Resources

Latest guides and notes
from Mirrors

Notes on controlling what production AI agents are told, checking what follows, and reducing repeated mistakes.

MirrorsComparison

AI agent observability vs evals vs corrections

Observability shows what an agent did, evals test a change, and corrections change what it gets in one situation. How they fit with Langfuse, LangSmith and Braintrust.

Which mistake can’t your agent afford to repeat?
Tell us what you’re building.

Book a demo