Mirrors

What is Mirrors?

Mirrors provides regression testing for AI agents. Teams shipping agents constantly change prompts, models, and tools, and there's no way to test any of it. Agents call bespoke internal tools and APIs no test framework can reproduce, so most teams ship on vibes. Mirrors rebuilds the tools your agent calls from your own production traces, then replays real sessions against every change before it merges. You see which tool calls changed, which arguments moved, and where state landed differently. And when something fails, we tell you whether your agent regressed or something upstream moved. Built for teams whose agents take irreversible actions. Refunds, record updates, outbound email. Runs in your CI on every PR.

From the website

Mirrors — Don’t let the same agent mistake reach another customer

Mirrors is building a way to carry your team's corrections into an agent's next decision. Join us as an early design partner to work on recurring agent mistakes.