Keynote

Shawn Wang

Editor & Founder , Latent.Space & Smol AI

Token Town (why compute strategy is product strategy)

Sarah Sachs

Eng Lead, AI , Notion

Token pricing is a noisy headline. What matters in production is what you pay per task once outputs get longer, retries creep in, and “good enough” models get deprecated. This talk breaks down the current dynamics of the frontier model market from the perspective of Notion AI product team on embarking this with No…

Everything Is a Factory

Geoff Huntley

Founder , Latent Patterns

Software development as we knew it is dead. The old world of hand-crafting every line, endless hiring cycles, and fragile vertical stacks has been overtaken by AI-driven software factories that turn simple prompts into fully functional software through automated iteration. This keynote traces the journey from the Ralp…

Why Your Coding Agent Forgets Everything

Igor Costa

CEO , Autohand AI

AI Hamsters Engineering: Circling Your Way to Success

Muhammad Ali

Senior Solution Architect , ClickHouse

Every AI engineer knows the loop — prompt tweaks, evals, regressions, repeat. It feels like going in circles. But that's not the problem. The problem is not knowing if each circle is tighter than the last. This talk is about how Langfuse turns iteration from an act of faith into something measurable — traces, scores, …

Fail fast, fix faster: Why faster AI models beat smarter ones

AJ Fisher

Technologist & Writer , ajfisher.me

The smartest model doesn't always win. In agentic coding loops, a model that is 10x faster but only marginally competent can often fail its way to success before a frontier model finishes reasoning. AJ Fisher breaks down the maths behind this counterintuitive result using diffusion models like Inception Labs' Me…

Beyond Silicon Valley: Building AI Governance on the Fair Go Principle

Aubrey Blanche

Founder , The Mathpath

Responsible AI isn’t culturally neutral. American AI development embeds distinctly American values — individual liberty, technological solutionism, and winner-takes-all competition. But what happens when these values clash with Australian cultural principles that prioritise collective welfare, egalitarianism, and the …

What If You Never Needed an API Key Again? Building a Mesh LLM From Spare Compute

Mic Neale

Principal Engineer , Block

The current AI stack has a dependency most of us don’t talk about: a handful of closed models from a handful of providers, and an API call standing between every agent and every action. Mic Neale — who helped build Goose, Block’s open-source agentic coding system — thinks that’s a problem worth solving at the infrastr…

Beyond Forgetful Bots: Architectural Patterns for Persistent, Proactive Claw-Style AI Agents

Navan Tirupathi

CTO , Architecture and AI Expert , Arivminds

Most AI agents are reactive chatbots—great for one-off queries, but they reset, forget, and lack initiative, failing in real-world use like personal assistants or autonomous workflows. This talk dives into the battle-tested architecture of Claw-family agents (OpenClaw and lightweight forks like NanoClaw, PicoClaw, …

Building Frameworks Building Systems

Ally Macdonald

Staff Builder , Stile Education

CI infrastructure is ripe for the vibing — so why don’t we? I have been. Our company must deliver 200 interactive science and maths games for millions of students this year. Only a few years ago were we making 30, by hand, for significantly fewer students. Rather than handcrafting 200 interactive games though…what …

Stop Blocking, Start Building: Rethinking Governance for the Agentic Era

Hamish Songsmith

Founder , ryora.ai

As AI moves from "chat" to "act," the risk surface is exploding. Traditional governance is too slow, too onerous, and often looks in the wrong places. Join this session to learn how to: - Identify the 3 fatal flaws of applying legacy governance to autonomous agents. - Implement the GRASP Framework: A 5-part approa…

Why AI coding tools might not make the slightest difference

Jason Cornwall

Head of Engineering Enablement , SEEK

Most “AI gives you 10x productivity” stories assume coding is the bottleneck. For large and mature companies this is almost never the case, so you roll out AI coding tools, people feel faster, but delivery metrics barely move. In this talk I’ll show how we used a Theory of Constraints approach at SEEK to find the actu…

