One-shotting is seductive. One line of code for web search. One prompt to serve every user. One deploy and you're done. Granola shipped a chat feature into their meeting notes app and found out what comes after that.

This talk is a product engineer's honest account of why the gap between "it works in the playground" and "it works in production" is so hard to close. Web search looks like a single tool call — until it blows up your context, bills you 10p per chat, and your provider ships an overnight update that silently degrades your results. Prompt personalization looks straightforward — until you realize that one prompt genuinely cannot serve the salesperson expecting a deal summary, the engineer expecting blockers and linear tickets, and the HR manager expecting something else entirely.

The response at Granola wasn't to prompt better. It was to build the machinery for iteration: custom internal tracing that exposes tool calls, search trails, reasoning traces, and cost in a UI built for everyone — not just engineers with CloudWatch access. And a move to run their Electron frontend as a web app, so every PR gets a preview link and Cursor can go test changes automatically. The point isn't any single technique. It's the feedback loop — and what happens to an AI feature when it actually has one.

Speaker info:
- https://x.com/mehedih_
- https://github.com/MehediH

AI Engineer

A product engineer at Granola (a meeting notes app) shares lessons learned from shipping AI features in production. Key insights include: why one-shotting LLM features rarely works at scale (cost, unpredictable behavior, context blowup), how they built internal LLM tracing tools for full visibility into agent loops, and how they turned their Electron app's frontend into a deployable web shell to enable preview links, faster iteration, and AI-assisted PR testing with Cursor. The core message is that building good AI products requires tight feedback loops rather than hoping a single prompt works.

You can't just one shot it — Mehedi Hassan, Granola