Programme in development. This is the working programme for AI Engineer Sydney 2026. Announced speakers and presentations are confirmed for the conference, while track assignments, session groupings and times may change. Unfilled positions are marked “Talk to be confirmed”.

Monday December 7

08:00
social

Registration

Doors open at 8am. Collect your badge, grab a coffee and meet our exhibitors before the opening keynotes.

09:30
housekeeping

Welcome to AI Engineer Sydney

John Allsopp opens AI Engineer Sydney and sets the scene for two days of engineering, leadership and research.

09:35
Keynote

The AI Theory of Constraints

Shawn Wang
Editor & Founder, Latent.Space & Smol AI
09:55
Keynote

Prompts Rot. Keep the Source.

Drew Breunig
CEO and Co-founder, Cmpnd

AI agents learn what we want from our feedback, then compress that intent into prompts, skills and memories—and discard the evidence. The result is a collection of natural-language artefacts that decay as models change…

10:15
Keynote

The Harness Is the Agent

Mike Chambers
Senior DevEx Engineer, AWS

The model gets the headlines, but the harness is what turns a model into an agent. In late 2026 the harness is where the real engineering, and the real differentiation, lives. This keynote covers why the harness matters…

10:35
Keynote

The BAML Programming Language

Aaron Villalpando
Co-founder & CTO, Boundary

Whether you like it or not, it’s no longer possible to read all the code that’s generated by a model. The solution cannot be, "Just ship it," or you end up with slop everywhere. Neither can the solution be "Read…

10:55
Keynote

The Elephant and the Goldfish: Architecture Patterns for Cutting 70% of Agent Token Costs in Production

Tanya Dixit
Forward Deployed Engineer, Google

LLM providers sell you a 2-million-token context window like an elephant that never forgets. If you actually build production agents that way, your latency explodes, your retrieval drifts, and your CFO will shut you…

11:15
housekeeping

Hackathon finalists and audience vote

The hackathon finalists present their work, followed by details of the audience vote.

11:30

Lunch

12:30
Leadership

Lessons from Economics for the Human / Agent Software Workforce

Daniel Nadasi
Principal Engineer, Google

AI is reshaping software engineering, creating uncertainty about how engineering roles will change as increasingly capable systems take on work that was once performed by people. While no one can predict the future with…

12:30
AI Engineering

Ontologies: AI’s Operating Manual For Your Business

Gareth Williams
Principal Engineer, Wesfarmers

Tools churn. Factories commoditise. When everyone has the same models, the advantage goes to whoever gives their agents the clearest blueprint of how the business works - what exists, how it connects and the rules it…

12:30
Software Engineering

Shipping together in an AI native team

Sandra Arato
Fractional Applied AI Engineer

While building an AI agent for marketing workflows at Leonardo.Ai, we discovered that the traditional design-to-engineering handoff was failing. A static mock could describe a happy path, but not how an agent would…

12:30
Industry

Lessons from Amazon's AI Journey

Matt Taylor
Principal AI Specialist, AWS

Learn how AWS transformed for and with AI with lessons learn around strategy, operating model, data foundations, governance, measurement, and change management.

12:50
Software Engineering

Dependency hell is back. This time it's your agent's config.

Jack Rudenko
Chief AI Officer (CAIO), 10X Labs

Everyone has an agentic harness now. Ours is not special. What nobody has solved is running one across a whole team without every engineer drifting into a private setup.

We run Claude Code across 50 engineers and…

12:50
Industry

The CLI is dead, long live the CLI

Jan Peer Stöcklmair
Senior Software Engineer, Sentry

Coding agents didn't kill the CLI. They became its most demanding users: they can't see a spinner, stall on prompts they can't answer, and treat error messages as instructions.

So we rewrote Sentry's CLI from scratch…

12:50
AI Engineering

Your website is a terrible API: serving agents a different page at the edge

Jack Bear
CEO Founder, Norg AI

Every enterprise site we work on was built for a human with a browser. When an AI agent fetches the same URL it receives navigation, cookie banners, client-rendered components and marketing prose, then has to guess at…

13:00
Leadership

Sovereignty Is an Inference Problem

Leo Borges
Chief Engineer - GenAI, Commbank

AI sovereignty isn’t about where the GPUs sit. It’s about who can switch the intelligence off.

Australia is spending billions on sovereign AI infrastructure. But onshore compute running models subject to another…

13:10
AI Engineering

My Agents broke APIs - Fixing Multi-Agent Systems with MCP

Anannya Roy Chowdhury
GenAI Developer Advocate, AWS

Modern AI agents struggle not because of reasoning limits, but because of interaction with tools on interfaces designed for humans. In agentic systems, this mismatch leads to incorrect tool selection, redundant calls,…

13:10
Software Engineering

One harness for every coding agent: swap models and runtimes without rewriting

Ananya Roy
AI Architect, Databricks

You want your team using the best coding agent for each job : Claude Code, Codex, Cursor, or one you built yourself , without rewiring your setup every time a better model ships, and without each agent running loose…

13:10
Industry

Inside Dovetail's Secure Software Factory: risk-tiered code review when everyone ships

Doug Rathbone
VP of Engineering, Dovetail
Patrick Collins
CEO & Co-Founder, Dam Secure

At Dovetail, engineers, designers, product managers and even the CEO ship code. Weekly merged pull requests have tripled since January, and risk-tiered review has cut time spent waiting for review by 70%.

In this joint…

13:30
Software Engineering

Why software factories can't be trusted (and how the Systems Engineering V-model helps)

Mark Johnson
CEO, Cardiobase

Coding agents will do anything to get to a PR. Ours marked tasks complete that didn't exist, wrote "next steps: verification" under unreviewed pull requests, and quietly skipped every boring stage between the ticket and…

13:30
Leadership

Token usage is the new lines of code (and it's just as useless)

Fawaz Ahmad
Senior Engineering Director, Canva

Canva hit mid-2026 with every AI metric a vendor could hand us and no answer to the only question the business actually cared about: is this working? Adoption flattened at around 85% of ~3,000 engineers, and the number…

13:30
AI Engineering

We Deleted Most of Our Agents. Everything Got Faster

Khang Nguyen Hoang
Data Scientist, Hello Clever

The default advice is to add agents: specialised roles, an orchestrator, handoffs between them. We built that. It was a genuinely useful way to explore the problem space, and under real production traffic it was slow…

13:30
Industry

Applied Decision Models: A Closer Look at System One Models, and How and Where to Use Them

Felipe Ryan
Principal Solution Architect Dev and AI, Cloudflare

In this session, I'll look at so-called "System One" models: how they work at a high level, and the use cases they're best suited to.

I'll use two Cloudflare models as examples. The first is clef, an open-weight model…

13:50
AI Engineering

The Guess Never Becomes a Fact: Provenance-Governed, Model-Free Memory for LLMs

Asha Soman
AI Software Engineer, TensorPRO

Long context solves within-session coherence, not cross-session persistence. Once an assistant starts storing memories, a quieter failure appears: its own inferences can be written back, retrieved in later sessions, and…

13:50
Software Engineering

Don't stop, won't stop. Automated verification of long-running agentic loops

AJ Fisher
VP Digital Science, Tetratherix

Long-running agentic loops create different engineering problems than code generation. Once agents work unattended for many hours, iterate through 20 or more review cycles, and build stacked PRs towards a larger goal,…

13:50
Industry

Running AI Coding Agents at Scale: Adopting New Models, Controlling Cost, and Governing What Agents Do

Anthony Ivan
Staff AI Forward Deployed Engineer, Databricks

Running coding agents across a company comes down to three questions: which models to offer, how to control cost, and what agents should be allowed to do. This talk gives four recommendations on those questions, drawn…

14:00
Leadership conversation

In conversation

Daniel Nadasi
Principal Engineer, Google
Leo Borges
Chief Engineer - GenAI, Commbank
Fawaz Ahmad
Senior Engineering Director, Canva

The session’s three speakers join the MC for a conversation.

