# What will you learn at AI Engineer Sydney?

> The programme follows the decisions teams face when AI moves from experiment to production: how to build capable systems, how to know they can be trusted, and how software work changes when agents become part of the team.

Canonical page: https://webdirections.org/ai-engineer/program/
Program status: The speaker lineup and talk descriptions are public. Session days, times, rooms and the full timetable have not yet been published.

## 01 — Build agents that work in production

Move beyond the demo: engineer context, memory, tools, interfaces and infrastructure for agents that must run reliably, economically and at scale.

Topics: [AI engineering](https://webdirections.org/ai-engineer/topics/ai-engineering/), [Agent architecture](https://webdirections.org/ai-engineer/topics/agent-architecture/), [Context, memory & knowledge](https://webdirections.org/ai-engineer/topics/context-memory-knowledge/), [Infrastructure](https://webdirections.org/ai-engineer/topics/infrastructure-operations/)

## 02 — Earn the right to trust them

Replace plausible output with evidence. Trace behaviour, evaluate changes, constrain authority and design for security, auditability and real consequences.

Topics: [Evals & evidence](https://webdirections.org/ai-engineer/topics/evals-evidence/), [Security & safety](https://webdirections.org/ai-engineer/topics/security-safety/), [Governance & risk](https://webdirections.org/ai-engineer/topics/governance-risk/)

## 03 — Change how software gets made

Understand what coding agents demand from codebases, tests, developer tools, review systems—and from the people and organisations adopting them.

Topics: [Software engineering](https://webdirections.org/ai-engineer/topics/software-engineering/), [Coding agents](https://webdirections.org/ai-engineer/topics/coding-agents/), [Teams, leadership & work](https://webdirections.org/ai-engineer/topics/teams-leadership/)

## All topics

- [Software engineering](https://webdirections.org/ai-engineer/topics/software-engineering/) — AI changes more than how code is generated. These talks look at the codebase, architecture, testing, review, delivery and team practices required when agents participate across the software lifecycle. (18 published talks)
- [AI engineering](https://webdirections.org/ai-engineer/topics/ai-engineering/) — AI engineering is the work of turning models into dependable systems. This collection covers context, tools, evaluation, observability, infrastructure and the production decisions between a promising model and a useful product. (22 published talks)
- [Coding agents](https://webdirections.org/ai-engineer/topics/coding-agents/) — Coding agents are moving from autocomplete into planning, implementation, review and delivery. These talks examine the harnesses, codebase design, tests, skills and controls that let them contribute without simply producing more code faster. (13 published talks)
- [Agent architecture](https://webdirections.org/ai-engineer/topics/agent-architecture/) — An agent is part model, part software system and part operating environment. Explore how teams structure context boundaries, tools, orchestration and interfaces so capability remains understandable as systems grow. (10 published talks)
- [Evals & evidence](https://webdirections.org/ai-engineer/topics/evals-evidence/) — When output can be fluent and wrong, “it looked good” is not release evidence. These talks show how teams use traces, benchmarks, provenance and evaluation loops to decide whether a change really improved an AI system. (11 published talks)
- [Security & safety](https://webdirections.org/ai-engineer/topics/security-safety/) — Agents can browse, call tools, mutate systems and act with delegated authority. This collection examines red-teaming, isolation, runtime protection and safer architectures for containing that expanded attack surface. (8 published talks)
- [Governance & risk](https://webdirections.org/ai-engineer/topics/governance-risk/) — Governance becomes an engineering concern when AI affects credit, education, audit or regulated decisions. These talks connect sovereignty, compliance and auditability to concrete system choices teams can test and defend. (8 published talks)
- [Context, memory & knowledge](https://webdirections.org/ai-engineer/topics/context-memory-knowledge/) — Useful agents need more than a very large prompt. These talks examine memory, provenance, retrieval, ontologies and tacit knowledge—how to give systems the right organisational context while keeping its source and meaning intact. (9 published talks)
- [Infrastructure](https://webdirections.org/ai-engineer/topics/infrastructure-operations/) — Production agents create new runtime problems: long-lived work, bursty concurrency, token cost and local or constrained inference. These talks focus on the systems and economics needed to operate them reliably at scale. (7 published talks)
- [Teams, leadership & work](https://webdirections.org/ai-engineer/topics/teams-leadership/) — Agents change roles, measures and handoffs as much as they change tooling. This collection looks at the leadership, craft, team design and human judgement required to make adoption productive rather than merely fast. (8 published talks)

The timetable is not public. Topic groupings describe the published talks and do not imply a day, time, room or track.