Artifacts is live in Lemma.
It uses your agent’s prompts, traces, and private context to decide what should surface as an issue.
Every issue you validate or dismiss updates what Lemma looks for next.
Introducing Lemma: production monitoring for AI agents.
Agents can look like they're working even when they've failed. Lemma fixes that:
→ Audits every trace against your agent's instructions
→ Groups recurring failures into issues
→ Alerts you in Slack before users notice
→ Pulls context into your coding agent via MCP
→ Turns every fix into an online eval
Backed by Y Combinator.
https://t.co/DhkHGSCTkj