Schedule

How to Build Agents That Run for Hours (Without Losing the Plot)

Skill Issue: How We Used AI to Make Agents Actually Good at Supabase

Let's go Bananas with GenMedia

Codex and Subagents

Agentic Search for Context Engineering

AI SDK v6

Mind the Gap (In your Agent Observability)

OpenClaw Open Hours #1

Make your own event-sourced agent harness in 60 seconds

TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM

Build & deploy AI-powered apps

Skills at Scale

Playground in Prod - Optimising Agents in Production Environments

Building Your Own Secure AI Workflows: Human-in-the-Loop Automation with n8n

OpenClaw Open Hours #2

Building Conversational Agents

Mergeable by default: Building the context engine to save time and tokens

Shipping complex AI applications with Braintrust

Building LLMs for Production

Ralph Loops: Build Dumb AI Loops That Ship

OpenClaw Open Hours #3

Running LLMs Locally: A Practical Benchmarking Walkthrough on a GPU Workstation

Build Your First Demand-Driven Context Base: Let AI Agents Tell You What They Need

Build & deploy AI-powered apps

Ship Real Agents: Hands-On Evals for Agentic Applications

Everything You Need To Know About Agent Observability

OpenClaw Open Hours #4

Opening Address

Harness Engineering: How to Build Software When Humans Steer and Agents Execute

OpenClaw update

Expo Session – Encord #1

Expo Session – Arize #2

Stop babysitting your agents: building a context engine for mergeable code

Expo Session – Bright Data #1

Two Roads to Durable Agents: Replay vs. Snapshot

Context Graphs 101: What They Are and How to Get Started in 5 Minutes

OpenClaw AMA

Harness Engineering AMA

Beyond Transcription: Building Voice AI That Actually Understands Conversations

Why building eval platforms is hard

The agent-ready web: Simplify user actions with WebMCP

LLM codegen fails and how to stop 'em

Agents on the Canvas in tldraw

AI on Android: Ask me Anything

What the Best Agents Share

I Gave an AI Agent the Keys to My Life (Here's What Happened)

Hierarchical Memory: Context Management in Agents

Agentic Evaluations at Scale — For Everybody

Everything I Learned Training Frontier Small Models

Why (Senior) Engineers Struggle to Build AI Agents

Skills issue. How agent skills get written, evaluated and improved out in the wild.

Personalization in the Era of LLMs

Building a Chess Coach

Proving Agents Correct: Memory Architecture and Formal Verification for Clawdbot

Build & deploy AI-powered apps

Building the Justice AI Unit: Shipping Production AI Inside Government

Rethinking Document Reading for Legal AI: From OCR Pipelines to Multimodal Agents

The Art & Science of Benchmarking Agents

What Breaks When You Build AI Under Sovereignty Constraints

TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM

Leadership Lunch

Reverse engineering a Viking VOIP phone protocol with Claude Code

Expo Session – Zed #1

The maturity phases of running evals

Expo Session – Bright Data #2

Untethered Productivity

Expo Session – Tessl #2

BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike

Expo Session – Together AI #2

Expo Session – Runpod #2

Expo Session – Modal #2

Expo Session – Cloudflare #1

Building Interactive UIs in VS Code with MCP Apps

Connecting the Dots with Context Graphs

What We Learned From a Zillion Agent Tasks

Scaling Agents on Kubernetes with acpx and ACP

Sovereign Escape Velocity: AI Ownership with Open Models

Harnesses in AI: A Deep Dive

What's new in AI Audio?

Why Your AI UX Is Broken (and It's Not the Model's Fault)

Self Driving Products: Engineering the Pipeline from Product Signals to Pull Requests

Context Graphs for Explainable, Decision-Aware AI Agents

You can't just one shot it

Any-to-Any: Building Native Multimodal Agents

Viktor — AI Coworker That Lives in Slack

Open-Source Agents Ecosystem

SWE-rebench: Lessons from Evaluating Coding Agents on Real Software Engineering Tasks

Combine Skills and MCP to Close the Context Gap

Self-Evolving AI Agents: Lessons from Winning an International Agent Competition

Text Diffusion

How agent o11y differs from traditional o11y

From Writing Code to Designing Systems: How the Developer Role Has Changed

Why Rust is the Ideal Language for Vibe-Coding

RAG is dead, right??

