debugging
29 talks
RAG Needs a Map: Using GraphRAG to Retrieve Connected Context
Advanced Workshop: Mastering AI Observability
From Vibes to Production: Evaluating and Shipping AI Agents That Work 101
The 5 Levels of Self-Driving Production
Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story
Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards
From Signal to PR: Anatomy of a Self-Improving Agent
The Future of Evals: From LLM as a Judge to Agent as a Judge
Your Agents Need a Save Button
The Prompt is the Platform
Your Agent Failed in Prod. Good Luck Reproducing It.
LLM Observability, Evaluation, Experimentation Platform
Fighting AI with AI
Make your own event-sourced agent harness using stream processors
Ship Real Agents: Hands-On Evals for Agentic Applications
Shipping complex AI applications
Challenges in High Performance Robotics Systems
Evaluating AI Search: A Practical Framework for Augmented AI Systems
Why you should care about AI interpretability
Continuous Profiling for GPUs
Full Spec MCP: Hidden Capabilities of the MCP Spec
Production software keeps breaking and it will only get worse
The State of MCP Observability: Observable.tools
Supercharging developer workflow with Amazon Q Developer
7 Habits of Highly Effective Generative AI Evaluations
Real ROI: Lessons from Enterprises That Have Already Succeeded with LLMs at Scale
GraphRAG: The Marriage of Knowledge Graphs and RAG
Fixing bugs in Gemma, Llama, and Phi 3
Low Level Technicals of LLMs