What If Bugs Fixed Themselves? - David Cramer, Sentry

Video Description

Meet Sear, Sentry’s new AI debugger. In this talk, David Cramer from Sentry explains how it works and why it matters. David walks us through Sentry’s shift from simple error monitoring to AI-assisted bug fixing. Cramer breaks down how large language models use pattern-matching to slot into real debugging workflows, and where their limits still are. The talk also digs into the realities of autonomous bug fixing and why context retrieval often beats clever prompt engineering. Cramer shows how Sentry is adopting the Model Context Protocol (MCP) to power human-in-the-loop coding agents. You'll also learn what’s working today, what isn’t, and what AI-first debugging might look like. Plus: a Q&A on JavaScript error handling, source maps, and MCP agent design. David Cramer is co-founder and Chief Product Officer at Sentry, a leading open-source error monitoring and application performance platform used by over 4 million developers and 150,000 companies. Sentry helps developers find and fix bugs faster through error tracking, performance monitoring, session replay, and code coverage tools. 🔗 CONNECT WITH DAVID CRAMER LinkedIn: https://www.linkedin.com/in/dmcramer Twitter/X: https://x.com/zeeg Sentry: https://sentry.io 📚 MASTRA RESOURCES Mastra: https://mastra.ai Learn Mastra in the world's first MCP-Based Course: https://mastra.ai/course Principles of Building AI Agents (Book): https://mastra.ai/book Patterns for Building AI Agents (New Book): https://mastra.ai/blog/patterns-book https://docs.google.com/forms/d/e/1FAIpQLSduJjc515f6RZJqtkR2ByqJZrB0iP8B7SUKnjjZE9IajH_I8w/viewform The TypeScript AI conference is the first conference for TypeScript AI developers. The inaugural event took place on November 6, 2025, in San Francisco and online. MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you’re a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. 00:00 Intro 01:02 Challenges of JavaScript Errors and Debugging 02:41 AI and LLM Existential Crisis in Software 04:19 LLMs as Pattern Matching for Debugging 04:54 Introducing Sear: Sentry's AI Debugger 05:24 Building Context Engines for AI Debugging 06:20 MCP Protocol for Bug Fixing 07:22 AI Bug Fixes: Successes and Limits 08:10 Root Cause Analysis in Distributed Systems 09:31 Case Study: AI Fixes Complex TypeScript Bug 10:08 Future: AI Debugging as Primary Workflow 11:11 The Dream: Fix Trivial Bugs Automatically 12:45 Handling JavaScript Errors: Best Practices 14:48 Future of Source Maps and AI Stack Traces 17:09 MCP Server Agent and AI Tool Evolution 18:07 Designing MCP for Agents and Language Interaction 19:41 MCP Agent Mode: Composability vs. Usability 20:15 Industry Challenges and Future of LLMs