14:10
Software Engineering

It's time for a new kind of software

Rupert Manfredi
Head of Design, Telepath

Applications package a predetermined interface, data model and set of capabilities around somebody else’s idea of a task. Generative models can now produce software on demand, but generative UI today either sits atop…

14:10
AI Engineering

Less is More: Optimising Search for Agents

Ryan Ahern
Forward Deployed Engineer, Exa

Giving agents more search results doesn't necessarily make them better.

Ryan Ahern explains how Exa is rethinking search for agents, improving task success rates while reducing the cost of finding the information they…

14:10
Industry

The Machine That Changed the World, vAI

Andre Kolodochka
Solutions Engineer, Sonar

AI agents can write code faster than any team can review it. Code is abundant. Confidence is scarce. Join Andre to learn how leading enterprises are building agentic software factories they can trust. Learn about:

-…

14:30

Afternoon break

15:30
Software Engineering

Your spaghetti code has an invoice now: what complexity does to coding agents

Artem Yakimenko
Engineering Director, Site Reliability, Culture Amp

We've told engineers for decades that high complexity makes code harder for humans to reason about. It turns out it makes code measurably more expensive for agents too. Unlike human frustration, this shows up directly…

15:30
Leadership

The Model Wasn't the MOAT: How 10 Design System Engineers Turned Platform Knowledge into Enterprise AI

Sudharsanam Narasimhan
Senior engineering manager, Design Systems & AI Developer Platforms, Atlassian

Most enterprise AI strategies begin with models, central AI teams, and a list of potential use cases. We started somewhere else: with a platform organisation that already shaped how more than 2,000 frontend engineers…

15:30
AI Engineering

Tools Before Autonomy: What 200,000 Tool Calls Taught Us About Agentic Evals

Dean Soste
Senior Machine Learning Engineer, Canva

Production AI problems are rarely observable through deterministic CI checks. They surface as user feedback, bad LLM-as-a-Judge scores, alerts, or even a vague sense that something is wrong. The evidence that explains…

15:30
Industry

MCP Isn't Enough: Why Agents Needed an Event Loop, Not Just an API

Saul Caganoff
Managing Director, Engineering, Deloitte Australia

Many apps are adding MCP interfaces so agents can query their systems of record. It works, until the workflows we actually care about turn out to be "something happened, now respond", and polling wastes network, context…

15:50
Software Engineering

Your Coding Agent Is Fast. Your Codebase Is the Bottleneck.

Shrey Somaiya
Principal Engineer - Jira Frontend Platform, Atlassian

AI agents can write code faster than teams can land it. Jira’s frontend codebase contains over 15 million lines of code, supports thousands of contributors, and doubles in size roughly every two years.

At this scale,…

15:50
AI Engineering

How to Change an LLM System Without Guessing

Yulia Kuchina
Staff AI Engineer, Software at Scale

We were running a production LLM pipeline that classified legal documents, and every change was a guess. Swap a prompt, change a model — better or worse? Nobody could say. The outputs looked plausible either way, and…

15:50
Industry

An AI-Assisted Brand Uplift at Scale

Guilherme Epifanio
Software Engineer, Design System, Easygo
Sam Annand
Tech Lead, Easygo

What if designers could build directly in the codebase? We used AI-assisted workflows to let designers prototype in production code with live preview links, while engineers focused on feasibility and scale. The result:…

16:00
Leadership

From REST to Agentic: Trusted APIs in the age of AI

Leigh Whiting
Principal Engineer, Atlassian

Enterprise platforms don't get to start from scratch. When AI agents need to act on behalf of users, they inherit the API surfaces those users already depend on — surfaces evolved over many years for human-driven…

16:10
Software Engineering

AI Janitor: Making Architecture Review Executable for Coding Agents

Dave Currie
AI Engineer, Square Peg

AI coding agents accelerate code generation, but they also accelerate architectural drift, regressions and false confidence. While building a multi-service production platform with only two of us, I found that a normal…

16:10
AI Engineering

From vibes to a systematic eval flywheel: evals for high stakes AI agents

Donna Zhou
Software engineer, Lorikeet
Rok Stular
Software Engineer, Lorikeet

If you are sceptical about how evals drive real results, or looking for more depth than introductory tutorial videos, this talk is for you.

We'll show you how Lorikeet, an AI customer service startup, built an eval…

16:10
Industry

Ship AI Agents Faster, from Prototype to Production

Sean Spires
Senior Solutions Engineer, Auth0

As AI agents take on more autonomous roles, the identity and access patterns built for humans and APIs no longer hold. This session draws on Auth0’s real-world experience securing agentic workflows where misconfigured…

16:30
Software Engineering

209 ports in six days, in a language the model barely knew

Burin Choomnuan
Principal Engineer/Team Lead/AI Engineer, NewsCorp Australia

Jolt and jank are two young Clojure implementations, one running on Chez Scheme and one compiling to native code through C++/LLVM. Between them they have almost no public code for a model to have learned from. Ask…

16:30
AI Engineering

Where Should the Dice Roll? Placing Non-Determinism Deliberately in Enterprise AI

Vighnesh Deshpande
AI Engineer, Vivanti Consulting

Most production AI guidance assumes you want consistency: pin the prompt, lower the temperature, eval for drift. But a whole class of enterprise use cases - idea generation, recommendation, exploration, synthesis - is…

16:30
Leadership

Does This Agent Make My Context Look Big? Right-Sizing AI Architectures for Production

Hamish Songsmith
Head of Applied AI, Silicon Quantum Computing

One agent that does everything is powerful, until it’s impossible to debug, eval or secure. Break it into a graph of specialised agents and you get control, until it doesn't for a multitude of reasons.

Neither…

16:30
Industry

Talk to be confirmed

This programme position is being held for an Industry presentation to be announced.

16:50
Software Engineering

Compounding lessons into skills: How we performed a large code migration using AI (with no new bugs!)

Tom Isles
Staff Software Engineer, Canva

Canva's "Ingredient Generation" service powers all of our media generation experiences. Every image, video, audio and 3d object request for generation goes through this service, which offers 50+ AI Models. One of its…

16:50
AI Engineering

Define Good, Then Ship: Blind Evals for Agentic Features

Yasith Fernando
Principal Engineer, Cuttable

In May I rebuilt our brand-strategy pipeline as a fully agentic system, replacing a chain of LLM calls with a managed agent. I compared old and new across 44 customers, and the new system won every time. But I was the…

16:50
Industry

Talk to be confirmed

This programme position is being held for an Industry presentation to be announced.

17:00
Leadership conversation

In conversation

Sudharsanam Narasimhan
Senior engineering manager, Design Systems & AI Developer Platforms, Atlassian
Leigh Whiting
Principal Engineer, Atlassian
Hamish Songsmith
Head of Applied AI, Silicon Quantum Computing

The session’s three speakers join the MC for a conversation.

17:10
Software Engineering

Your Test Strategy Assumes Humans Write Code

Lee Simpson
Engineering Partner, Deloitte Australia
Ethan McDonnell
Senior Software Engineer, Deloitte Australia

Thirteen months building a custom state government full-stack application with zero code written by hand.

7,137 tests, 5,631 of them unit tests. It was a textbook testing pyramid but still bugs stacked up.

The…

17:10
AI Engineering

The agents went rogue at 2%

James Peter
Co-Founder, JustEvery

Giving an agent a skill sounds straightforward: it loads a Markdown file, follows the instructions and completes the task.

Ours launched a long-running, paid process and told the agent to wait for the result. But…

17:10
Industry

Talk to be confirmed

This programme position is being held for an Industry presentation to be announced.

