planning
35 talks
Dashboards Are Dead
Long-Horizon Agents Need Experiments, Not Just Prompts
Multimodal Collaborative Agents for Next-Gen Commerce
Velocity Sickness: What Happens When Your Whole Team Gets 10x Faster
Local Agentic Theory For Mobile Games
Why We Killed Our Multi-Agent Pipeline
Every Harness Will Become A Claw
Autonomous Agents for Scientific Tasks
Software engineering is not about writing code
Beyond the Harness: A Journey Towards Adaptive Engineering
Context Graphs for Explainable, Decision-Aware AI Agents
Software Engineering Is Becoming Plan and Review
Collaborative AI Engineering: One Dev, Two Dozen Agents, Zero Alignment
The Infinite Software Crisis
Code World Model: Building World Models for Computation
The Cure for the Vibe Coding Hangover
The Unbearable Lightness of Agent Optimization
Designing AI-Intensive Applications
How to Build Planning Agents without Losing Control
Top Ten Challenges to Reach AGI
A Taxonomy for Next-gen Reasoning
Measuring AGI: Interactive Reasoning Benchmarks for ARC-AGI-3
Building Code First AI Agents with Azure AI Agent Service
Effective agent design patterns in production
Reasoning + RL
Real AI Agents Need Planning, Not Just Prompting
How Deep Research Works
How to Improve Your Agents: Academic Lit Review
Let's Build an Agent from Scratch
Why people think "agent" is a buzzword but it isn't
Build an AI Research Agent
Realtime Data Connectivity for AI
More Nodes Is All You Need
Building State of the Art Open Weights Tool Use: The Command R Family
Building Reliable Agentic Systems