Writing

Short, specific notes on AI features, automation and shipping systems that keep running. What worked, and what I’d do again.

  1. I let an LLM read a sales team's CRM notes. Then I refused to trust it.

    How I built a pipeline that surfaces which marketing assets show up in the deals that advance — and why the interesting engineering is all downstream of the model.

  2. Make a small team move like a big one

    The repetitive work is a hidden tax on every team. Here is how I stop paying it.

  3. Shipping your first AI feature without losing the plot

    Extraction, not magic. Treat the model like an unreliable function and wrap it accordingly.

  4. Event-driven on AWS serverless, from zero

    SQS, Lambda, DynamoDB — a mental model that scales without babysitting.

  5. Rebuilding a production browser extension

    What I'd tell myself before starting a ground-up extension rebuild.