"To love without understanding harms the object of your love" (Thich Nhat Hanh) For us, to code without understanding harms the product of our code -- our software. And quietly hollow out our own skills in the process. So how can you use AI as your coach, your teacher, and your partner in exploration? How can you prevent the brain rot of passivity? And when you're not writing it -- how can you keep all of the new code in your head? This talk aims to ensure your favourite LLM makes you a better developer, not a worse one. I'll share a system for collaborating on software that leaves you sharper, more skilful, and still the one who understands what's running in production.

What happens when you stop treating AI as a chatbot and start building systems around it?

At 15, I’m using AI to build businesses, create content and manage my everyday work. In this talk, I’ll share how I’ve gone from experimenting with different AI tools to developing practical workflows across my business, Vajra Works, my personal brand and my productivity systems.

I’ll explore how I choose the right tools, structure workflows, decide what to automate and keep human judgment involved. Through real examples, demonstrations and lessons from things that haven’t worked, I’ll show how AI can move beyond prompts into systems that help get meaningful work done.

The goal is to make this a practical and valuable session for the developer audience.

A model I was working with scored R squared 0.998 on public US data. One of the input columns had been calculated from the target by the same agency that published both, so the model was rediscovering a formula it had already been handed. Tests don't catch this. Nothing throws, nothing fails, the numbers look great. So I built a linter for it. You write a manifest of what derives from what, the tool walks the graph, and CI goes red when a feature sits on a derivation path to or from your target. It returns four verdicts, including one for columns whose provenance nobody has traced yet. The code is Python. The idea applies anywhere you have a dependency graph and a CI job. I'll show the leak, the manifest, the linter, and a run going red live.
Repo: https://github.com/Adeniyikayodee/derives-from-tutorial

RL Nabors spent years on the React core team at Meta and on browser teams before that. Now they're building an omni-client combining X, LinkedIn, Bluesky and Mastodon content streams and publications in one private app, with no algorithm. Mima (mima.social) launched in San Francisco last month.

RL will demo it live, then take questions about local models and the future of the web in the agentic era.