Building Frameworks Building Systems
How Many Agents Are Too Many? The Hidden Cost of Multi-Agent Systems
Code Trust and Verification for the AI Era
Craft in the Time of Agents
Opening Words
Beyond Silicon Valley: Building AI Governance on the Fair Go Principle
When a Small Language Model Beat Our LLM in Production
19Cabs: 1115 Drivers, 500 Customers, 90 Days from Idea — And Why We Still Had to Stop and Rethink AI
Don't Be Cheap: AI and the Appearance of Engineering
The AI Control Plane: When Your Infrastructure Becomes the Context Window
Who Needs a LoRA?
Everyone Wants AI Capacity Now. Few Are Actually Running It.
Agent Observability: Monitoring and Understanding Agents at Internet Scale
Not Everything Needs an LLM
Build Agent-Powered Workflows on Notion Developer Platform
Everything Is a Factory
State of the AI Model Landscape
Stop Blocking, Start Building: Rethinking Governance for the Agentic Era
Why Your Coding Agent Forgets Everything
Enabling Safe AI Experimentation for Non-Technical Founders
Agentic Self-Healing in Production
The State of the AI Engineering Job Market in Australia
Engineering for the Agentic Web When 50% of Your Traffic Is Robots
Why AI Coding Tools Might Not Make the Slightest Difference
Treating Infrastructure as Data: Building an AI-Native Control Plane
Keynote
How to Get Fired as an AI Engineer
The Red Flags of Vibe Coding a Dating App
Building Sdks in the Agentic Era
The Agentic Contract: A Practical Framework from Enterprises Shipping Agents to Production
What If You Never Needed an API Key Again? Building a Mesh LLM from Spare Compute
Flue: The Agent Harness Framework, at Cloudflare
From Zero to Production: How 15 Engineers Shipped a Production LLM Product with AI Coding Tools
Your Agent Doesn't Like Your APIs
Close Your Agentic Loop
AI Hamsters: Circling Your Way to Success
Build Long Running AI Agents That Pause Resume and Never Lose Context with ADK
Beyond Forgetful Bots: Architectural Patterns for Persistent, Proactive Claw-Style AI Agents
Spec Driven AI Development - a Real World Perspective
Having Your Cake and Eating It: An Implementation Guide for Privacy with AI
Democratizing Frontier LLMs - Cloud-Cluster Scale Intelligence Running on Any Desktop PC
Constitutional Prompting: Making AI Coding Agents Reliable Without the Iteration Tax
Multi-Armed Bandits: The Scientific Shotgun for Evals
One Tool to Rule Them All: Building a Fast AI Agent for Real-Time Response
How Canva Built an Agentic Support Experience Using Langfuse Observability
Token Town (Why Compute Strategy Is Product Strategy)
How Canva Built an Agentic Support Experience Using Langfuse Observability
Deploying AI at the Edge: Model Compression and Hardware-Aware Optimization
Orbital Lasers Vs for Loops: Economically Matching Models to Tasks
Evaluation Precedes Evolution: Rubrics as the Load-Bearing Infrastructure of Self-Improving Agents
Regulatory AI: Building Intelligent Compliance Into Financial Operating Systems
Your AI Can’t Engineer (Yet)
Three Lanes Below One Millisecond: A Rust SDK for Gemini Live
The Software Engineer Who Don't Code
Our AI Hallucinated in Production: How We Fixed It with Evals
Towards Long-Horizon Tasks
