Web Directions the AI engineering conference accessibility Agentic Web agents agile AI AI Engineering AI Native Dev AI safety AI/ML in the browser architecture authentication autonomous agents browser API career development CI/CD code modernisation code smell coding agent context engineering Conversational UI cryptography culture Design design thinking developer tools diversity documentation economics edge computing Engineering Leadership environmental impact Ethics evals financial systems generative AI governance image optimisation iot junior developers leadership legacy code lethal trifecta LLMs local-first Machine Learning management MCP mental health mentoring o11y observability offline open source performance privacy product development product management product strategy prompting prototyping psychology regulation security software engineering spec driven development TDD testing wellness Presentations 12TB of AI coding agent logs – what works, what fails Dave Slutzkin 19Cabs: 1115 drivers, 500 customers, 90 days from idea — and why we still had to stop and rethink AI Balram Singh Agent Observability: Monitoring and Understanding Agents at Internet Scale Daniel Nadasi Agentic SAST: Building an AI Pipeline for Rule Synthesis and Root-Cause Vulnerability Analysis Danila Sashchenko Agentic Self-Healing in Production Jack McNicol AGENTS.md is the wrong conversation Jakub Riedl AI After an Apocalypse Simon Knox AI Agents Are Distributed Systems Lovee Jain AI Hamsters: Circling Your Way to Success Muhammad Ali Are Your AI Agents Secure? Defending the Privileged Agent Daizen Ikehara Beat Burnout, Find Flourishing: The AI Edition Navin Keswani Beyond Forgetful Bots: Architectural Patterns for Persistent, Proactive Claw-Style AI Agents Navan Tirupathi Beyond Silicon Valley: Building AI Governance on the Fair Go Principle Aubrey Blanche Building Frameworks Building Systems Ally Macdonald Building SDKs in the Agentic Era Mark McDonald Close your agentic loop Moss Ebeling COBOL and AI: Building a Self-Serve Knowledge Layer for 2,000 Batch Jobs Matthew Gillard Code Trust and Verification for the AI Era Andre Kolodochka Constitutional Prompting: Making AI Coding Agents Reliable Without the Iteration Tax Prem Pillai Craft in the Time of Agents Annie Vella Democratizing Frontier LLMs: Cloud-cluster Scale Intelligence Running on Any Desktop PC Obadiah Pewee Deploying AI at the Edge: Model Compression and Hardware-Aware Optimization Shivay Lamba Designing Inference-Native Systems Sajjad Kamal Don’t Be Cheap: AI and the Appearance of Engineering Birger Halfmeier Edge AI with Direct Device Control Jeremy Kelaher Enabling Safe AI Experimentation for Non-Technical Founders Inga Pflaumer Engineering for the Agentic Web When 50% of Your Traffic is Robots Janna Malikova Engineering without reading code Ben Taylor Evaluation Precedes Evolution: Rubrics as the Load-Bearing Infrastructure of Self-Improving Agents Tanya Dixit Everyone Wants AI Capacity Now. Few Are Actually Running It. Daniel Apps Everything Is a Factory Geoffrey Huntley Fail fast, fix faster: Why faster AI models beat smarter ones Andrew Fisher Flue: The Agent Harness Framework Michael Hart From AI Survey to Production: What the Readiness Gap Actually Looks Like Dr Christian Dandre From Zero to Production: How 15 Engineers Shipped a Production LLM Product with AI Coding Tools Michael Zhang Fully Automated Luxury Gay Space Engineering Daniel Rodgers-Pryor Hacking the Model: AI Red Teaming in Practice Pas Apicella Having your cake and eating it: An implementation guide for privacy with AI Nick Lothian How Canva built an Agentic Support Experience using Langfuse Observability Sergey Iakovlev How Many Agents Are Too Many? The Hidden Cost of Multi-Agent Systems Anannya Roy Chowdhury How to Get Fired as an AI Engineer Kanish Gosain Keynote Jeremy Howard Kill the God Agent Adesh Gairola Legacy Software + Agentic Discovery Chris Rickard