Software Engineering (Day 1 Midday)

  1. Fail fast, fix faster: Why faster AI models beat smarter ones AJ Fisher Technologist & Writer ajfisher.me
  2. Building Frameworks Building Systems Ally Macdonald Staff Builder Stile Education
  3. Why AI coding tools might not make the slightest difference Jason Cornwall Head of Engineering Enablement SEEK
  4. Constitutional Prompting: Making AI Coding Agents Reliable Without the Iteration Tax Prem Pillai Sr. AI Engineer Block Inc
  5. From Zero to Production: How 15 Engineers Shipped a Production LLM Product with AI Coding Tools Michael Zhang Principal ML Engineer MYOB
  6. Multi-Armed Bandits: The Scientific Shotgun for Evals Ron Au Senior Software Engineer Canva (Leonardo.Ai)
Watch replay

Software Engineering (Day 1 Afternoon)

  1. Engineering for the Agentic Web When 50% of Your Traffic is Robots Janna Malikova Software engineer Tomato Elephant Studio
  2. The AI Control Plane: When Your Infrastructure Becomes the Context Window Bojan Zivic Director - AI & Modernisation V2ai
  3. Treating Infrastructure as Data: Building an AI-Native Control Plane Jeffrey Aven Maintainer StackQL Studios
  4. Your Agent Doesn't Like Your APIs Mike Chambers Senior Developer Advocate AI AWS
  5. Agentic Self-Healing in Production Jack McNicol Lead Agentic Engineer SuperIT
  6. How Canva built an Agentic Support Experience using Langfuse Observability Sergey Lakovlev; Sahil Bahl Lead ML Engineer Canva
Watch replay

Software Engineering (Day 2 Midday)

  1. Spec driven AI development - A Real World Perspective Nick Beaugeard Managing Director Released Pty Ltd
  2. Building SDKs in the Agentic Era Mark McDonald Gemini Developer Experience Google DeepMind
  3. AGENTS.md is the wrong conversation Jakub Riedl Technical Founder ctx|
  4. Engineering without reading code Ben Taylor Product Engineering Team Lead Stile Education
  5. The Death of Documentation Josh Gillies Senior Software Engineer Prefactor
  6. Designing Inference-Native Systems Sajjad Kamal CEO OnSet Health
Watch replay

Software Engineering (Day 2 Afternoon)

  1. Agentic SAST: Building an AI Pipeline for Rule Synthesis and Root-Cause Vulnerability Analysis Danila Sashchenko Security Engineer, previously Offensive Security Engineer TikTok
  2. AI After an Apocalypse Simon Knox Computer Programmer apartments.com.au
  3. Stop vibing your agents to production: applying ML discipline to agent development Justin Barias Lead AI Engineer Australian Government
  4. Fully Automated Luxury Gay Space Engineering Daniel Rodgers-Pryor Head of Stile AI Labs Stile Education
  5. 12TB of AI coding agent logs - what works, what fails Dave Slutzkin CEO Cadence
  6. Slop is a standards problem David Lewis Engineering Manager Nine Entertainment
Watch replay