tool-use
187 talks
Your Agent Is a Lethal Trifecta (And What to Do About It)
Small Models, Big Results: Training a Finance Agent for Under $500
Building on the Codex Harness
Designing CLIs for Agents, Not Humans
Why Bigger Context Windows Won't Save Your Agent
Why We Deleted Our MCP Server and Rebuilt It
AI Hackers Are Faster Than Your Pen Test
Why AI Agents Should Have Their Own Sandbox
How AI Agents Pay: Checkout in ChatGPT and Google AI Mode
How Many Credentials Should Your AI Agent Have? Zero.
Move Fast and Don't Break Things: Scaling Databases for the AI Era
Agents That Write Their Own Tools at Runtime
Dashboards Are Dead
We Built an AI Support Agent That Resolves 80% of Tickets
An Interaction Is All You Need
Why 99% Accurate Browser Agents Still Fail
The Dark Arts of Skill Engineering
Pinecone 2.0
Realtime Voice Agents with Frontier Intelligence
Voice Agents Can Just Do Things
Your Voice Agent is Just a Walkie Talkie
Agents Without Code: Skills, YAML, and Filesystems Replaced Python
ACP: The Universal Remote Control for AI Agents
Build-Time vs. Run-Time: Why Dev Tools Fail in Production
It's Tokens All The Way Down: How RLMs are Different
MCP Apps: Give the Model Data, Give the User a UI
From Coding to Knowledge Work Agents
Agent Spending Without Controls
The End of the Static Screen: Architecting Intent-Driven UX
When AI Agents Pay and Sellers Monetize: Building x402 Apps on AWS
Why Your AI Agent Needs a Wallet: USDC and Nanopayments
Your Agent Just Authorized What?!
AI Agents Are Just Distributed Systems Now
Tell the Robot What You Want
How to Avoid Disaster When Vibe-Coding a Billing Engine
The Agentic Commerce Stack
The Missing Layer in Agentic AI
How I automate my own job at Hugging Face using agents
IT Admin for the AI Workforce
Security Firewall for Agents
The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans
Scaling up Continual Learning
Anthropic's CCA Exam as a Field-Guide for Agentic Engineering
Your Agent Didn't Fail. Your Harness Did.
Why Agentic Systems Need Ontologies
Better Auth
Agentic Development Security
Agentic Security: Permissions, Provenance, and the Agent Supply Chain
It's 10pm. Do You Know Where Your Agents Are?
Agents Need Receipts, Not More Tool Calls
I've Never Seen Anything Scarier Than an LLM with Tool Calls
Claws Out: Securing and Building with OpenClaw
Stop AI Agent Hallucinations: 5 Techniques + Production Patterns
Building an ACP-Compatible Agent Live
Running a Chess YouTube Channel Entirely by AI
Teaching Coding Agents to Do Spreadsheets
How We Taught Agents to Use Good Retrieval
What if the harness mattered more than the model?
Field Guide to Fable
MCP Apps: Primitives, Discovery, and the Future of Software
The Future Is Domain-Specific Agents
The 100-Tool Agent Is a Trap
Your Agent's Biggest Lie: "I Searched the Web"
The agent-ready web: Simplify user actions with WebMCP
Stop Making Models Bigger, Make Them Behave
From Transcription to Live Music: Gemini's Audio Stack
From MCP to Scale: Pipelines That Build Themselves
Building Safe Payment Infrastructure for the Autonomous Economy
Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents
Why (Senior) Engineers Struggle to Build AI Agents
Reverse Engineering a Viking VoIP Phone Protocol with Claude Code
Let's Talk About FOMAT: Fear of Missing Agent Time
Introducing WebMCP: Agents in the Browser
Any-to-Any: Building Native Multimodal Agents
From 46% to 90%: Fine-Tuning Tiny LLMs for On-Device Agents
Harnesses in AI: A Deep Dive
Beyond Code Coverage: Functionality Testing with Playwright MCP
A Piece of Pi: Embedding the OpenClaw Coding Agent in Your Product
Give Your Chat Agent a Voice
Agentic Search for Context Engineering
Agents on the Canvas in tldraw
Building Conversational Agents
Build & deploy AI-powered apps
Everything I Learned Training Frontier Small Models
Scaling GitHub for your Agents
MCP = Mega Context Problem
Code Mode: Let the Code do the Talking
The Future of MCP
Bending a Public MCP Server Without Breaking It
Let LLMs Wander: Engineering RL Environments
Your MCP Server is Bad (and you should feel bad)
Spec-Driven Development: Agentic Coding at FAANG Scale and Quality
Claude Agent SDK [Full Workshop]
Building Intelligent Research Agents with Manus
Amp Code: Next Generation AI Coding
Minimax M2: Building the #1 Open Model
Agent Reinforcement Fine-Tuning
Future-Proof Coding Agents
Evolving Claude APIs for Agents
Building Cursor Composer
Five hard earned lessons about Evals
Real World Development with GitHub Copilot and VS Code
Realtime Voice AI
Useful General Intelligence
Agents vs Workflows: Why Not Both?
