Back to feed
Dev.to
Dev.to
7/26/2026
I built an agent that asks your app what happened to it on SigNoz

I built an agent that asks your app what happened to it on SigNoz

Short summary

A hackathon project called 'Why Did It Break' builds an AI agent on top of SigNoz that investigates production issues by running live queries against traces, logs, and metrics. The agent receives natural-language questions like 'why is checkout slow?' and follows leads across six tools to identify root causes with evidence links and confidence scores. It enforces a strict no-mocks rule, operating entirely against real telemetry data from a live HotROD demo system.

  • •AI agent runs live SigNoz queries to diagnose production issues from natural-language questions
  • •Six tools let the agent drill into service stats, slow spans, error spans, and logs autonomously
  • •Every claim links to exact traces; agent shows full tool-call trail for trust and transparency

Generated with AI, which can make mistakes.

#ai-agents#ai-tools#open-source
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

Multi-agent AI system for autonomous production incident investigation
Dev.to
The original title is: "Building AXRAY: Observability for AI Coding Agents with SigNoz and OpenTelemetry"
Dev.to
The original title is "Building Missio: An Evidence-Bound Remediation Agent with SigNoz"
Dev.to
Building a Multi-Agent Code Review Crew with OpenTelemetry Tracing in SigNoz
Dev.to