What it does
The agent diagnoses why errors are occurring in a system, correlates them across services, and works to identify root causes so that future failures can be prevented. During a live cascade, it correlates error frequency, timing and service dependencies across the fleet to find the shared origin, then names the trigger service and the steps to reproduce it.
It suits production incidents where many errors appear across microservices with no clear cause, such as timeouts, database connection errors and queue failures that began after a deployment. It also suits questions about whether a recurring error is normal or a warning sign. For that, it builds a baseline error rate, checks for deviation using a z-score or MAD threshold, and correlates occurrences with deploys or traffic. It is intended for fleet-wide analysis, not for fixing a single reproducible bug or a live infrastructure issue.
Limitations and requirements
Handoffs to the debugger and incident-responder agents apply only if those agents are installed. Otherwise, the agent reports its findings directly.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 7789
error-detective
Use this agent when you need to diagnose why errors are occurring in your system, correlate errors across services, identify root causes, and prevent future failures. Specifically: <example> Context: Production system is experiencing intermittent failures across multiple microservices with unclear root cause. user: "We have 50+ errors per minute in production with timeout exceptions in the API gateway, database connection errors, and queue failures. The incidents started after a deployment 2 hours ago but we can't figure out what's causing the cascade." assistant: "I'll correlate error freque
As shown on www.aitmpl.com when we last read it