17:30
social

Reception

At the close of day one, join fellow attendees and speakers for drinks, conversation and the chance to continue the day’s discussions.

19:30
social

Speaker dinner

Leadership ticket holders join the speakers for dinner after the reception. Final venue details will be shared with guests.

08:00
social

Registration

Doors open at 8am. Collect your badge, grab a coffee and meet our exhibitors before the opening keynotes.

09:30
housekeeping

Welcome to AI Engineer Sydney

John Allsopp opens AI Engineer Sydney and sets the scene for two days of engineering, leadership and research.

09:35
Keynote

The AI Theory of Constraints

Shawn Wang
Editor & Founder, Latent.Space & Smol AI
09:55
Keynote

Prompts Rot. Keep the Source.

Drew Breunig
CEO and Co-founder, Cmpnd

AI agents learn what we want from our feedback, then compress that intent into prompts, skills and memories—and discard the evidence. The result is a collection of natural-language artefacts that decay as models change…

10:15
Keynote

The Harness Is the Agent

Mike Chambers
Senior DevEx Engineer, AWS

The model gets the headlines, but the harness is what turns a model into an agent. In late 2026 the harness is where the real engineering, and the real differentiation, lives. This keynote covers why the harness matters…

10:35
Keynote

The BAML Programming Language

Aaron Villalpando
Co-founder & CTO, Boundary

Whether you like it or not, it’s no longer possible to read all the code that’s generated by a model. The solution cannot be, "Just ship it," or you end up with slop everywhere. Neither can the solution be "Read…

10:55
Keynote

The Elephant and the Goldfish: Architecture Patterns for Cutting 70% of Agent Token Costs in Production

Tanya Dixit
Forward Deployed Engineer, Google

LLM providers sell you a 2-million-token context window like an elephant that never forgets. If you actually build production agents that way, your latency explodes, your retrieval drifts, and your CFO will shut you…

11:15
housekeeping

Hackathon finalists and audience vote

The hackathon finalists present their work, followed by details of the audience vote.

11:30

Lunch

12:30
Leadership

Lessons from Economics for the Human / Agent Software Workforce

Daniel Nadasi
Principal Engineer, Google

AI is reshaping software engineering, creating uncertainty about how engineering roles will change as increasingly capable systems take on work that was once performed by people. While no one can predict the future with…

AI Engineering

Ontologies: AI’s Operating Manual For Your Business

Gareth Williams
Principal Engineer, Wesfarmers

Tools churn. Factories commoditise. When everyone has the same models, the advantage goes to whoever gives their agents the clearest blueprint of how the business works - what exists, how it connects and the rules it…

Software Engineering

Shipping together in an AI native team

Sandra Arato
Fractional Applied AI Engineer

While building an AI agent for marketing workflows at Leonardo.Ai, we discovered that the traditional design-to-engineering handoff was failing. A static mock could describe a happy path, but not how an agent would…

Industry

Lessons from Amazon's AI Journey

Matt Taylor
Principal AI Specialist, AWS

Learn how AWS transformed for and with AI with lessons learn around strategy, operating model, data foundations, governance, measurement, and change management.

12:50
AI Engineering

Your website is a terrible API: serving agents a different page at the edge

Jack Bear
CEO Founder, Norg AI

Every enterprise site we work on was built for a human with a browser. When an AI agent fetches the same URL it receives navigation, cookie banners, client-rendered components and marketing prose, then has to guess at…

Software Engineering

Dependency hell is back. This time it's your agent's config.

Jack Rudenko
Chief AI Officer (CAIO), 10X Labs

Everyone has an agentic harness now. Ours is not special. What nobody has solved is running one across a whole team without every engineer drifting into a private setup.

We run Claude Code across 50 engineers and…

Industry

The CLI is dead, long live the CLI

Jan Peer Stöcklmair
Senior Software Engineer, Sentry

Coding agents didn't kill the CLI. They became its most demanding users: they can't see a spinner, stall on prompts they can't answer, and treat error messages as instructions.

So we rewrote Sentry's CLI from scratch…

13:00
Leadership

Sovereignty Is an Inference Problem

Leo Borges
Chief Engineer - GenAI, Commbank

AI sovereignty isn’t about where the GPUs sit. It’s about who can switch the intelligence off.

Australia is spending billions on sovereign AI infrastructure. But onshore compute running models subject to another…

13:10
AI Engineering

My Agents broke APIs - Fixing Multi-Agent Systems with MCP

Anannya Roy Chowdhury
GenAI Developer Advocate, AWS

Modern AI agents struggle not because of reasoning limits, but because of interaction with tools on interfaces designed for humans. In agentic systems, this mismatch leads to incorrect tool selection, redundant calls,…

Software Engineering

One harness for every coding agent: swap models and runtimes without rewriting

Ananya Roy
AI Architect, Databricks

You want your team using the best coding agent for each job : Claude Code, Codex, Cursor, or one you built yourself , without rewiring your setup every time a better model ships, and without each agent running loose…

Industry

Inside Dovetail's Secure Software Factory: risk-tiered code review when everyone ships

Doug Rathbone
VP of Engineering, Dovetail
Patrick Collins
CEO & Co-Founder, Dam Secure

At Dovetail, engineers, designers, product managers and even the CEO ship code. Weekly merged pull requests have tripled since January, and risk-tiered review has cut time spent waiting for review by 70%.

In this joint…

13:30
Leadership

Token usage is the new lines of code (and it's just as useless)

Fawaz Ahmad
Senior Engineering Director, Canva

Canva hit mid-2026 with every AI metric a vendor could hand us and no answer to the only question the business actually cared about: is this working? Adoption flattened at around 85% of ~3,000 engineers, and the number…

AI Engineering

We Deleted Most of Our Agents. Everything Got Faster

Khang Nguyen Hoang
Data Scientist, Hello Clever

The default advice is to add agents: specialised roles, an orchestrator, handoffs between them. We built that. It was a genuinely useful way to explore the problem space, and under real production traffic it was slow…

Software Engineering

Why software factories can't be trusted (and how the Systems Engineering V-model helps)

Mark Johnson
CEO, Cardiobase

Coding agents will do anything to get to a PR. Ours marked tasks complete that didn't exist, wrote "next steps: verification" under unreviewed pull requests, and quietly skipped every boring stage between the ticket and…

Industry

Applied Decision Models: A Closer Look at System One Models, and How and Where to Use Them

Felipe Ryan
Principal Solution Architect Dev and AI, Cloudflare

In this session, I'll look at so-called "System One" models: how they work at a high level, and the use cases they're best suited to.

I'll use two Cloudflare models as examples. The first is clef, an open-weight model…

13:50
AI Engineering

The Guess Never Becomes a Fact: Provenance-Governed, Model-Free Memory for LLMs

Asha Soman
AI Software Engineer, TensorPRO

Long context solves within-session coherence, not cross-session persistence. Once an assistant starts storing memories, a quieter failure appears: its own inferences can be written back, retrieved in later sessions, and…

Software Engineering

Don't stop, won't stop. Automated verification of long-running agentic loops

AJ Fisher
VP Digital Science, Tetratherix

Long-running agentic loops create different engineering problems than code generation. Once agents work unattended for many hours, iterate through 20 or more review cycles, and build stacked PRs towards a larger goal,…

Industry

Running AI Coding Agents at Scale: Adopting New Models, Controlling Cost, and Governing What Agents Do

Anthony Ivan
Staff AI Forward Deployed Engineer, Databricks

Running coding agents across a company comes down to three questions: which models to offer, how to control cost, and what agents should be allowed to do. This talk gives four recommendations on those questions, drawn…

14:00
Leadership conversation

In conversation

Daniel Nadasi
Principal Engineer, Google
Leo Borges
Chief Engineer - GenAI, Commbank
Fawaz Ahmad
Senior Engineering Director, Canva

The session’s three speakers join the MC for a conversation.

