-
09:00–09:05Welcome — Day 2John Allsopp
-
09:10–09:40KeynoteJeremy Howard
-
09:40–09:58Craft in the Time of AgentsAnnie Vella
-
10:00–10:20What If You Never Needed an API Key Again? Building a Mesh LLM From Spare ComputeMic Neale
-
10:20–10:38Towards Long-Horizon TasksZixuan Li
-
10:50–10:55Morning keynote outroJohn Allsopp
-
12:00–12:18Deploying AI at the Edge: Model Compression and Hardware-Aware OptimizationShivay Lamba
-
12:20–12:38When a Small Language Model Beat Our LLM in ProductionAvni Bhatt
-
12:40–12:58Multi-Model Collaboration with Claude Code: How to Measure What Actually WorksJack Rudenko
-
13:00–13:18Edge AI with Direct Device ControlJeremy Kelaher
-
13:20–13:38COBOL and AI: Building a Self-Serve Knowledge Layer for 2,000 Batch JobsMatthew Gillard
-
13:40–13:58Legacy Software + Agentic DiscoveryChris Rickard
-
15:00–15:18Why LLMs Fall for Stories (And 5 Production Patterns That Actually Stop Them)Mal Curtis
-
15:20–15:38Hacking the Model: AI Red Teaming in PracticePas Apicella
-
15:40–15:58Why Most AI De-Identification Fails in Production, And How We Built One Lawyers Actually TrustMoin Zaman
-
16:00–16:18Are Your AI Agents Secure? Defending the Privileged AgentDaizen Ikehara
-
16:20–16:38Your Agents Pass Every Benchmark—Then Memory Breaks Them in ProductionAnanya Roy
-
16:40–16:58AI Agents Are Distributed SystemsLovee Jain
-
12:00–12:18Spec driven AI development - A Real World PerspectiveNick Beaugeard
-
12:20–12:38Building SDKs in the Agentic EraMark McDonald
-
12:40–12:58AGENTS.md is the wrong conversationJakub Riedl
-
13:00–13:18Engineering without reading codeBen Taylor
-
13:20–13:38The Death of DocumentationJosh Gillies
-
13:40–13:58Designing Inference-Native SystemsSajjad Kamal
-
15:00–15:18Agentic SAST: Building an AI Pipeline for Rule Synthesis and Root-Cause Vulnerability AnalysisDanila Sashchenko
-
15:20–15:38AI After an ApocalypseSimon Knox
-
15:40–15:58Stop vibing your agents to production: applying ML discipline to agent developmentJustin Barias
-
16:00–16:18Fully Automated Luxury Gay Space EngineeringDaniel Rodgers-Pryor
-
16:20–16:3812TB of AI coding agent logs - what works, what failsDave Slutzkin
-
16:40–16:58Slop is a standards problemDavid Lewis
-
12:00–12:25Not Everything Needs an LLMDave Hall
-
12:30–12:55The AI Tax and "legal" ways to minimise itKrishna kanth Mundada
-
13:00–13:25Your engineers aren't afraid of AI. They're afraid of becoming junior again.Andy Kelk
-
13:30–13:55Panel: Engineering RealityAJ Fisher, Dave Hall, Krishna kanth Mundada, Andy Kelk
-
15:00–15:25From AI Survey to Production: What the Readiness Gap Actually Looks LikeDr Christian Dandre
-
15:30–15:55What We Learned Taking a Culture-First Approach to AI Adoption at scaleEric Grigson, Paul Hughes
-
16:00–16:25Beat Burnout, Find Flourishing: The AI EditionNavin Keswani
-
16:30–16:55Panel: Culture & PeopleAndrew Murphy, Dr Christian Dandre, Eric Grigson, Paul Hughes, Navin Keswani
-
11:15–11:35Build Agent-Powered Workflows on Notion Developer PlatformEsti Frischling
-
11:40–12:00Why Engineering Velocity Still BreaksAldo Schumann
-
14:10–14:30Stop Rebuilding Authorisation: Accelerating AI Agent DevelopmentDaizen Ikehara, Kevin Akermanis
-
14:35–14:55Hacking the Model: AI Red Teaming in Practice
-
07:30–08:45AI Leaders Roundtable Breakfast