Shipping Sandboxed Workers for Notion Agents

Adam Hudson

Software Engineer , Notion

In this talk, we will share how we built a platform at Notion that allows developers to extend AI agents with custom code. The system enables developers to write small programs that give their agents access to tools such as internal APIs and external services. We will focus on the engineering decisions that made th…

DGX Spark & Sovereign AI: Architecting Air-Gapped Agents

Thiago Shimada Ramos

AI & Cloud Native Consultant

The shift from mainframes to PCs in the 1980s removed gatekeepers by putting computing power directly in the hands of engineers. Today, NVIDIA DGX Spark does the same for AI, giving builders ownership of the machine instead of leaving compute, timelines, and progress under institutional control. In this session, I'…

Who Needs a LoRA?

Charli Posner

Builder , Stile Education

Can you faithfully edit hand-drawn illustrations using an image model you haven’t fine-tuned? Most practitioners assume you need a LoRA for style-faithful editing. I set out to prove otherwise — building a production system that edits character avatars in an educational platform, changing their facial expressions to m…

Constitutional Prompting: Making AI Coding Agents Reliable Without the Iteration Tax

Prem Pillai

Sr. AI Engineer , Block Inc

Every engineering team trying to automate developer workflows with AI agents hits the same wall: the iteration tax. You ask an agent to review a PR, scaffold a feature, or audit code quality — it does something almost right, you correct it, it overcorrects, you add guardrails, it gets confused. Four round-trips later …

Having your cake and eating it: An implementation guide for privacy with AI

Nick Lothian

Staff Engineer , N/A

Everyone wants privacy, but the best models require you to give up control of your data. What options are there for keeping data private but while still embracing the promise of AI? In this talk we'll take a practical, experience based look at options ranging from private models, trusted execution environments, dif…

Close your agentic loop

Moss Ebeling

Software Engineer , Optiver

Every time you've told an agent it broke the layout of your website, output the wrong schema or failed an invariant - you are the feedback loop. The teams achieving the best outcomes right now are focused on building better systems: automated feedback that allows agents to check their own work. Join to learn what clos…

How Many Agents Are Too Many? The Hidden Cost of Multi-Agent Systems

Anannya Roy Chowdhury

GenAI Developer Advocate , AWS

Multi-agent systems promise scalability and smarter reasoning—but in production, more agents often mean more cost, latency, and failure. This talk shares real-world engineering lessons, metrics, and architectural trade-offs to help you decide when multi-agent designs add value—and when a simpler approach performs bett…

Panel: Governance & Ethics

Andrew Murphy

CEO (Chief Everything Officer.) , Debugging Leadership

Aubrey Blanche

Founder , The Mathpath

Hamish Songsmith

Founder , ryora.ai

Nick Lothian

Staff Engineer , N/A

A moderated conversation closing the Governance & Ethics session. Andrew Murphy leads a discussion with Aubrey Blanche, Hamish Songsmith, and Nick Lothian on how principles, operational frameworks, and hands-on privacy implementation come together in practice.

Kill the God Agent

Adesh Gairola

Co-founder & CTO , raxIT Labs

Your multi-agent system probably has one orchestrator with access to every tool, every database, every API. If that agent gets injected, the entire toolchain is compromised. Guardrails won't save you. In this session, learn three architectural patterns that move agent security from hope to proof: how to isolate agent …

Multi-Armed Bandits: The Scientific Shotgun for Evals

Ron Au

Senior Software Engineer , Canva (Leonardo.Ai)

A/B testing is too rigid a tool for AI systems. You're stuck serving worse results for the duration of the experiment and getting billed for slower models while three providers release SOTA updates this week. Steal a trick from data science instead and use multi-armed bandits to organically surface ideal models, pr…

Agent Observability: Monitoring and Understanding Agents at Internet Scale

Daniel Nadasi

Principal Engineer , Google

Agent usage is exploding (if you haven't noticed) with an unprecedented transformation in the activities of both developers and other roles creating enormous volumes of new autonomous, dynamic decision making programs that can do extraordinary things but also hallucinate, misunderstand and in the worst case cause real…