14:10
AI Engineering

Less is More: Optimising Search for Agents

Ryan Ahern
Forward Deployed Engineer, Exa

Giving agents more search results doesn't necessarily make them better.

Ryan Ahern explains how Exa is rethinking search for agents, improving task success rates while reducing the cost of finding the information they…

Software Engineering

It's time for a new kind of software

Rupert Manfredi
Head of Design, Telepath

Applications package a predetermined interface, data model and set of capabilities around somebody else’s idea of a task. Generative models can now produce software on demand, but generative UI today either sits atop…

Industry

The Machine That Changed the World, vAI

Andre Kolodochka
Solutions Engineer, Sonar

AI agents can write code faster than any team can review it. Code is abundant. Confidence is scarce. Join Andre to learn how leading enterprises are building agentic software factories they can trust. Learn about:

-…

14:30

Afternoon break

15:30
Leadership

The Model Wasn't the MOAT: How 10 Design System Engineers Turned Platform Knowledge into Enterprise AI

Sudharsanam Narasimhan
Senior engineering manager, Design Systems & AI Developer Platforms, Atlassian

Most enterprise AI strategies begin with models, central AI teams, and a list of potential use cases. We started somewhere else: with a platform organisation that already shaped how more than 2,000 frontend engineers…

AI Engineering

Tools Before Autonomy: What 200,000 Tool Calls Taught Us About Agentic Evals

Dean Soste
Senior Machine Learning Engineer, Canva

Production AI problems are rarely observable through deterministic CI checks. They surface as user feedback, bad LLM-as-a-Judge scores, alerts, or even a vague sense that something is wrong. The evidence that explains…

Software Engineering

Your spaghetti code has an invoice now: what complexity does to coding agents

Artem Yakimenko
Engineering Director, Site Reliability, Culture Amp

We've told engineers for decades that high complexity makes code harder for humans to reason about. It turns out it makes code measurably more expensive for agents too. Unlike human frustration, this shows up directly…

Industry

MCP Isn't Enough: Why Agents Needed an Event Loop, Not Just an API

Saul Caganoff
Managing Director, Engineering, Deloitte Australia

Many apps are adding MCP interfaces so agents can query their systems of record. It works, until the workflows we actually care about turn out to be "something happened, now respond", and polling wastes network, context…

15:50
AI Engineering

How to Change an LLM System Without Guessing

Yulia Kuchina
Staff AI Engineer, Software at Scale

We were running a production LLM pipeline that classified legal documents, and every change was a guess. Swap a prompt, change a model — better or worse? Nobody could say. The outputs looked plausible either way, and…

Software Engineering

Your Coding Agent Is Fast. Your Codebase Is the Bottleneck.

Shrey Somaiya
Principal Engineer - Jira Frontend Platform, Atlassian

AI agents can write code faster than teams can land it. Jira’s frontend codebase contains over 15 million lines of code, supports thousands of contributors, and doubles in size roughly every two years.

At this scale,…

Industry

An AI-Assisted Brand Uplift at Scale

Guilherme Epifanio
Software Engineer, Design System, Easygo
Sam Annand
Tech Lead, Easygo

What if designers could build directly in the codebase? We used AI-assisted workflows to let designers prototype in production code with live preview links, while engineers focused on feasibility and scale. The result:…

16:00
Leadership

From REST to Agentic: Trusted APIs in the age of AI

Leigh Whiting
Principal Engineer, Atlassian

Enterprise platforms don't get to start from scratch. When AI agents need to act on behalf of users, they inherit the API surfaces those users already depend on — surfaces evolved over many years for human-driven…

16:10
AI Engineering

From vibes to a systematic eval flywheel: evals for high stakes AI agents

Donna Zhou
Software engineer, Lorikeet
Rok Stular
Software Engineer, Lorikeet

If you are sceptical about how evals drive real results, or looking for more depth than introductory tutorial videos, this talk is for you.

We'll show you how Lorikeet, an AI customer service startup, built an eval…

Software Engineering

AI Janitor: Making Architecture Review Executable for Coding Agents

Dave Currie
AI Engineer, Square Peg

AI coding agents accelerate code generation, but they also accelerate architectural drift, regressions and false confidence. While building a multi-service production platform with only two of us, I found that a normal…

Industry

Ship AI Agents Faster, from Prototype to Production

Sean Spires
Senior Solutions Engineer, Auth0

As AI agents take on more autonomous roles, the identity and access patterns built for humans and APIs no longer hold. This session draws on Auth0’s real-world experience securing agentic workflows where misconfigured…

16:30
Leadership

Does This Agent Make My Context Look Big? Right-Sizing AI Architectures for Production

Hamish Songsmith
Head of Applied AI, Silicon Quantum Computing

One agent that does everything is powerful, until it’s impossible to debug, eval or secure. Break it into a graph of specialised agents and you get control, until it doesn't for a multitude of reasons.

Neither…

AI Engineering

Where Should the Dice Roll? Placing Non-Determinism Deliberately in Enterprise AI

Vighnesh Deshpande
AI Engineer, Vivanti Consulting

Most production AI guidance assumes you want consistency: pin the prompt, lower the temperature, eval for drift. But a whole class of enterprise use cases - idea generation, recommendation, exploration, synthesis - is…

Software Engineering

209 ports in six days, in a language the model barely knew

Burin Choomnuan
Principal Engineer/Team Lead/AI Engineer, NewsCorp Australia

Jolt and jank are two young Clojure implementations, one running on Chez Scheme and one compiling to native code through C++/LLVM. Between them they have almost no public code for a model to have learned from. Ask…

Industry

Talk to be confirmed

This programme position is being held for an Industry presentation to be announced.

16:50
AI Engineering

Define Good, Then Ship: Blind Evals for Agentic Features

Yasith Fernando
Principal Engineer, Cuttable

In May I rebuilt our brand-strategy pipeline as a fully agentic system, replacing a chain of LLM calls with a managed agent. I compared old and new across 44 customers, and the new system won every time. But I was the…

Software Engineering

Compounding lessons into skills: How we performed a large code migration using AI (with no new bugs!)

Tom Isles
Staff Software Engineer, Canva

Canva's "Ingredient Generation" service powers all of our media generation experiences. Every image, video, audio and 3d object request for generation goes through this service, which offers 50+ AI Models. One of its…

Industry

Talk to be confirmed

This programme position is being held for an Industry presentation to be announced.

17:00
Leadership conversation

In conversation

Sudharsanam Narasimhan
Senior engineering manager, Design Systems & AI Developer Platforms, Atlassian
Leigh Whiting
Principal Engineer, Atlassian
Hamish Songsmith
Head of Applied AI, Silicon Quantum Computing

The session’s three speakers join the MC for a conversation.

17:10
AI Engineering

The agents went rogue at 2%

James Peter
Co-Founder, JustEvery

Giving an agent a skill sounds straightforward: it loads a Markdown file, follows the instructions and completes the task.

Ours launched a long-running, paid process and told the agent to wait for the result. But…

Software Engineering

Your Test Strategy Assumes Humans Write Code

Lee Simpson
Engineering Partner, Deloitte Australia
Ethan McDonnell
Senior Software Engineer, Deloitte Australia

Thirteen months building a custom state government full-stack application with zero code written by hand.

7,137 tests, 5,631 of them unit tests. It was a textbook testing pyramid but still bugs stacked up.

The…

Industry

Talk to be confirmed

This programme position is being held for an Industry presentation to be announced.

17:30
social

Reception

At the close of day one, join fellow attendees and speakers for drinks, conversation and the chance to continue the day’s discussions.

19:30
social

Speaker dinner

Leadership ticket holders join the speakers for dinner after the reception. Final venue details will be shared with guests.

