What they do
feeds situation-specific guidance to production agents from patterns in past runs
How close to us
2, near
improves agents and checks if outcomes improved, but for engineers fixing prompts, not seeing what is stuck.
Wedges
- W2 Seeing whether your AI agents actually produce adjacent
Who buys
- Firm size
- not known
- Buyer type
- developer
- Role
- head of engineering
- UK
- not known
Their own description (from YC)
Production agents handle many different customer workflows. Currently, when one handles a situation badly, an engineer reads the trace and patches the prompt. The next situation needs another exception. Soon, improving the agent becomes a recurring engineering job, and the prompt keeps growing.
Mirrors finds patterns in past runs. Engineers review guidance for a specific situation and preview where it would apply. Mirrors then delivers that guidance while the agent works, inside the team’s existing setup. The team can check whether the change improved the outcome.
We’re building Mirrors for engineering teams running customer-facing agents across varied workflows, so they can improve behavior without hardcoding every lesson in the global prompt.
Full teardown
No full teardown yet. On the deep list.
Technical detail
- Slug
- mirrors
- Lens hash
- 179096c479
- Pass
- screen
- Stale
- no