structured-outputs
60 talks
Parsing the Epstein Files for JMail
RAG Needs a Map: Using GraphRAG to Retrieve Connected Context
Turning Agent Memory Into Skills That Work
5 Voice Agent Failure Modes You'll Hit in Week One
Training Taste
Multimodal Collaborative Agents for Next-Gen Commerce
Teaching agents to pay
The End of the Static Screen: Architecting Intent-Driven UX
Your Agent Just Authorized What?!
Building the Engine While Flying the Plane: Launching the Figma MCP Server
How Kepler Built Verifiable AI for Financial Services
Why Agentic Systems Need Ontologies
Agent Output Is Not UX: Rendering Layer Your LLM Pipeline Is Missing
Agents Need Receipts, Not More Tool Calls
Semantic Blindness: 500,000 Sensors Confused an LLM
Respect The Process
Build Systems, Not Code
Why MCP and ChatGPT Apps Use Double Iframes
Why Can't Anyone Answer Questions About the Business?
From Transcription to Live Music: Gemini's Audio Stack
Building Safe Payment Infrastructure for the Autonomous Economy
Let's Go Bananas with GenMedia
MCP UI: Extending the frontier
Agents on the Canvas in tldraw
Contact Center Voice AI: Low-Latency Intelligence Extraction from Messy Audio Streams
Spec-Driven Development: Agentic Coding at FAANG Scale and Quality
DSPy: The End of Prompt Engineering
Wisdom-Driven Knowledge Augmented Generation at Scale
Human seeded Evals
The Billable Hour is Dead; Long Live the Billable Hour
Practical GraphRAG: Making LLMs Smarter with Knowledge Graphs
Stop Using RAG as Memory
AI and Human Whiteboarding Partnership
AI Pipelines and Agents in Pure TypeScript with Mastra.ai
AI Engineering with the Google Gemini 2.5 Model Family
The New Code
Agentic GraphRAG: Simplifying Retrieval Across Structured and Unstructured Data
Forget RAG Pipelines: Build Production-Ready Agents in 15 Minutes
Analyzing 10,000 Sales Calls With AI In 2 Weeks
My AI Thinks I'm Eating My Feelings (and Other Nutritional Insights)
RAG Evaluation Is Broken! Here's Why (And How to Fix It)
Vercel AI SDK Masterclass: From Fundamentals to Deep Research
Trust, but Verify: Knowledge Agents for Finance Workflows
Stop Guessing: Build Robust AI with Layered CoT
The Model Isn't Wrong—You're Just Bad at Prompting
Tool Calling Is Not Just Plumbing for AI Agents
Voice Agents: the good, the bad, and the ugly
Your LLM Ran Out of Knowledge: Now What?
Claude Plays Minecraft
Ionic Launch: Opening the economy to AI agents
No More Bad Outputs with Structured Generation
Pydantic is STILL all you need
Building with Anthropic Claude: Prompt Workshop
Open Models track
Using AI to Build an Infinite Game
Pragmatic AI with TypeChat
AI Engineering 201: The Rest of the Owl
Pydantic is all you need
Principles for Prompt Engineering
AI Engineer Summit 2023, Day 1 Livestream