Your AI agent just refunded a customer, deleted a database table, or emailed a spreadsheet to the...
Your AI agent just refunded a customer, deleted a database table, or emailed a spreadsheet to the wrong person. Three weeks later, someone asks what happened.
What do you have?
A log line.
Who wrote it?
Your own code.
Most AI agent audit logs can tell you what prompt ran, what model answered, and which tools were...
Build a separate append-only audit trail for every message an Agent Account sends and receives — keyed by message_id and…
This post builds on a conversation that started in Ian Johnson's harness stack thread and the...
Your AI agent called a tool. Can you prove it followed the rules? Your agent just wrote a...
A practical AI agent run ledger for recording outcomes, cost, time, failures, evidence, decisions, and human release approval…
A hands-on demo of cryptographically verifiable agent behavior — a tamper-evident receipt proving an agent ran the approved…
