Engineers spend 70% of their time understanding code, not writing it. That’s why we built Asimov at Reflection. The best-in-class code research agent, built for teams and organizations.

Code comprehension is hard. Production codebases are large with a lot of context outside of the code itself. In blind tests, Asimov's answers to complex questions were preferred 60 - 80% of the time. Asimov works because…

1] Asimov builds a single source of truth for eng knowledge Asimov looks at more than just code. It pulls knowledge from your codebase, your team’s messages, your project management tools, and more. Watch it trace a bug from a chat thread to the exact PR that introduced it:

2] Asimov captures team-wide tribal knowledge with memories Asimov learns from expert feedback and captures tribal knowledge stored in engineers' minds. e.g. "asimov, remember X works in Y way" Once an update is made it benefits the entire team.

3] Asimov is designed to ingest a lot of context Today agent designs fall into two categories: RAG or agentic search. Both struggle with large codebases. Asimov uses a new multi-agent design (a big reasoner with small retrievers) to ingest large codebases.

Asimov was built for engineering teams with large complex codebases. We are selecting partners for early access today. Sign up for the waitlist here:

Asimov is our first step toward superintelligence. We believe comprehension is at the root of this problem. Build with us. Product: shape how teams use Asimov. Research: develop powerful agentic models.

Thanks to @willknight for covering our story in @WIRED.

Scan any documents, convert images into text, PDF files, etc. 👍

@reflection_ai First launch with the Reflection team! We built the agent we always wanted when the code made no sense and the comments lied.

@reflection_ai Proud to be building this with you

@reflection_ai Really exited to share what we have been building with the incredible team at @reflection_ai

@reflection_ai the best co-founder a man could ask for