Expo Session – Qodo #1

Expo Session – Runpod #1

Building safe Payment Infrastructure for the autonomous economy

Software Engineering + AI = ?

It Ain't Broke: Why Software Fundamentals Matter More Than Ever

Gemma, DeepMind's Family of Open Models

What Do Models Still Suck At?

AgentCraft: Putting the Orc in Agent Orchestration

Building pi in a World of Slop

Expo Session – Zed #2

Building AI Systems That Ship

Benchmarking semantic code retrieval on Claude Code

Spec-Driven Testing for Agents With A Brain the Size of A Planet

Snapshot the Machine, Not the State: Firecracker MicroVMs for Durable AI Agents

How to talk to statues

Replacing 12K LoC with a 200 LoC Skill

Context Is the New Code

Single Sign-On for MCPs

Every API Is a Tool for Agents

Open Models at Google DeepMind

Rewiring the State

Scaling Reinforcement Learning: Lessons from Trillion-Token Deployments at Fortune 500s

A Piece of PI – Embedding The OpenClaw Coding Agent In Your Product

Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents

MLX Genmedia

Q&A (continuation of Open Models at Google DeepMind session)

The Embedding Infrastructure Nobody Built (So We Did)

The Year of Latency Debt (And How Big Tech Is Paying It Down)

MCP UI

Most Enterprise Agentic Projects Are Doomed — Here’s Why

What goes into building generative image and video models at scale

The Domain-Native AI Organization: How to Leverage Domain Expertise

Agents for Creative Optimisation at Scale: In Theory and in Practice

Why MCP and ChatGPT Apps Use Double Iframes (And What That Means for Your App)

The Missing Primitive for Agent Swarms

Lawrence Jones - Fighting AI with AI

Think You Can Build a Game with AI? Think Again! The New Games Are Just Being Invented!

Scaling the Next Paradigm of Heterogeneous Intelligence

Beyond Components: Designing Generative UI for MCP Apps

CI/CD Is the New Breaking Point of Agentic Software

Factory Missions - Super Long Running Agents

Agentic Panel with KP Sawhney

Expo Session – Together AI #1

Expo Session – Arize #1

Expo Session – Qodo #2

Task Fidelity Scaling Laws

Stop babysitting your agents: building a context engine for mergeable code

Expo Session – Modal #1

Comprehend First, Code Later: The AI Skill I Rely On Daily

Mastering AI Pricing: Flexible & Agile Monetization for your AI solutions

Expo Session – Tessl #1

Why Can't Anyone Answer Questions About the Business?

Expo Session – Tailscale #1

Expo Session – Comet #1

You Might Not Need 50 Diffusion Steps

Lessons from Scaling GitHub's Remote MCP Server

Your Coding Agent Should Do AI System Engineering

Software Engineering Is Becoming Plan and Review

Accelerating AI on Edge

Beyond Code Coverage: Functionality Testing with Playwright

Let’s Talk About FOMAT – Fear of Missing Agent Time

Your Agent Is an Infinite Canvas

How Building with AI Can Double the Throughput of Your Engineering Team

Office Hours with Deepmind

Stop Rolling Your Own Model Router

Cooking with Agents in VS Code

Bringing MCPs to the Enterprise

Agents Don't Do Standups: Building the Post-Engineer Engineering Org

Office Hours with Deepmind

Does GenAI "belong" to data scientists?

Stop Making Models Bigger. Make Them Behave

Build an Aura Agent in 10 Minutes — From Unstructured Content to Knowledge Graphs

Expo Session – AMA: AIE Europe with swyx

Can LLMs generate Enterprise Quality Code?

Fireside Chat with Gergely Orosz and Linear's Tuomas Artman

Agents need more than a chat

The Friction Is Your Judgment