Engineering for the Agentic Web When 50% of Your Traffic is Robots

Janna Malikova

Software engineer , Tomato Elephant Studio

Over the last two years, our customer web traffic changed: today around 50% of visitors were unknown browsers and AI agents. The era of aligning with the traditional search engine crawlers with Core Web Vitals is shifting; the new challenge is feeding focused low-noise context to autonomous agents and Large Language M…

Regulatory AI: Building Intelligent Compliance into Financial Operating Systems

Theo Adis

AI Systems Architect | Financial Operating Systems (Fintech) , Accelerate Funding Group

Regulatory AI represents the next evolution of financial systems, where compliance, risk, and governance are no longer external constraints, but embedded, intelligent capabilities within the platform itself. This session showcases the design and implementation of a Regulatory AI framework developed across the Accel…

Our AI Hallucinated in Production: How We Fixed It With Evals

Yicheng Guo

Senior Machine Learning Engineer , REA Group

We shipped one of REA Group’s first generative AI features to production: Property Highlights, which turns long real-estate listings into three skimmable takeaways. The demo was easy; real traffic wasn’t—hallucinations showed up in front of real users. This talk covers how we built an evaluation stack to launch saf…

The AI Control Plane: When Your Infrastructure Becomes the Context Window

Bojan Zivic

Director - AI & Modernisation , V2ai

We've spent a decade codifying infrastructure, Terraform, Pulumi, CDK. This session explores what happens when you treat infrastructure as a queryable data layer: exposing cloud state, Skills giving agents reusable operational knowledge, and LLM gateways routing and governing model access. You'll see how policy-as-c…

19Cabs: 1115 drivers, 500 customers, 90 days from idea — and why we still had to stop and rethink AI

Balram Singh

AI architect , Publicis Sapient

Balram Singh is a frontend-focused full-stack engineer and architect with over a decade of experience building web and mobile applications. He currently works at Publicis Sapient in Australia, delivering large-scale digital solutions across enterprise clients. His current focus is on applying AI beyond development sp…

we fired our LLM judge

Jack Silman

Staff Software Engineer , Commonwealth Bank of Australia

Abdul Karim

Applied AI Scientist , Commonwealth Bank of Australia

Every team building with LLMs hits the same wall. Someone in the room asks: “Why are we doing evals? Isn’t this slowing us down?” And honestly if your evals aren’t tied to anything real, they probably are. You’re running benchmarks, getting green ticks, and your agent is still giving users wrong answers in product…

Treating Infrastructure as Data: Building an AI-Native Control Plane

Jeffrey Aven

Maintainer , StackQL Studios

StackQL provides a unified control plane data model for agents, tools, processes and humans to interact with. The StackQL MCP server exposes this unified interface to AI agents, allowing them to query, provision, and update cloud resources, including executing lifecycle operations. In this session we will demonstr…

Democratizing Frontier LLMs - Cloud-cluster scale intelligence running on any Desktop PC

Obadiah Pewee

Chief Executive Officer , Monadd-AI

Explore the engineering breakthroughs behind running state-of-the-art, ultra-large Mixture-of-Experts models (100B-600B+ parameters) entirely offline on consumer-grade desktop hardware. This session dives deep into our novel storage-centric inference engine, developed by Monadd-AI and a research partner, that leverage…

Orbital Lasers vs For Loops: Economically Matching Models to Tasks

Stephen Sennett

AWS Community Hero & Lead Consultant at V2 AI , V2 AI

Most developers pick their AI model the same way: use the biggest, smartest one available for everything. Bash script? Opus. Dockerfile? Whatever's at the top of the dropdown. Then they hit their usage limits halfway through the day and lose the productivity gains they were chasing. After too many cases of my workflow…

Your Agent Doesn't Like Your APIs

Mike Chambers

Senior Developer Advocate AI , AWS

Every API you've shipped was designed for a human reading docs. Agents don't read docs - they load your entire tool schema into a context window every call, then burn tokens guessing which endpoint to try. Take a standard accounting API — clean REST, solid docs, every endpoint you'd expect. Point an agent at it wit…