Tuesday December 8

07:30
Leadership breakfast

Leadership Breakfast with Notion: The Lonely Builder — Thinking Together in the Age of AI

JW Selvaraj
Forward Deployed Engineering Lead, APAC, Notion

A breakfast for engineering and technology leaders, hosted by Notion. Places are limited: join the waitlist to attend.

As coding agents become everyday collaborators, engineers can move faster, but may find themselves…

09:00
housekeeping

Welcome to day two

John Allsopp opens the second day of AI Engineer Sydney.

09:05
Keynote

Keynote speaker to be announced

This keynote position is being held while one further speaker is finalised.

09:25
Keynote

The State of Open Source AI

Raffi Krikorian
Chief Technology Officer, Mozilla

Raffi Krikorian, Chief Technology Officer at Mozilla, explores the state of open-source AI, with a preview of Mozilla’s next State of Open Source AI report.

09:45
Keynote

Who Keeps It Open?

Manik Surtani
CTO and co-founder, Agentic AI Foundation

Every generational shift in computing produces plumbing that everyone depends on. TCP/IP, HTTP, the container runtime. And every time, there is a window where someone can quietly come to own it, and everyone else pays…

10:05
Keynote

Keynote speaker to be announced

One further editorial keynote will be announced for this position.

10:25
Keynote

The AI year: how we work, hire and grow now

Fiona Chan
Partner & Technical Recruiter, Lookahead

For a lot of teams, this was the year AI stopped being an experiment and started being part of the job. Shipping got faster, but so did the pace, the pressure and the pile of code waiting for review.

Drawing on…

10:45
housekeeping

Hackathon winner and closing

We announce the hackathon winner and close the keynote programme before the day’s tracks begin.

11:00

Lunch

12:00
AI Engineering

Oops I Hacked It Again: Six Months of Red Teaming Our AI Agents

Jon Shen
AI Practice Executive - Strategy and Governance, Suncorp

In March I onboarded our first team member dedicated to AI Red Teaming. That was a month before the announcement of Claude Mythos Preview, and the open letters that followed from APRA in April and ASIC in May…

12:00
Leadership

How we introduced LLMs into credit decisioning

Kevin Nguyen
Senior Product Engineer, Skip

Over the past nine months we've built and deployed an AI-assisted credit assessment system that's now used in production to help credit assessors process home loan applications. More importantly, it was signed off by…

12:00
Research / Deep Tech

The Benchmark Ends. The World Doesn’t: Building Persistent Engineering Environments for Continual Learning

Theodoros Galanos
FDE @ APAC, Nomic

Large language models can complete sequences of tasks—but continual learning is not just doing more tasks. Most agent environments reset after every episode: state disappears, required follow-up vanishes, delayed…

12:00
Software Engineering

The Contradictions of Building AI Products and Teams

Sherif Mansour
Distinguished Product Manager and Head of AI, Atlassian

For every claim about how to build with AI, there seems to be an equal and opposite claim that’s also true. Chat is the universal interface, so go headless. Never bolt AI onto your product, reimagine it. Everyone on…

12:20
AI Engineering

Deliberate Holes Only

Karla Burnett
Security Engineer, Lorikeet

Making an AI agent vulnerable to exactly one attack is harder than making it completely secure, let alone doing it six different times.

In this talk, I'll describe the process of building an agentic AI capture the…

12:20
Research / Deep Tech

Extracting Tacit Knowledge for Production Agents

Khali Kalpa-Young
Founder, Alchymie

An eval is a definition of "good" written down well enough for a machine to grade against. In a real business, "good" isn't written down anywhere. It lives in someone's reaction, in what past work actually did, and in…

12:20
Software Engineering

Sovereign AI Across the Stack: From Infrastructure to Inference

Daniel Apps
Head of Solutions, ResetData

Building sovereign AI takes more than Australian-hosted infrastructure. It requires control across the entire AI stack, from GPU compute and model deployment to inference, APIs and the platform connecting it all.…

12:30
Leadership

Building AI for students who can't tell you when it's wrong

Ez Herrmann
Technical Solution Architect, Sitback Solutions

Teachers in Australian specialist schools spend two hours or more preparing a single lesson, then adapt it again for every ability group in the room. Many are already pasting student details into consumer chatbots to…

12:40
AI Engineering

Query before mutation: guardrail patterns for agents that touch production infrastructure

Jeffrey Aven
Maintainer, StackQL Studios

Giving an AI agent permission to change production infrastructure removes the human pause that made plan-and-apply safe. In this talk, Jeffrey Aven shows how to put that judgement back into the system itself.

He…

12:40
Research / Deep Tech

Adaptive Learning: Encoding Clinician Edits as Memory

Vlad Gavrilov
Senior AI Engineer, Heidi

Clinicians edit their AI-generated notes for many reasons: adding or removing content, fixing spelling, and preferences for structure, wording, or terminology. Some of these edits are contextual, applying in some…

12:40
Software Engineering

We Replaced Our AI Framework in Two Weeks

John Law
Principal Engineer, Accesso

Our main product is a conversational agent that helps users explore and analyse their data. As LLM providers released capabilities such as finer-grained cache checkpoints and tool search, the framework underneath our…

13:00
Research / Deep Tech

Building Agentic Memory for an AI SOC: Why Our Semantic Cache Was the Wrong Answer

Mukesh Singh
Principal Detection and Response Engineer, Atlassian

We run a fleet of AI agents against production security detections at Atlassian. One tunes noisy detection rules, another reviews new ones, and more are coming for alert triage and hunting. Every one of them started…

13:00
Leadership

Regulated Doesn't Mean On Rails: what compliance actually asks of your engineers

Stephen Sennett
Principal Forward-Deployed Engineer - Applied AI, V2 AI

We spent three months rebuilding a regulated enterprise's development lifecycle around agents, then worked out how much of the governance we had added was doing real compliance work. Less than we assumed.

Across…

13:00
AI Engineering

AI Sandboxes: Running Coding Agents Safely in Production-Grade Environments

Shivay Lamba
Lead Machine Learning | Developer Experience Engineer, Qualcomm

The number of cyber attacks and security risks related to Coding Agents has sky rocketed. AI coding agents like Claude Code, Codex CLI, and Gemini CLI don’t behave like your typical developer tools. They install system…

13:00
Software Engineering

Dark Software Factory: Why We Build Differently

Igor Costa
CEO, Autohand AI

What happens when traditional software development approaches can no longer solve the problems we face? In this session, we explore the challenges, gaps, and limitations that remain unsolved, why conventional approaches…

13:20
Research / Deep Tech

From Documents to Defensible Evidence: Rethinking RAG for Audits

Sharat Madanapalli
Founder, InTune AI

Audits impose strict requirements for evidence, traceability and expert judgement. Each entity being audited supplies a new body of evidence, made up of manuals, records, tables, diagrams, scans and multilingual…

13:20
AI Engineering

Beyond System Prompts: Securing AI Agents with Fine-Grained Authorization

Daizen Ikehara
Principal Developer Advocate, Auth0

To make an AI agent useful, we often give it broad access to APIs and data. As systems move from simple retrieval to autonomous action, system-prompt instructions are not an adequate security boundary.

This…

13:20
Software Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

13:30
Leadership conversation

In conversation

Kevin Nguyen
Senior Product Engineer, Skip
Ez Herrmann
Technical Solution Architect, Sitback Solutions
Stephen Sennett
Principal Forward-Deployed Engineer - Applied AI, V2 AI

The session’s three speakers join the MC for a conversation.

13:40
AI Engineering

Building a Security Agent: Model choice, Harnesses and Evals

Simon Harloff
CTO, Dam Secure

In this presentation, I’ll show how we set out to give developers useful security feedback on every pull request in under three minutes. The benchmark results and methodology are published here:…

13:40
Research / Deep Tech

Classifiers are dead. Long live classifiers!

