Programme topic
AI engineering
Turn a model into a useful product. These talks connect harness design, tool use, search, evaluation and observability with the production lessons that change how teams build their next system.
26 published talks
Talks about ai engineering
The Harness Is the Agent
Mike ChambersSenior 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…
MCP Isn't Enough: Why Agents Needed an Event Loop, Not Just an API
Saul CaganoffManaging 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…
Less is More: Optimising Search for Agents
Ryan AhernForward 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…
Define Good, Then Ship: Blind Evals for Agentic Features
Yasith FernandoPrincipal 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…
Building AI for students who can't tell you when it's wrong
Ez HerrmannTechnical 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.…
The Elephant and the Goldfish: Architecture Patterns for Cutting 70% of Agent Token Costs in Production
Tanya DixitForward 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…
From Prompt Rules to Structural Guarantees: The Harness Behind a Production Analytics Agent
Jiggy KakkadStaff AI Engineer, Quantium
Tinus WillemseExecutive 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…
Office-Brain and the Night Shift: What Happens When You Turn Off the Meter
Mark PesceCo-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…
Building Agentic Memory for an AI SOC: Why Our Semantic Cache Was the Wrong Answer
Mukesh SinghPrincipal 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…
Building a Security Agent: Model choice, Harnesses and Evals
Simon HarloffCTO, 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…
Tools Before Autonomy: What 200,000 Tool Calls Taught Us About Agentic Evals
Dean SosteSenior 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…
Query before mutation: guardrail patterns for agents that touch production infrastructure
Jeffrey AvenMaintainer, 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…
Give Every Agent a Flight Recorder
Rahul TrikhaPrincipal 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…
How to Change an LLM System Without Guessing
Yulia KuchinaStaff 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…
Don't Fight Hallucinations. Make Them Impossible
Nadia MakarevichPrincipal Engineer, Heatseeker
The Heatseeker AI chat answers data questions for marketers who make decisions with million-dollar budgets. Wrong answers or hallucinated numbers are…
Running 100K+ Concurrent Agents: It's Never the Prompt
Harry NguyenAI 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:…
Adaptive Learning: Encoding Clinician Edits as Memory
Vlad GavrilovSenior AI Engineer, Heidi
Clinicians edit their AI-generated notes for many reasons: adding or removing content, fixing spelling, and preferences for structure, wording, or…
Ontologies: AI’s Operating Manual For Your Business
Gareth WilliamsPrincipal 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 BAML Programming Language
Aaron VillalpandoCo-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…
Classifiers are dead. Long live classifiers!
Charli PosnerBuilder, 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…
Don't stop, won't stop. Automated verification of long-running agentic loops
AJ FisherVP Digital Science, Tetratherix
Long-running agentic loops create different engineering problems than code generation. Once agents work unattended for many hours, iterate through 20…
Where Should the Dice Roll? Placing Non-Determinism Deliberately in Enterprise AI
Vighnesh DeshpandeAI 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…
The Benchmark Ends. The World Doesn’t: Building Persistent Engineering Environments for Continual Learning
Theodoros GalanosFDE @ 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…
Extracting Tacit Knowledge for Production Agents
Khali Kalpa-YoungFounder, 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…
We Deleted Most of Our Agents. Everything Got Faster
Khang Nguyen HoangData 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…
Does This Agent Make My Context Look Big? Right-Sizing AI Architectures for Production
Hamish SongsmithHead 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…