Enabling Safe AI Experimentation for Non-Technical Founders

Inga Pflaumer

Consulting CTO

Inga Pflaumer shares how a pre-seed startup without technical leadership was able to quickly build and iterate on their product using AI without sacrificing safety, focusing on setting up the right foundations and lightweight guardrails so non-technical founders could experiment independently while staying within secu…

Your Agents Pass Every Benchmark—Then Memory Breaks Them in Production

Ananya Roy

AI Architect , Databricks

You add memory to your agent, it works great in testing, and you ship it. A few weeks later, outputs start getting worse and nobody can figure out why. The agent is pulling in old information that's no longer true, retrieving context that's loosely related but clutters its reasoning, and sometimes carrying forward bad…

Agentic Self-Healing in Production

Jack McNicol

Lead Agentic Engineer , SuperIT

Your pipeline breaks at 2am. Nobody's watching. By morning, it's already fixed. That's not wishful thinking — that's agentic self-healing in production. In this talk, we'll explore how AI agents can monitor, diagnose, and autonomously recover failing pipelines without human intervention. We'll cover the patterns and…

Panel: Case Studies

AJ Fisher

Technologist & Writer , ajfisher.me

Theo Adis

AI Systems Architect | Financial Operating Systems (Fintech) , Accelerate Funding Group

Balram Singh

AI architect , Publicis Sapient

Inga Pflaumer

Consulting CTO

A moderated conversation closing the L2 Case Studies session. AJ Fisher leads a discussion with Theo Adis, Balram Singh, and Inga Pflaumer about what it really took to ship AI into live businesses across regulated finance, transport, and agent tooling.

How Canva built an Agentic Support Experience using Langfuse Observability

Sergey Lakovlev

Lead ML Engineer , Canva

Sahil Bahl

Senior ML Engineer , Canva

At Canva, our support experience is powered by multiple AI systems, from real-time assistance to asynchronous ticket resolution that handles complex, multi-step workflows and escalates to humans when needed. In this talk, we’ll share how we took these systems from MVP to serving Canva’s 250M+ users, and the infrastruc…

Keynote

Jeremy Howard

Founding CEO & Co-founder , Answer.AI & fast.ai

Craft in the Time of Agents

Annie Vella

Distinguished Engineer , Westpac New Zealand

You feel more productive than you’ve ever been. You put on the Iron Man suit and now you’re building things in hours that used to take weeks. And you’re exhausted by Wednesday. The craft that used to sustain you — the flow of writing code, the satisfaction of making something work — has given way to a middle loop of s…

State of the Model Market

George Cameron

Co-founder & CPO , Artificial Analysis

Spec driven AI development - A Real World Perspective

Nick Beaugeard

Managing Director , Released Pty Ltd

AI demos are easy. Production systems are not. In this session, we move beyond hype and explore what it actually takes to deliver AI systems that work in the real world. Not experiments. Not playgrounds. Proper, spec-driven, commercially accountable systems. You will see how clear specifications, structured prom…

Not Everything Needs an LLM

Dave Hall

Principal Consultant , Dave Hall Consulting

I got frustrated. My support tickets kept getting routed to the wrong team. Every misroute added a day to resolution. I decided to fix it. The obvious approach in 2024 was to throw the problem at an LLM. I knew that wasn’t going to work. The overlap in team responsibilities made it impossible to write a concise pro…

Observability and Evaluation for LLM Apps and Agentic AI with Langfuse

Muhammad Ali

Senior Solution Architect , ClickHouse

Shipping an LLM app is easy. Knowing whether it's actually working is hard. Unlike traditional software, LLM systems and agentic pipelines can run without errors while producing wrong or degraded answers — and with agents making multi-step decisions across tools and APIs, a single bad output can cascade silently throu…

Deploying AI at the Edge: Model Compression and Hardware-Aware Optimization

Shivay Lamba

Senior AI/ML Engineer , Qualcomm

Large AI models often struggle to meet the latency, memory, and power constraints required for real-world edge deployments. This talk explores practical techniques for making modern AI models efficient enough to run on-device using model distillation, quantization, and hardware-aware optimization strategies. Attendees…