Charli Posner
Builder, Stile Education

Training a classifier used to mean collecting labelled data, choosing an architecture, training a model, evaluating it, and deploying it. Today, for a surprising number of problems, you can replace most of that with a…

13:40
Software Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

14:00

Afternoon break

15:00
AI Engineering

Running 100K+ Concurrent Agents: It's Never the Prompt

Harry Nguyen
AI engineer, insightfactory.ai

Your Agents Aren't Failing at Prompting

Every agent demo works. Then you run ten thousand at once, and the failures have nothing to do with the model: dead tuples piling up, a sync HTTP client freezing the event…

15:00
Software Engineering

Trust is engineered, not granted: why we focus on verifying before background coding agents

Vivek Katial
Engineering Lead, Applied AI, Heidi Health
Belen Garcia Fava
Head of Engineering, Heidi Health

Heidi is an AI scribe used by 130K clinicians a week. Our 150 engineers ship 100+ PRs daily into prod, and AI made writing code so cheap that review became the bottleneck: our P75 review wait was 14 hours, almost all of…

15:00
Leadership

Management Is Dead, Leadership Is Not

Inga Pflaumer
Consulting CTO

Engineering teams are getting smaller. A team of four with strong AI tooling now ships what took twelve people two years ago, and the org chart has not caught up. The first layer to feel it is middle management - the…

15:00
Research / Deep Tech

Skippy: The Little Inference Engine That CUDA

James Dumay
Founder, Stealth AI Startup
Daniel Winter-Wijntjes
Co-CEO and Founder, Stealth AI Startup

What happens under the hood when you run a large language model? This talk explores Skippy, a custom inference engine built for Mesh on top of llama.cpp, and the engineering behind local and distributed AI inference.…

15:20
Software Engineering

From Prompt Rules to Structural Guarantees: The Harness Behind a Production Analytics Agent

Jiggy Kakkad
Staff AI Engineer, Quantium
Tinus Willemse
Executive Manager, AI & Data Science, Quantium

Checkout AI answers open-ended questions about retail sales data in natural language. It plans,
calls analytics tools over MCP, executes Python in a sandbox, and returns a written analysis with
charts. In a system…

15:20
AI Engineering

Don't Fight Hallucinations. Make Them Impossible

Nadia Makarevich
Principal Engineer, Heatseeker

The Heatseeker AI chat answers data questions for marketers who make decisions with million-dollar budgets. Wrong answers or hallucinated numbers are not an option here, as you can imagine ;)

The fight against them…

15:20
Research / Deep Tech

Local AI and the End of the Cloud Default

Lukas Wesemann
Co-founder, CEO, Base Compute

Most AI today runs in the cloud, where every token costs money and every input leaves your device. Now AI agents are running around the clock with access to your email, files, and most sensitive data. That burns through…

15:30
Leadership

Half our handoffs are the bot's idea

Adeline Yaw
AI Integration Specialist, Automattic

About one in four conversations with WordPress.com's AI support bot ends with a person. In about half of those, the bot suggested it.

These are two different problems. In one, the user asks for a person. In the…

15:40
AI Engineering

Give Every Agent a Flight Recorder

Rahul Trikha
Principal AI Engineer, Zendesk

Agent teams should not need to file a ticket with a central evaluation team just to learn whether a new prompt, model, or tool made their agent better. At Zendesk, we developed and deployed a trace-first evaluation…

15:40
Software Engineering

Safely releasing AI applications while continuously patching vulnerabilities

Jay Yuan
Staff Software Engineer, Commonwealth Bank of Australia

AI applications still need regular security patches and dependency updates, but those software changes can also affect the data processing, model interaction, and evaluation paths around an LLM. In our releases,…

15:40
Research / Deep Tech

Robot Kintsugi: The Art and Design of Reengineering Old Hardware

Martin Kemka
engineer and designer

What does it take to give an old robot new life with AI?

This talk explores the art and design of reengineering abandoned hardware, treating its physical constraints and original character as starting points for new…

16:00
AI Engineering

Office-Brain and the Night Shift: What Happens When You Turn Off the Meter

Mark Pesce
Co-Founder, Noops

"Good enough" AI now runs on a reasonably beefy laptop. Qwen3.8-27B benchmarks at an Intelligence Index of 52 - roughly the best money could buy back in February - and inferences happily on consumer kit. When tokens are…

16:00
Software Engineering

Should You Build a Software Factory? Tales from an Open-Source Maintainer

Harlan Wilton
Open-source developer, Self Employed

Coding agents helped me write code faster, but I kept running into problems elsewhere in my engineering workflow. Tests passed without proving much. Parallel tasks changed the same files. Reviews piled up. This talk…

16:00
Leadership

The five stages of losing our craft

Andrew Murphy
CEO, Prudixa

Your best engineer won't use AI tools. Your tech lead is using them but won't tell anyone. Your new grads don't understand what the fuss is about. And you, the leader, are supposed to have answers for all of them.…

16:00
Research / Deep Tech

How to Count to One Hundred

Hugo O'Connor
R&D Engineer, Anuna Research

Agents don't work well together in chat rooms: put a few in a channel and they talk past each other. Natural language and unrestricted JSON feed an open-ended pipeline of reasoning and tool calls with full Turing power.…

16:20
Software Engineering

Autonomous agents need autonomous protection

Adesh Gairola
Founder and CEO, raxIT Labs

Autonomous agents need autonomous protection. An agent that acts alone at 3am cannot wait for a quarterly pen test, a consultant's report, or a security engineer the team does not have. We started with the data. We…

16:20
AI Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

16:20
Research / Deep Tech

Talk to be confirmed

This programme position is being held for a Research / Deep Tech presentation to be announced.

16:30
Leadership conversation

In conversation

Inga Pflaumer
Consulting CTO
Adeline Yaw
AI Integration Specialist, Automattic
Andrew Murphy
CEO, Prudixa

The session’s three speakers join the MC for a conversation.

16:40
Software Engineering

Assert Chaos

Chris Lienert
Senior Principal Engineer, Smart AI Connect

Once a product reaches the wilds of production, all sorts of things can go wrong. Carefully logging and monitoring are one thing, but what if we could do better?

Bring new levels of code stability by recreating the…

16:40
AI Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

16:40
Research / Deep Tech

Talk to be confirmed

This programme position is being held for a Research / Deep Tech presentation to be announced.

18:00
social

AI Engineer Sydney closing reception

Join fellow attendees and speakers from 6:00 pm for drinks, conversation and a final chance to continue the conference’s discussions together. Gadigal Station is just around the corner from Hilton Sydney; Blackwattle is…

07:30
Leadership breakfast

Leadership Breakfast with Notion: The Lonely Builder — Thinking Together in the Age of AI

JW Selvaraj
Forward Deployed Engineering Lead, APAC, Notion

A breakfast for engineering and technology leaders, hosted by Notion. Places are limited: join the waitlist to attend.

As coding agents become everyday collaborators, engineers can move faster, but may find themselves…

09:00
housekeeping

Welcome to day two

John Allsopp opens the second day of AI Engineer Sydney.

09:05
Keynote

Keynote speaker to be announced

This keynote position is being held while one further speaker is finalised.

09:25
Keynote

The State of Open Source AI

Raffi Krikorian
Chief Technology Officer, Mozilla

Raffi Krikorian, Chief Technology Officer at Mozilla, explores the state of open-source AI, with a preview of Mozilla’s next State of Open Source AI report.

09:45
Keynote

Who Keeps It Open?

Manik Surtani
CTO and co-founder, Agentic AI Foundation

Every generational shift in computing produces plumbing that everyone depends on. TCP/IP, HTTP, the container runtime. And every time, there is a window where someone can quietly come to own it, and everyone else pays…

10:05
Keynote

Keynote speaker to be announced

One further editorial keynote will be announced for this position.

