From Error to Agent: Automating Sentry Issue Triaging

Engineering teams use Sentry to capture errors and performance issues, but turning that signal into action remains largely manual. Most teams ignore errors until things break.

I’ll demo an agentic workflow that goes from ignored Sentry errors to triaged PRs using AI agents. We’ve built a first-class integration that maps Sentry’s project-based error model to GitHub repositories, letting developers review issues directly inside Continue. The system allows teams to filter and surface relevant errors, then launch an agent to investigate, summarize, or propose fixes.

This Continuous AI workflow originated from a YC company struggling with their massive Sentry backlog. Their ask was simple: “Let me look at my Sentry inbox, decide what matters, and offload the rest to an agent.” The result is a tight loop between runtime issues, developer intent, and automated AI-powered actions.

Attendees will learn how to design AI-driven triage workflows, how agents can listen to Sentry webhooks to create tasks instantly, and how teams can turn noisy error data into structured, actionable work.