# Software engineering — AI Engineer Sydney 2026 > 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. Canonical page: https://webdirections.org/ai-engineer/topics/software-engineering/ Program status: The speaker lineup and talk descriptions are public. Session days, times, rooms and the full timetable have not yet been published. ## Published talks - [Your spaghetti code has an invoice now: what complexity does to coding agents](https://webdirections.org/ai-engineer/speakers/artem-yakimenko/) — Artem Yakimenko 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 on your API bill. I show and discuss my research based around a series of controlled benchmarks on the same codebase with different levels of… - [Compounding lessons into skills: How we performed a large code migration using AI (with no new bugs!)](https://webdirections.org/ai-engineer/speakers/tom-isles/) — Tom Isles 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 core capabilities is the ability to automatically switch between models when one fails. As the service has grown, product logic specific to… - [The BAML Programming Language](https://webdirections.org/ai-engineer/speakers/vaibhav-gupta/) — Vaibhav Gupta 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 everything," because that’s impractical and doesn’t take advantage of one of the greatest inventions in history. Just as TypeScript enabled… - [209 ports in six days, in a language the model barely knew](https://webdirections.org/ai-engineer/speakers/burin-choomnuan/) — Burin Choomnuan 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 Claude for jank and it confidently writes JVM Clojure, and none of that compiles. Over six days in July I ported 209 of raylib's official C… - [AI Janitor: Making Architecture Review Executable for Coding Agents](https://webdirections.org/ai-engineer/speakers/dave-currie/) — Dave Currie 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 human review loop could not keep up with the volume of AI-generated change. I needed some of the boundaries and feedback a platform team… - [Dependency hell is back. This time it's your agent's config.](https://webdirections.org/ai-engineer/speakers/jack-rudenko/) — Jack Rudenko 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 dozens of client codebases at 10xlabs. Within a few months, the drift was everywhere. One engineer's agent was excellent. The next one ran a config… - [Your Coding Agent Is Fast. Your Codebase Is the Bottleneck.](https://webdirections.org/ai-engineer/speakers/shrey-somaiya/) — Shrey Somaiya 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, verification, slow CI, defense against legacy patterns had become the bottleneck. AI is great at generation of code - but design?… - [Why software factories can't be trusted (and how the Systems Engineering V-model helps)](https://webdirections.org/ai-engineer/speakers/mark-johnson/) — Mark Johnson 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 the diff. In our world, that isn't a quirk — it's disqualifying. We build cardiology, respiratory and clinical-trials systems for public… - [Should You Build a Software Factory? Tales from an Open-Source Maintainer](https://webdirections.org/ai-engineer/speakers/harlan-wilton/) — Harlan Wilton 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 follows the changes I made while building a SaaS and maintaining my open-source projects. I'll use real code and PRs to show what each change… - [Trust is engineered, not granted: why we focus on verifying before background coding agents](https://webdirections.org/ai-engineer/speakers/vivek-katial/) — Vivek Katial 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 it queue time. A 14-hour queue is a reliability problem — it batches changes, delays fixes, and pushes people toward the "just approve it"… - [It's time for a new kind of software](https://webdirections.org/ai-engineer/speakers/rupert-manfredi/) — Rupert Manfredi 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 the existing application stack or replaces the richness of the app with an interface disconnected from the data and capabilities needed to do… - [Don't stop, won't stop. Automated verification of long-running agentic loops](https://webdirections.org/ai-engineer/speakers/aj-fisher/) — AJ Fisher 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, the challenge changes to keeping that activity aligned, verifiable and useful. This talk looks at the verification systems built around… - [The CLI is dead, long live the CLI](https://webdirections.org/ai-engineer/speakers/jan-peer-stocklmair/) — Jan Peer Stöcklmair 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 for humans and agents. This talk is a practical guide to building CLIs for both: output that adapts to its reader, prompts that never block,… - [From REST to Agentic: Trusted APIs in the age of AI](https://webdirections.org/ai-engineer/speakers/leigh-whiting/) — Leigh Whiting 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 workflows, not autonomous reasoning. This talk explores the practical journey of adapting established, trusted API layers to serve agentic… - [My Agents broke APIs - Fixing Multi-Agent Systems with MCP](https://webdirections.org/ai-engineer/speakers/anannya-roy-chowdhury/) — Anannya Roy Chowdhury 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, increased latency, & weak workflows that fail under real-world conditions. As MCP emerges as a standard for how models connect with tools &… - [AI Sandboxes: Running Coding Agents Safely in Production-Grade Environments](https://webdirections.org/ai-engineer/speakers/shivay-lamba/) — Shivay Lamba 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 packages, modify configurations, delete files, run services, and even spin up Docker containers, often requiring constant permission prompts… - [The Model Wasn't the MOAT: How 10 Design System Engineers Turned Platform Knowledge into Enterprise AI](https://webdirections.org/ai-engineer/speakers/sudharsanam-narasimhan/) — Sudharsanam Narasimhan 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 built software. A team of 10 engineers working across design systems, internationalisation, and accessibility had something a general-purpose… - [Shipping together in an AI native team](https://webdirections.org/ai-engineer/speakers/sandra-arato/) — Sandra Arato 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 group assets, select tools, recover from errors, or change behaviour when its underlying model changed. Engineering could implement the interface… The timetable is not public. This page does not imply a day, time, room or track. - [Explore the whole programme](https://webdirections.org/ai-engineer/program/) - [Conference overview](https://webdirections.org/ai-engineer/index.md)