10:25
Keynote

The AI year: how we work, hire and grow now

Fiona Chan
Partner & Technical Recruiter, Lookahead

For a lot of teams, this was the year AI stopped being an experiment and started being part of the job. Shipping got faster, but so did the pace, the pressure and the pile of code waiting for review.

Drawing on…

10:45
housekeeping

Hackathon winner and closing

We announce the hackathon winner and close the keynote programme before the day’s tracks begin.

11:00

Lunch

12:00
Leadership

How we introduced LLMs into credit decisioning

Kevin Nguyen
Senior Product Engineer, Skip

Over the past nine months we've built and deployed an AI-assisted credit assessment system that's now used in production to help credit assessors process home loan applications. More importantly, it was signed off by…

AI Engineering

Oops I Hacked It Again: Six Months of Red Teaming Our AI Agents

Jon Shen
AI Practice Executive - Strategy and Governance, Suncorp

In March I onboarded our first team member dedicated to AI Red Teaming. That was a month before the announcement of Claude Mythos Preview, and the open letters that followed from APRA in April and ASIC in May…

Software Engineering

The Contradictions of Building AI Products and Teams

Sherif Mansour
Distinguished Product Manager and Head of AI, Atlassian

For every claim about how to build with AI, there seems to be an equal and opposite claim that’s also true. Chat is the universal interface, so go headless. Never bolt AI onto your product, reimagine it. Everyone on…

Research / Deep Tech

The Benchmark Ends. The World Doesn’t: Building Persistent Engineering Environments for Continual Learning

Theodoros Galanos
FDE @ APAC, Nomic

Large language models can complete sequences of tasks—but continual learning is not just doing more tasks. Most agent environments reset after every episode: state disappears, required follow-up vanishes, delayed…

12:20
AI Engineering

Deliberate Holes Only

Karla Burnett
Security Engineer, Lorikeet

Making an AI agent vulnerable to exactly one attack is harder than making it completely secure, let alone doing it six different times.

In this talk, I'll describe the process of building an agentic AI capture the…

Software Engineering

Sovereign AI Across the Stack: From Infrastructure to Inference

Daniel Apps
Head of Solutions, ResetData

Building sovereign AI takes more than Australian-hosted infrastructure. It requires control across the entire AI stack, from GPU compute and model deployment to inference, APIs and the platform connecting it all.…

Research / Deep Tech

Extracting Tacit Knowledge for Production Agents

Khali Kalpa-Young
Founder, Alchymie

An eval is a definition of "good" written down well enough for a machine to grade against. In a real business, "good" isn't written down anywhere. It lives in someone's reaction, in what past work actually did, and in…

12:30
Leadership

Building AI for students who can't tell you when it's wrong

Ez Herrmann
Technical Solution Architect, Sitback Solutions

Teachers in Australian specialist schools spend two hours or more preparing a single lesson, then adapt it again for every ability group in the room. Many are already pasting student details into consumer chatbots to…

12:40
AI Engineering

Query before mutation: guardrail patterns for agents that touch production infrastructure

Jeffrey Aven
Maintainer, StackQL Studios

Giving an AI agent permission to change production infrastructure removes the human pause that made plan-and-apply safe. In this talk, Jeffrey Aven shows how to put that judgement back into the system itself.

He…

Software Engineering

We Replaced Our AI Framework in Two Weeks

John Law
Principal Engineer, Accesso

Our main product is a conversational agent that helps users explore and analyse their data. As LLM providers released capabilities such as finer-grained cache checkpoints and tool search, the framework underneath our…

Research / Deep Tech

Adaptive Learning: Encoding Clinician Edits as Memory

Vlad Gavrilov
Senior AI Engineer, Heidi

Clinicians edit their AI-generated notes for many reasons: adding or removing content, fixing spelling, and preferences for structure, wording, or terminology. Some of these edits are contextual, applying in some…

13:00
Leadership

Regulated Doesn't Mean On Rails: what compliance actually asks of your engineers

Stephen Sennett
Principal Forward-Deployed Engineer - Applied AI, V2 AI

We spent three months rebuilding a regulated enterprise's development lifecycle around agents, then worked out how much of the governance we had added was doing real compliance work. Less than we assumed.

Across…

AI Engineering

AI Sandboxes: Running Coding Agents Safely in Production-Grade Environments

Shivay Lamba
Lead Machine Learning | Developer Experience Engineer, Qualcomm

The number of cyber attacks and security risks related to Coding Agents has sky rocketed. AI coding agents like Claude Code, Codex CLI, and Gemini CLI don’t behave like your typical developer tools. They install system…

Software Engineering

Dark Software Factory: Why We Build Differently

Igor Costa
CEO, Autohand AI

What happens when traditional software development approaches can no longer solve the problems we face? In this session, we explore the challenges, gaps, and limitations that remain unsolved, why conventional approaches…

Research / Deep Tech

Building Agentic Memory for an AI SOC: Why Our Semantic Cache Was the Wrong Answer

Mukesh Singh
Principal Detection and Response Engineer, Atlassian

We run a fleet of AI agents against production security detections at Atlassian. One tunes noisy detection rules, another reviews new ones, and more are coming for alert triage and hunting. Every one of them started…

13:20
AI Engineering

Beyond System Prompts: Securing AI Agents with Fine-Grained Authorization

Daizen Ikehara
Principal Developer Advocate, Auth0

To make an AI agent useful, we often give it broad access to APIs and data. As systems move from simple retrieval to autonomous action, system-prompt instructions are not an adequate security boundary.

This…

Software Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

Research / Deep Tech

From Documents to Defensible Evidence: Rethinking RAG for Audits

Sharat Madanapalli
Founder, InTune AI

Audits impose strict requirements for evidence, traceability and expert judgement. Each entity being audited supplies a new body of evidence, made up of manuals, records, tables, diagrams, scans and multilingual…

13:30
Leadership conversation

In conversation

Kevin Nguyen
Senior Product Engineer, Skip
Ez Herrmann
Technical Solution Architect, Sitback Solutions
Stephen Sennett
Principal Forward-Deployed Engineer - Applied AI, V2 AI

The session’s three speakers join the MC for a conversation.

13:40
AI Engineering

Building a Security Agent: Model choice, Harnesses and Evals

Simon Harloff
CTO, Dam Secure

In this presentation, I’ll show how we set out to give developers useful security feedback on every pull request in under three minutes. The benchmark results and methodology are published here:…

Software Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

Research / Deep Tech

Classifiers are dead. Long live classifiers!

Charli Posner
Builder, Stile Education

Training a classifier used to mean collecting labelled data, choosing an architecture, training a model, evaluating it, and deploying it. Today, for a surprising number of problems, you can replace most of that with a…

14:00

Afternoon break

15:00
Leadership

Management Is Dead, Leadership Is Not

Inga Pflaumer
Consulting CTO

Engineering teams are getting smaller. A team of four with strong AI tooling now ships what took twelve people two years ago, and the org chart has not caught up. The first layer to feel it is middle management - the…

AI Engineering

Running 100K+ Concurrent Agents: It's Never the Prompt

Harry Nguyen
AI engineer, insightfactory.ai

Your Agents Aren't Failing at Prompting

Every agent demo works. Then you run ten thousand at once, and the failures have nothing to do with the model: dead tuples piling up, a sync HTTP client freezing the event…

Software Engineering

Trust is engineered, not granted: why we focus on verifying before background coding agents

Vivek Katial
Engineering Lead, Applied AI, Heidi Health
Belen Garcia Fava
Head of Engineering, Heidi Health

Heidi is an AI scribe used by 130K clinicians a week. Our 150 engineers ship 100+ PRs daily into prod, and AI made writing code so cheap that review became the bottleneck: our P75 review wait was 14 hours, almost all of…