Building Conversational AI Agents
Building the Platform for Agent Coordination
Piloting agents in GitHub Copilot
Human seeded Evals
How agents will unlock the $500B promise of AI
How to Build Planning Agents without Losing Control
Design like Karpathy is watching
Real-world MCPs in GitHub Copilot Agent Mode
Full Spec MCP: Hidden Capabilities of the MCP Spec
The Rise of the Agentic Economy on the Shoulders of MCP
Automating Escrow with USDC and AI
AI Pipelines and Agents in Pure TypeScript with Mastra.ai
AI Engineering with the Google Gemini 2.5 Model Family
2025 in LLMs so far, illustrated by Pelicans on Bicycles
12-Factor Agents: Patterns of Reliable LLM Applications
MCP Is Not Good Yet
Agents, Access, and the Future of Machine Identity
Intro to GraphRAG
The Emerging Skillset of Wielding Coding Agents
Building voice agents with OpenAI
Building Agentic Applications with Heroku Managed Inference and Agents
Building Code First AI Agents with Azure AI Agent Service
"Data readiness" is a Myth: Reliable AI with an Agentic Semantic Layer
Introducing Strands Agents, an Open Source AI Agents SDK
Milliseconds to Magic: Real-Time Workflows Using the Gemini Live API and Pipecat
Ship it! Building Production Ready Agents
Unlocking AI-Powered DevOps Within Your Organization
Windsurf everywhere, doing everything, all at once
Building Protected MCP Servers
Remote MCPs: What We Learned from Shipping
MCP: Origins and Requests For Startups
Exposing Agents as MCP Servers with mcp-agent
Just do it. (let your tools think for themselves)
MCPs are Boring (or: Why We Are Losing the Sparkle of LLMs)
Supercharging developer workflow with Amazon Q Developer
AI Engineer World's Fair 2025, Day 1 Keynotes and MCP Track
Are MCPs Overhyped? A Rant about MCPs
Blender MCP and The Future Of Creative Tools
Breaking the Chain: Agent Continuations for Resumable AI Workflows
ChatGPT is poorly designed. So I fixed it
Letting AI Interface with Your App with MCP
MCP Agent Fine-tuning Workshop
The Future of Qwen: A Generalist Agent Model
The Knowledge Graph Mullet: Trimming GraphRAG Complexity
Why the Best AI Agents Are Built Without Frameworks
Function Calling Is All You Need
Self Coding Agents
Vercel AI SDK Masterclass: From Fundamentals to Deep Research
How We Build Effective Agents
Rethinking how we Scaffold AI Agents
How Windsurf Writes 90% of Your Code with an Agentic IDE
Reinforcement Learning for Agents
Building Agents with Model Context Protocol
Beyond APIs: How AI Web Agents Are Automating the "Long Tail" of Knowledge Work
Building Multi-agent Systems with Finite State Machines
How to Build AI Agents that Actually Work
Let's Build an Agent from Scratch
Privacy First Enterprise AI: Building AI Agents that Never Leave Your Security Boundary
This video was edited with AI agent. But how?
Tool Calling Is Not Just Plumbing for AI Agents
Why people think "agent" is a buzzword but it isn't
Customized, production-ready inference with open source models
Claude Plays Minecraft
Agentic Workflows on Vertex AI
Creating and scaling your own custom copilots with Azure AI Studio
How to Add Secure Code Interpreting in Your AI App
Ionic Launch: Opening the economy to AI agents
Build an AI Research Agent
Architecting and Testing Controllable Agents
Realtime Data Connectivity for AI
Making Open Models 10x Faster and Better for Modern Application Innovation
Pydantic is STILL all you need
Building State of the Art Open Weights Tool Use: The Command R Family
Building Reliable Agentic Systems
What's new from Anthropic and what's next
From Software Developer to AI Engineer
The Future of Knowledge Assistants
Open Models track
Pragmatic AI with TypeChat
Building Reactive AI Apps
Pydantic is all you need
The Age of the Agent