A finished run is not a successful run
Agents don't throw. They improvise, apologise and mark the ticket solved. Here is how we detect the failures that look like success.
Blog
Agents don't throw. They improvise, apologise and mark the ticket solved. Here is how we detect the failures that look like success.
Approvals · 7 min read
Approvals everywhere kill the point of an agent. Approvals nowhere is how you end up in the news. A framework for drawing the line.
Cost · 6 min read
How one retry loop turned a $0.05 run into a $4 run, and the three guards that would have caught it.
Evals · 8 min read
Synthetic test sets miss the weird stuff. Real runs don't. How to turn yesterday's traffic into tomorrow's regression suite.
Security · 10 min read
Your agent can call tools on servers you've never audited. Allowlists, argument policies and what to log.
Cost · 5 min read
Soft limits are a notification. Hard limits are a product decision. How we designed pause-at-100% without breaking runs mid-flight.
Traces · 6 min read
Gaps, staircases, fan-outs and long tails: the six shapes that tell you what an agent was doing before you read a single span.