Research / Deep Tech

Skippy: The Little Inference Engine That CUDA

James Dumay
Founder, Stealth AI Startup
Daniel Winter-Wijntjes
Co-CEO and Founder, Stealth AI Startup

What happens under the hood when you run a large language model? This talk explores Skippy, a custom inference engine built for Mesh on top of llama.cpp, and the engineering behind local and distributed AI inference.…

15:20
AI Engineering

Don't Fight Hallucinations. Make Them Impossible

Nadia Makarevich
Principal Engineer, Heatseeker

The Heatseeker AI chat answers data questions for marketers who make decisions with million-dollar budgets. Wrong answers or hallucinated numbers are not an option here, as you can imagine ;)

The fight against them…

Software Engineering

From Prompt Rules to Structural Guarantees: The Harness Behind a Production Analytics Agent

Jiggy Kakkad
Staff AI Engineer, Quantium
Tinus Willemse
Executive Manager, AI & Data Science, Quantium

Checkout AI answers open-ended questions about retail sales data in natural language. It plans,
calls analytics tools over MCP, executes Python in a sandbox, and returns a written analysis with
charts. In a system…

Research / Deep Tech

Local AI and the End of the Cloud Default

Lukas Wesemann
Co-founder, CEO, Base Compute

Most AI today runs in the cloud, where every token costs money and every input leaves your device. Now AI agents are running around the clock with access to your email, files, and most sensitive data. That burns through…

15:30
Leadership

Half our handoffs are the bot's idea

Adeline Yaw
AI Integration Specialist, Automattic

About one in four conversations with WordPress.com's AI support bot ends with a person. In about half of those, the bot suggested it.

These are two different problems. In one, the user asks for a person. In the…

15:40
AI Engineering

Give Every Agent a Flight Recorder

Rahul Trikha
Principal AI Engineer, Zendesk

Agent teams should not need to file a ticket with a central evaluation team just to learn whether a new prompt, model, or tool made their agent better. At Zendesk, we developed and deployed a trace-first evaluation…

Software Engineering

Safely releasing AI applications while continuously patching vulnerabilities

Jay Yuan
Staff Software Engineer, Commonwealth Bank of Australia

AI applications still need regular security patches and dependency updates, but those software changes can also affect the data processing, model interaction, and evaluation paths around an LLM. In our releases,…

Research / Deep Tech

Robot Kintsugi: The Art and Design of Reengineering Old Hardware

Martin Kemka
engineer and designer

What does it take to give an old robot new life with AI?

This talk explores the art and design of reengineering abandoned hardware, treating its physical constraints and original character as starting points for new…

16:00
Leadership

The five stages of losing our craft

Andrew Murphy
CEO, Prudixa

Your best engineer won't use AI tools. Your tech lead is using them but won't tell anyone. Your new grads don't understand what the fuss is about. And you, the leader, are supposed to have answers for all of them.…

AI Engineering

Office-Brain and the Night Shift: What Happens When You Turn Off the Meter

Mark Pesce
Co-Founder, Noops

"Good enough" AI now runs on a reasonably beefy laptop. Qwen3.8-27B benchmarks at an Intelligence Index of 52 - roughly the best money could buy back in February - and inferences happily on consumer kit. When tokens are…

Software Engineering

Should You Build a Software Factory? Tales from an Open-Source Maintainer

Harlan Wilton
Open-source developer, Self Employed

Coding agents helped me write code faster, but I kept running into problems elsewhere in my engineering workflow. Tests passed without proving much. Parallel tasks changed the same files. Reviews piled up. This talk…

Research / Deep Tech

How to Count to One Hundred

Hugo O'Connor
R&D Engineer, Anuna Research

Agents don't work well together in chat rooms: put a few in a channel and they talk past each other. Natural language and unrestricted JSON feed an open-ended pipeline of reasoning and tool calls with full Turing power.…

16:20
AI Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

Software Engineering

Autonomous agents need autonomous protection

Adesh Gairola
Founder and CEO, raxIT Labs

Autonomous agents need autonomous protection. An agent that acts alone at 3am cannot wait for a quarterly pen test, a consultant's report, or a security engineer the team does not have. We started with the data. We…

Research / Deep Tech

Talk to be confirmed

This programme position is being held for a Research / Deep Tech presentation to be announced.

16:30
Leadership conversation

In conversation

Inga Pflaumer
Consulting CTO
Adeline Yaw
AI Integration Specialist, Automattic
Andrew Murphy
CEO, Prudixa

The session’s three speakers join the MC for a conversation.

16:40
AI Engineering

Talk to be confirmed

This programme position is being held for a presentation to be announced.

Software Engineering

Assert Chaos

Chris Lienert
Senior Principal Engineer, Smart AI Connect

Once a product reaches the wilds of production, all sorts of things can go wrong. Carefully logging and monitoring are one thing, but what if we could do better?

Bring new levels of code stability by recreating the…

Research / Deep Tech

Talk to be confirmed

This programme position is being held for a Research / Deep Tech presentation to be announced.

18:00
social

AI Engineer Sydney closing reception

Join fellow attendees and speakers from 6:00 pm for drinks, conversation and a final chance to continue the conference’s discussions together. Gadigal Station is just around the corner from Hilton Sydney; Blackwattle is…

Wednesday December 9

Workshops workshop

Build and Evaluate a Security Agent: Models, Harnesses and Evals

Simon Harloff
CTO, Dam Secure

Can an AI security reviewer find vulnerabilities it has never seen—or is it simply repeating familiar benchmarks? In this three-hour hands-on workshop, you’ll build a security-review agent and the evaluations needed to…

Workshops workshop

BAML by Example: Build a Self-Improving Agent

Aaron Villalpando
Co-founder & CTO, Boundary

Give an agent a goal in plain language. In this hands-on workshop, you’ll use BAML to build an agent that creates the tools it needs on demand, critiques its own failures, rewrites those tools and improves across…

Workshops workshop

AI-Powered ESP32 Development with PlatformIO

Jeremy Kelaher
AI Enablement Architect, SBS

AI-assisted development is reaching every part of software engineering—including embedded development on microcontrollers such as the ESP32. In this introductory, hands-on workshop, participants will connect an AI…

Workshops workshop

Context Engineering: Building Better Context Systems with DSPy

Drew Breunig
CEO and Co-founder, Cmpnd

Context systems often fail in ways that better prompting alone will not fix. In this hands-on workshop with the author of O'Reilly's The Context Engineering Handbook, you’ll diagnose a range of common—and less…

Workshops workshop

Moving Your Agentic Coding Workflow to Open-Weight Models

Joseph Gulay
Senior Machine Learning Engineer, ResetData

Claude Code, Codex and other AI coding agents are transforming how developers work. But their cost, privacy implications and dependence on proprietary models are leading many teams to explore more open alternatives.…

Workshops workshop

Building Agents That Safely Operate Real Cloud Infrastructure

Jeffrey Aven
Maintainer, StackQL Studios

AI agents can inspect and change cloud infrastructure—but how do you let them act without giving up control?

In this hands-on workshop, you’ll first build a read-only inventory and audit agent that queries live…

Workshops workshop

Beyond the Context Window: Building Shared Agent Memory

Shivay Lamba
Lead Machine Learning | Developer Experience Engineer, Qualcomm

Your coding agent learns how a project works, then the next session repeats the same investigation. Another agent misses an architectural decision, follows an outdated instruction or cannot access knowledge held in a…

Workshops workshop

Building for dataflow: the developer stack behind fast inference

Justin Woo
Developer Advocate, SambaNova
MK Swaminathan
Product Lead, SambaNova

An interactive, half-day session focused on SambaNova's dataflow developer tools, detailing how engineers deploy and fine-tune models designed for Reconfigurable Dataflow Units (RDUs).

You will compile a PyTorch model…