Long-running Agents with ADK Nakul Gowdra Multi-Armed Bandits: The Scientific Shotgun for Evals Ron Au Multi-Model Collaboration with Claude Code: How to Measure What Actually Works Jack Rudenko Not Everything Needs an LLM Dave Hall One Tool to Rule Them All: Building a Fast AI Agent for Real-Time Response Ryan Samarakoon Optimising GenAI at Runtime with Experimentation and Guardrails Aaron Montana Orbital Lasers vs For Loops: Economically Matching Models to Tasks Stephen Sennett Our AI Hallucinated in Production: How We Fixed It With Evals Yicheng Guo Panel: Case Studies Andrew Fisher Panel: Engineering Reality Andrew Fisher Panel: Governance & Ethics Andrew Murphy Regulatory AI: Building Intelligent Compliance into Financial Operating Systems Theo Adis Shipping Sandboxed Workers for Notion Agents Adam Hudson Slop is a standards problem David Lewis Spec driven AI development – A Real World Perspective Nick Beaugeard State of the AI Model Landscape George Cameron Stop Blocking, Start Building: Rethinking Governance for the Agentic Era Hamish Songsmith Stop vibing your agents to production: applying ML discipline to agent development Justin Barias The Agentic Contract Matt Doughty The AI Control Plane: When Your Infrastructure Becomes the Context Window Bojan Zivic The AI Tax and “legal” ways to minimise it Krishna kanth Mundada The Application Layer Is the New Research Lab Abdul Karim The Death of Documentation Josh Gillies The Red Flags of Vibe Coding a Dating App Karina Pamamull The Software Engineer Who Don’t Code Yasith Fernando The State of the AI Engineering Job Market in Australia Jake Maloney Three Lanes Below One Millisecond: A Rust SDK for Gemini Live Vamsi Ramakrishnan Token Town (why compute strategy is product strategy) Sarah Sachs Towards Long-Horizon Tasks Zixuan Li Treating Infrastructure as Data: Building an AI-Native Control Plane Jeffrey Aven What If You Never Needed an API Key Again? Building a Mesh LLM From Spare Compute Michael Neale What We Learned Taking a Culture-First Approach to AI Adoption at scale Eric Grigson When a Small Language Model Beat Our LLM in Production Avni Bhatt Who Needs a LoRA? Charli Posner Why AI coding tools might not make the slightest difference Jason Cornwall Why LLMs Fall for Stories (And 5 Production Patterns That Actually Stop Them) Mal Curtis Why Most AI De-Identification Fails in Production, And How We Built One Lawyers Actually Trust Moin Zaman Why Your Coding Agent Forgets Everything Igor Costa Your Agent Doesn’t Like Your APIs Mike Chambers Your Agents Pass Every Benchmark – Then Memory Breaks Them in Production Ananya Roy Your AI Can’t Engineer (Yet) Theodoros Galanos Your engineers aren’t afraid of AI. They’re afraid of becoming junior again. Andy Kelk Speakers Dave Slutzkin Balram Singh Daniel Nadasi Danila Sashchenko Jack McNicol Jakub Riedl Simon Knox Lovee Jain Muhammad Ali Daizen Ikehara Navin Keswani Navan Tirupathi Aubrey Blanche Ally Macdonald Mark McDonald Moss Ebeling Matthew Gillard Andre Kolodochka Prem Pillai Annie Vella Obadiah Pewee Shivay Lamba Sajjad Kamal Birger Halfmeier Jeremy Kelaher Inga Pflaumer Janna Malikova Ben Taylor Tanya Dixit Daniel Apps Geoffrey Huntley Andrew Fisher Michael Hart Dr Christian Dandre Michael Zhang Daniel Rodgers-Pryor Pas Apicella Nick Lothian Sergey Iakovlev Sahil Bahl Anannya Roy Chowdhury Kanish Gosain Jeremy Howard Adesh Gairola Chris Rickard Nakul Gowdra Ron Au Jack Rudenko Dave Hall Ryan Samarakoon Aaron Montana Stephen Sennett Yicheng Guo Theo Adis Krishna kanth Mundada Andy Kelk Andrew Murphy Hamish Songsmith Adam Hudson David Lewis Nick Beaugeard George Cameron Justin Barias Matt Doughty Bojan Zivic Abdul Karim Josh Gillies Karina Pamamull Yasith Fernando Jake Maloney Vamsi Ramakrishnan Sarah Sachs Zixuan Li Jeffrey Aven Michael Neale Eric Grigson Paul Hughes Avni Bhatt Charli Posner Jason Cornwall Mal Curtis Moin Zaman Igor Costa Mike Chambers Ananya Roy Theodoros Galanos