong results
Thumbs down, a flag, a correction: any feedback your users or team give on bad results becomes a direct training signal.
RL checkpoints ship automatically
Feedback feeds into our RL loop. Improved model checkpoints are validated and deployed—no manual tuning required.
"We were three months into building our own retrieval pipeline and still couldn't trust the answers on complex queries. We replaced all of it in two weeks."
Get started with Charcoal.
One API to replace your retrieval stack.