observability
173 talks
How to Actually Tokenmaxx and Save Millions
Paving the Road to Production: Governed Enterprise AI Agents
The Agent Works. Does Anyone Trust It?
Scheduled Agents, Dreaming and Q&A: Claude Managed Agents (Part 3 of 4)
An AI Future Without the Lock-In
From Your Laptop to the Pipeline: Scaling Custom Agents with GitHub Copilot
Giving AI Agents Memory That Learns
Your AI Agent Has No Nervous System
The Software Factory: From Bug Report to Production Code
Why Your AI Agents Can't Talk to Each Other (Yet)
Advanced Workshop: Mastering AI Observability
The Self-Improving OSS Agent Stack
What Is an Inference Engine, Anyway?
Why Building an Eval Platform Is Harder Than It Looks
From Vibes to Production: Evaluating and Shipping AI Agents That Work 201
From Vibes to Production: Evaluating and Shipping AI Agents That Work 101
The Transcript Looked Fine. The Call Wasn't.
GPU Died. Training Didn't: Self-Healing Training at Scale
Your LLM App Returned 200 OK. It Was Still Wrong.
The 5 Levels of Self-Driving Production
Your Agents Are in Solitary Confinement: Why MCP & A2A Aren't Enough
How We Built an Agent That Improves Itself
Are LLM Performance Benchmarks Reliable?
I Monitored Crime Audio. Voice Agents Scare Me More.
Harness Engineering: Building the Production Cage for Powerful Domain Agents
Tethered: Our Agents Are Us
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
How AI Agents Let GTM Teams Scale
Agent Frameworks Considered Harmful
FinOps for AI Agents: Who Spent All the Tokens?
Give the Agent a Budget, Not a Token
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
The Evolution of Agentic Surfaces
Always-on agents run production without the on-call tax
How Kepler Built Verifiable AI for Financial Services
Your Agent Didn't Fail. Your Harness Did.
AI Agents for Performance: Ship Faster, Pay Less
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
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
Agents Need Feature Flags
Your Agents Need a Save Button
WTF Is the Context Layer? The Missing Infrastructure for Production Agents
ReviewDebt: A Practical Framework for Scoring Every Pull Request
Your agent is blindfolded
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
AI System Design: From Idea to Production
Bypassing the Multimodal Tax: Hybrid RAG, SQL RRF & UI Telemetry
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
LLM Observability, Evaluation, Experimentation Platform
How Lovable self-improves every hour
What if the network was the sandbox?
How Agent Observability Differs from Traditional Observability
The maturity phases of running evals
What the Best Agents Share
Does GenAI "belong" to data scientists?
How Google DeepMind Runs Agents at Scale
Skill issue: Lessons from skilling up coding agents to use Langfuse
What Breaks When You Build AI Under Sovereignty Constraints
AI Engineer Singapore Day 2
How Building with AI Can Double the Throughput of Your Engineering Team
Mind the Gap (In Your Agent Observability)
Ship Real Agents: Hands-On Evals for Agentic Applications
Malleable Evals: Why Are We Evaluating Adaptive Systems with Static Tests?
Feedback Loops are All You Need
Everything You Need To Know About Agent Observability
Human-in-the-Loop Automation with n8n
Shipping complex AI applications
Why building eval platforms is hard
One Registry to Rule Them All
From Chaos to Choreography: Multi-Agent Orchestration Patterns That Actually Work
Platforms for Humans and Machines: Engineering for the Age of Agents
Your Insecure MCP Server Won't Survive Production
Building Durable Agents with Workflow DevKit & AI SDK
Shipping AI That Works: An Evaluation Framework for PMs
Can You Prove AI ROI in Software Engineering?
From Stateless Nightmares to Durable Agents
Infra that fixes itself, thanks to coding agents
2025 is the Year of Evals! Just like 2024, and 2023, and …
The 2025 AI Engineering Report
From Self-driving to Autonomous Voice Agents
Scaling AI Agents Without Breaking Reliability
Human seeded Evals
Building AI Products That Actually Work
Building Applications with AI Agents
3 ingredients for building reliable enterprise agents
Continuous Profiling for GPUs
Critical AI Inference Your CIO Can Trust
CIAM for AI: Authn/Authz for Agents
MCP is all you need
Shipping an Enterprise Voice AI Agent in 100 Days
Production software keeps breaking and it will only get worse
The Build-Operate Divide: Bridging Product Vision and AI Operational Reality
Conquering Agent Chaos
Mastering AI Evaluation: From Playground to Production
Turning Fails into Features: Zapier's Hard-Won Eval Lessons
Data is Your Differentiator: Building Secure and Tailored AI Systems
Engineering Better Evals: Scalable LLM Evaluation Pipelines That Work
Evals 101
How to build world-class AI products
Realtime Conversational Video with Pipecat and Tavus
Taming Rogue AI Agents with Observability-Driven Evaluation
Why should anyone care about Evals?
The State of MCP Observability: Observable.tools
The Web Browser Is All You Need
Remote MCPs: What We Learned from Shipping
Break It 'Til You Make It: Building the Self-Improving Stack for AI Agents
Evals
AI Engineer World's Fair 2025, Day 1 Keynotes and MCP Track
Building Reliable Support Agents Using the Effect TypeScript Library
How agents broke app-level infrastructure
The Demo I Wish I'd Had: OpenAI's Agents SDK... serverless!
The RAG Stack We Landed On After 37 Fails
How to Build Your Own AI Data Center in 2025
Ensure AI Agents Work: Evaluation Frameworks for Scaling Success
The DevOps Engineer Who Never Sleeps
AI + Security & Safety
Voice Agent Engineering
Building LinkedIn's GenAI Platform
The Agent Development Life Cycle
RAG Agents in Prod: 10 Lessons We Learned
Agent Evals: Finally, With The Map
AI Agents, Meet Test Driven Development
Building Enterprise LLM Agents That Work
Lessons from building GenAI based applications
OpenLLMetry is all you need
The Hidden Costs of Building Your Own RAG Stack
AI Leadership
Optimizing LLMs in Insurance with DSPy
Building security around ML
Creating and scaling your own custom copilots with Azure AI Studio
Lessons from the Trenches: Building LLM Evals That Work IRL
BotDojo Launch: Enhancing AI Assistants with Evaluations and Synthetic Data
AI Platform Engineering
E-Values: Evaluating the Values of AI
Real ROI: Lessons from Enterprises That Have Already Succeeded with LLMs at Scale
Iterating on LLM apps at scale: Learnings from Discord
How Zapier Builds AI Products and Features with the Help of Braintrust
What It Actually Takes to Deploy GenAI Applications to Enterprises
Productionizing GenAI Models
How to Construct Domain Specific LLM Evaluation Systems
Judging LLMs
Git push get an AI API
Hypermode Launch
Lessons From A Year Building With LLMs
AI Engineering 201: The Rest of the Owl
The AI Pivot
Building Context-Aware Reasoning Applications with LangChain and LangSmith
AI Engineer Summit 2023, Day 1 Livestream