From 57 bugs to 1, thanks to Seer

Summary

Software teams frequently defer low-priority bugs to the backlog because manual triage, investigation, and code fixes consume valuable engineering time. To resolve 56 out of 57 backlog bugs, Dan Mindru utilized Sentry telemetry combined with Seer and the hosted Sentry Model Context Protocol server. Sentry captures context including traces, logs, and session replays, allowing Seer to assess fixability scores and generate pull requests with unit tests for isolated issues. For more intricate problems, developers query production breadcrumbs and telemetry directly in their agentic editors while supplying missing historical business logic. Consequently, automated tool calling and agent workflows drastically lowered the economic cost of addressing routine production bugs.

Context

Software backlogs frequently accumulate low-priority bugs because the economic cost and engineering time needed to investigate and fix them cannot be justified compared to building high-value new features.

Approach / What changed

The author used Sentry and its AI capabilities, including Seer and the hosted Sentry MCP server, to automate root cause analysis and code fixes. Seer analyzes telemetry data, such as traces, logs, and session replays, and automatically opens pull requests on GitHub for isolated issues. For complex bugs, developers query production telemetry directly within IDE agents like Cursor via the Sentry MCP server while supplying proprietary business context.

Takeaways

• Seer generates automated pull requests for issues that occurred within the last 14 days, possess sufficient event volume, and meet a minimum fixability score.
• The hosted Sentry MCP server enables AI agents in tools like Cursor to inspect production events, breadcrumbs, and telemetry directly during chat investigations.
• Seer automatically parses repository rule files for tools like Cursor and Claude Code, ensuring generated fixes follow established codebase conventions.

Related reading

• Sentry · May 11, 2026

  From vibe code to production-ready: observability for Next.js and Supabase apps

  AI-assisted software development often generates functional code that lacks proper instrumentation, leading to unindexed database queries, N+1 patterns, and fragmented connection strategies. While Supabase provides built-in query analytics, security advisors, and subsystem logs, it cannot trace distributed requests across the entire application stack. Integrating Sentry bridges this visibility gap by establishing distributed traces across Next.js frontends, Deno-based Supabase Edge Functions, and Postgres databases. Teams can forward Supabase logs into dedicated Sentry projects and configure runtime integrations to automatically detect performance bottlenecks such as slow spans and Web Vitals regressions. Furthermore, integrating Model Context Protocol servers allows Sentry's Seer debugger to identify root causes and generate automated fixes for emerging issues.

  Sergiy Dybskiy

• Sentry · May 26, 2026