Everyone is obsessed with autonomous agents right now, but you don't always need one. Often, the better approach is to use AI to generate structured data up front, then let standard code handle the rest. Keep it simple: use AI to build the setup, and run simple logic at runtime.

To prove it, I built an AI movement coach that breaks down videos (like a tennis serve, dance move, or martial arts kata) into step-by-step interactive lessons. A live webcam coach then tracks your form and scores you as you practice.

I built the app using AI tools, but at runtime, it only makes a single call to Claude per new lesson (and even that can be skipped). Once a lesson is created, the system caches it and converts each movement into target joint angles. Plain math handles the scoring in real time. The result is fast, cheap, predictable, and simple.

In this talk, I'll walk through:

Live demos of the coach in action My AI-assisted development workflow Practical strategies to keep runtime costs low Honest takeaways on when an agent is actually worth it versus when a single API call does the job

What is Lovable?
Lovable is an AI-powered app builder that lets anyone turn ideas into real, working software — just by chatting with AI.

Start your project:

Enter your prompt
A prompt is the instruction you type to tell Lovable what to build or change. Be specific — describe what you want and Lovable will generate it.

Enable Plan Mode for complex builds
Plan Mode lets Lovable think through your request before writing code. It asks clarifying questions and maps out an approach — like brainstorming with a co-founder.

Watch as Lovable transforms your prompt into a real product
Lovable writes the code, builds the UI, and gives you a live preview you can interact with instantly.

Make it beautiful with design instructions
Drag in screenshots, reference sites, or describe a style. Ask Lovable to match a specific aesthetic, add animations, or use a particular color palette. Great design is just a prompt away.

Understanding user needs is the foundation of UX, but adoption is what makes solutions truly valuable. At Weir, a global industrial manufacturer, the SMART Factory team thought they knew what factory operators needed. Yet their solutions were being ignored (or even physically broken!).

This talk shares how Weir’s UX team partnered with engineers to uncover real user needs, the creative methods required to co-create digital and physical tools that operators embraced, and how the UX team brought the factory floor into the boardroom to win global stakeholder buy-in.

What you'll learn:

User engagement is critical to innovation, and to making it stick Use your users (the subject matter experts!) when you're designing solutions Creative storytelling wins stakeholder buy-in

This session explores what happens when design meets politics, including, when evidence, policy, and public opinion collide. Drawing on real government projects, Jane shows how design decisions are never neutral, how to recognise political risks early, and how to stay true to user-centred design in complex environments.

Jane Dolan is a user research and service design consultant with over 30 years’ experience working across UK government, defence and public services. Ethical and empathetic in her approach, she specialises in complex and politically sensitive domains, keeping real human needs at the centre of digital services.

Jane leads The Dolan Method and supports teams to design evidence-based, ethical services grounded in robust research. She is also co-founder of ResearchU Ltd, providing certified trauma-informed research training for practitioners working in high-risk and sensitive environments.