Ask HN: How do you audit autonomous AI agent decisions?

Posted by credentum 3 days ago

Counter4Comment2OpenOriginal

Building agents that can spend money (via AP2/payment APIs). Regulators want audit trails. Agents use tools from multiple vendors.

Problem: No unified way to prove why an agent made a decision. Each vendor logs their piece, but the full decision chain is fragmented.

Anyone solved this? Especially interested in: - Cross-vendor decision provenance - What to log (CoT? Context? Just actions?) - Storage (centralized DB vs. immutable ledger)

Comments

Comment by bigyabai 3 days ago

git blame

Comment by credentum 2 days ago

git blame shows who wrote the code.

It doesn't show why an agent approved a $50K purchase order. The agent read 3 APIs, thought about it, then acted. That decision isn't in any repo.