When a Small Language Model Beat Our LLM in Production

Avni Bhatt

Sr Enterprise Architect , Commonwealth Bank

Large language models are often the default choice for production AI systems, even when the task does not require broad reasoning or generative depth. In this talk, I will share a real production case where an LLM-based solution underperformed on latency, cost, and reliability and was ultimately replaced, in part, by …

Building SDKs in the Agentic Era

Mark McDonald

Gemini Developer Experience , Google DeepMind

In the time it takes to train a frontier model, the open source libraries we rely on can undergo significant changes. This creates an ongoing delta between what an LLM coding agent suggests and what the best practices are, or what even works. For the team at Google DeepMind, this is an ongoing challenge as we publish …

The AI Tax and "legal" ways to minimise it

Krishna kanth Mundada

Software Engineer , Versent

AI tools feel productive. That's the problem. A 2025 METR study found experienced developers were 19% slower using AI on their own codebases, yet believed they were 20% faster. I didn't need a study to tell me something was off. I could feel it: more code shipping, more bugs slipping through, reviewing functions I co…

AGENTS.md is the wrong conversation

Jakub Riedl

Technical Founder , ctx|

AGENTS.md started as a simple way to guide coding agents, but many teams are discovering that a default or poorly written one can actually make agents worse. Obvious facts, vague rules, outdated guidance, and generic instructions often confuse models more than they help. But manually crafting it won’t cut it once …

Multi-Model Collaboration with Claude Code: How to Measure What Actually Works

Jack Rudenko

CTO , MadAppGang

We built Claudish, a free open-source proxy that lets Claude Code work with any AI model. 15+ providers directly - Google, OpenAI, xAI, Kimi, MiniMax, and more. OpenRouter for even wider access. Or fully offline with Ollama. That was just the starting point. What came next was way more interesting. When you can run…

The Software Engineer Who Don't Code

Yasith Fernando

Staff Software Engineer

AI coding tools are rewriting what it means to build software, turning engineers into architects, reviewers, and orchestrators of AI-generated code rather than authors of every line. This talk explores the emerging reality where software engineers spend less time writing code and more time defining problems, evaluatin…

Your engineers aren't afraid of AI. They're afraid of becoming junior again.

Andy Kelk

Fractional CTO , Self Employed

When you roll out AI coding tools, you expect pushback about job security and workflow disruption. What you get instead is something harder to fix: senior engineers watching AI produce in seconds what used to take them years to master. This talk is about what's really driving quiet resistance in your team and what …

Edge AI with Direct Device Control

Jeremy Kelaher

AI Enablement Architect , SBS

Despite all the hype and promise, we are in the Timeshare Mainframe moment of AI. Even our devices rely on the cloud for most inference. As AI moves beyond the cloud and into the physical world, the real opportunity lies at the edge. It’s where local intelligence meets local data and action. In this talk, we explore h…

Engineering without reading code

Ben Taylor

Product Engineering Team Lead , Stile Education

In 2024 my team built 2 web-based Interactives for our Science Curriculum. In 2025 we built 50, in 2026 we expect to build over 100. In 2024 Engineers collaborated with Writers to build Interactives. In 2025 Writers built the Interactives and Engineers reviewed and deployed them. In 2026 we're getting Engineering out …

COBOL and AI: Building a Self-Serve Knowledge Layer for 2,000 Batch Jobs

Matthew Gillard

Principal , V2 AI

Modernization planning stalls when the business rules are locked inside decades of COBOL code. This talk shares a practical, production‑tested playbook I used to extract those rules, make them explainable, and serve them to teams in a usable form. It’s not economical to have humans extract this level of operational k…

The Death of Documentation

Josh Gillies

Senior Software Engineer , Prefactor

For decades, documentation has been the "sacred bridge" between human intent and machine execution. Historically, this was born of necessity: when computer time was scarce, we had to document our plans perfectly before touching a terminal. But in the modern era, documentation has morphed into a static snapshot—often s…

