On Health Loops.
One timeline. The input, each step, its timing, its return value and every log line.
Answers complaints. Who, when, what was said, which tool ran and where it went, kept so a complaint can be answered weeks later.
Your own store. Each organisation’s runs live in its own data store, apart from every other customer.
Questions
What is an agent run record?
A run record is the full history of one agent run: the trigger, each step and its result, every tool call, every log line and every error.
Who can see run records?
Your team, in your organisation’s own data store.
Are failed runs kept?
Yes. An uncaught error fails the run and keeps the message and stack.