What Building an AI Product Actually Taught Me

Description

This talk is about what happens when LLM responses drive your application's behaviour - when the output gets parsed, validated, and executed by your business logic.

While building BraidFlow, a conversation orchestration tool, I discovered that the industry's documented problems aren't solved by better models or bigger context windows. Context drift in multi-turn conversations isn't just a prompt engineering challenge. It's an architectural one. Structured output reliability doesn't need JSON mode - schema field ordering and validation-driven retry logic function as instruction. And cost optimisation isn't about getting the one-shot right with the best model. Informed retry prompts with cheap models can work just as well.

I'll share the benchmarking data that surprised me, the architectural patterns I tried along the way, and the decisions that finally worked. You'll see real code and real failures.

No theory. No hand-waving. Just lessons from shipping features that had to work.