The Red Flags of Vibe Coding a Dating app

Karina Pamamull

AI Speaker, Trainer & Consultant , Self Employed

Move fast. Follow the vibe. Launch it. That works… until you’re building a dating app. Based on real world experiments building AI driven dating and community tools, this talk breaks down what actually happens when you rely on instinct and prompts to design for human connection. Think broken matching logic, conf…

Panel: Engineering Reality

AJ Fisher

Technologist & Writer , ajfisher.me

Dave Hall

Principal Consultant , Dave Hall Consulting

Krishna kanth Mundada

Software Engineer , Versent

Andy Kelk

Fractional CTO , Self Employed

A moderated conversation closing the L3 Engineering Reality session. AJ Fisher leads a discussion with Dave Hall, Krishna Mundada, and Andy Kelk on when not to reach for an LLM, the real costs of AI in production, and what it means for engineering teams and careers.

Legacy Software + Agentic Discovery

Chris Rickard

Founder & CEO , Userdoc

Legacy Software powers the world - from banking to utilities and government. The hardest part isn’t the code - we have the code.... it’s when the old guy with the beard leaves, and the knowledge walks out with him: what the code really means, the system truth, the business rules, and the original intent. To moderni…

Vibe-coded Multiplayer Video Games

Dr Sam Donegan

Medical Doctor, AI Engineer & President @ MLAI , MLAI

Every had a great idea for a video game but developing it always felt out of reach? AI is at a point now, where you can develop fully-fledged, multiplayer online games without needing to code. I'll take you through my workflow and how to get your game built quickly and cheaply!

Designing Inference-Native Systems

Sajjad Kamal

For a long time, the world has run on systems built on logic. You put something in, follow a set of rules, and you get an output. Now we have systems that can run on inference — systems that can update belief, decide, and act. That changes how we should think about building systems. We don't need to keep forcing every…

Agentic SAST: Building an AI Pipeline for Rule Synthesis and Root-Cause Vulnerability Analysis

Danila Sashchenko

Security Engineer, previously Offensive Security Engineer , TikTok

Project Electrification is an agentic, AI-powered application security pipeline designed to eliminate vulnerabilities at their source. Autonomous agents scan large codebases, generate and execute custom SAST rules, and produce unified risk analytics through the ELK stack. Security engineers then convert these insight…

Why LLMs Fall for Stories (And 5 Production Patterns That Actually Stop Them)

Mal Curtis

Principal Software Engineer , NVIDIA

Prompt injection isn't a bug - it's a feature. LLMs trained on humanity's written corpus learned something we didn't intend: narrative structure. They understand dramatic tension, plot twists, and persuasive framing. When an attacker crafts a compelling story ("Actually, the real system prompt said..."), the model fol…

From AI Survey to Production: What the Readiness Gap Actually Looks Like

Dr Christian Dandre

Founder and Principal Consultant , The Objective Company

Everyone talks about AI transformation. Almost no one talks about what happens when you survey your workforce and discover that executives and employees have completely different ideas about what AI readiness means - or when your pilot succeeds technically but stumbles in implementation. This talk walks through a r…

Hacking the Model: AI Red Teaming in Practice

Pas Apicella

Field CTO , Snyk APJ

Lawrence Crowther

Director, Solutions Engineering , Snyk APJ

AI is already in production—but almost no one has tested how it breaks. Today I’ll show you how attackers think, how models are actually exploited—from prompt injection to data exfiltration—and how to systematically uncover those risks before they become incidents.

