Intelligent end-to-end monitoring for AI agents

We've been working on Sentinel, a platform that continuously monitors AI agents, learns from your codebase to set up evaluation rubrics, and runs end-to-end evaluations to spot and fix issues in production.

We're curious to get any thoughts and hear how you currently observe or debug AI agents.

Join the waitlist if you want early access: https://trysentinel.vercel.app/