observability
43 talks
Agents Are Where Microservices Were in 2015
AI Agents Are Just Distributed Systems Now
From Tokenmaxxing to Trusted Throughput
Tribal Dungeons of Global Shipping: AI Agents at Global Scale
AI Evals for Cross-Functional Teams
Building uReview, Uber's Multi-Agent Code Review Engine
Agent Frameworks Considered Harmful
FinOps for AI Agents: Who Spent All the Tokens?
Building Agents Is Trivial Now, Context Is the Next Frontier
How I automate my own job at Hugging Face using agents
Infra behind Krea 2: How to train and serve at scale
Bringing agents onto the World Wide Web
How Web Data Infrastructure Powers the Next Generation of AI
Designing Agents (The Floor Is the Frontier)
Improving Agents is a Data Mining Problem
Always-on agents run production without the on-call tax
Your Agent Didn't Fail. Your Harness Did.
From Agent Traces to Agent Simulations
From Signal to PR: Anatomy of a Self-Improving Agent
How Evals and Prompts Shape Agent Behavior
The Future of Evals: From LLM as a Judge to Agent as a Judge
Citation Needed: Provenance for LLM-Built Knowledge Graphs
Learned Execution Graphs for Anomaly Detection & Drift in APIs
Your agent architecture has a half-life of 6 months
Medic for Apache Spark: First Aid for Failing Jobs
Build Evals That Actually Matter
From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization
Your Agents Need a Save Button
WTF Is the Context Layer? The Missing Infrastructure for Production Agents
The Pipeline Is Dead
The Missing Layer After Launch
Deterministic Infra for Non-Deterministic AI Agents
The Agentic AI Engineer
Your Agent Failed in Prod. Good Luck Reproducing It.
Agents Building Agents
Bypassing the Multimodal Tax: Hybrid RAG, SQL RRF & UI Telemetry
User Signal Dies at the Retrieval Boundary
Your Agent Is Wasting Tokens and You Don't Know It
Agents in Production: How OpenGov Built and Scaled OG Assist
Production Evals For Agentic AI Systems
The Production AI Playbook: Deploying Agents at Enterprise Scale
Self Driving Products: Product Signals to Pull Requests
LLM Observability, Evaluation, Experimentation Platform