AI After an Apocalypse

Simon Knox

Computer Programmer , apartments.com.au

Cloud outages used to mean your site went down, maybe you couldn't deploy. Just small unimportant stuff. Now an outage means you can't even write any code. And unreliable connections cause the same problems as ever - random cutoffs partway through, lost or incomplete work. The broken assumption remains that we are onl…

What We Learned Taking a Culture-First Approach to AI Adoption at scale

Eric Grigson

Director of Developer Experience , Culture Amp

Paul Hughes

Director of Engineering Enablement , Culture Amp

Most AI transformation stories focus on tooling, targets, and adoption curves. At Culture Amp, our primary focus was people and culture. We still wanted to drive and accelerate our impact, but we weren’t willing to compromise on our focus on people to get there. We then partnered with an engineering analytics firm to …

Stop vibing your agents to production: applying ML discipline to agent development

Justin Barias

Lead AI Engineer , Australian Government

When I joined my current team, it was a familiar pattern: 6-8 experiments over a year, each taking 10-12 weeks, 60-70% of the time burned on infrastructure, one thing in production held together with duct tape, and our entire agent lifecycle dependent on what our cloud provider made available in our region. The fix wa…

Why Most AI De-Identification Fails in Production, And How We Built One Lawyers Actually Trust

Moin Zaman

Co-founder , Smartnote

De-identifying text is easy to demo and surprisingly hard to ship. This talk is a deep technical case study of building SmartScrub, a reversible de-identification system designed for legal workflows, where privacy guarantees, auditability, and user trust are non-negotiable. The original goal was simple, allow lawy…

Fully Automated Luxury Gay Space Engineering

Daniel Rodgers-Pryor

Head of Stile AI Labs , Stile Education

Autocomplete is *so* 2023. Chatbots were already tedious by 2024. Running agents locally was cool... back in early 2025. The future of engineering doesn't have a human in the coding loop at all. When it's within the AI's — rapidly growing — capabilities, *you* are the bottleneck in shipping code. How many PRs ca…

Beat Burnout, Find Flourishing: The AI Edition

Navin Keswani

CPTO , TANK

AI tools are an amplifier. They don't just amplify productivity, they amplify whatever dynamics already exist in a team. Steve Yegge calls it the Dracula Effect: AI coding at full speed is vampiric, draining engineers faster than anyone expected. We've got to defend our teams against burnout and help them amplif…

Are Your AI Agents Secure? Defending the Privileged Agent

Daizen Ikehara

Principal Developer Advocate , Auth0

Are the AI agents you're developing truly secure? AI agents that execute actions autonomously offer unprecedented value. But what about the "privileges" granted to them to act "on behalf of the user"? Improper privilege management for agents is no longer a theoretical problem—it's a clear and present danger. An …

Your AI Can’t Engineer (Yet)

Theodoros Galanos

Generative AI Leader , Aurecon

Large language models excel at code—but engineering isn't just code. When you ask an AI to calculate short-circuit currents per IEC 60909 or size a pavement per Austroads 2022, you're asking it to operate outside its training distribution. The result: confident answers that miss unit conversions, ignore standard-speci…

12TB of AI coding agent logs - what works, what fails

Dave Slutzkin

CEO , Cadence

Three things matter for AI coding effectiveness: the tool, the codebase, the developer. When we look at the nuance of sessions, we can see patterns across all these - what works, what doesn't, what you can control, what you can't. I can't fix everything for you but I'll give you a few useful steps forward.

Panel: Culture & People

Andrew Murphy

CEO (Chief Everything Officer.) , Debugging Leadership

Dr Christian Dandre

Founder and Principal Consultant , The Objective Company

Eric Grigson

Director of Developer Experience , Culture Amp

Paul Hughes

Director of Engineering Enablement , Culture Amp

Navin Keswani

CPTO , TANK

A moderated conversation closing the L4 Culture & People session — and closing the Leadership track. Andrew Murphy leads a discussion with Dr Christian Dandre, Eric Grigson and Paul Hughes (Culture Amp), and Navin Keswani on readiness, adoption, and keeping people healthy through the change.

AI Agents Are Distributed Systems

Lovee Jain

Senior Software Engineer | Google Developer Expert | AWS Community Builder

AI agents aren’t magic. They’re distributed systems — with better marketing. Behind every impressive demo is a messy reality: multiple tools, remote services, auth boundaries, latency, retries, side effects, and deployment trade-offs. When I took a seemingly simple multi-tool agent built with MCP and Gemini ADK and…