Product and Engineering Executive

Software, AI, and things I’m building.

I’m a product and engineering executive. This is my personal space for writing, experiments, and projects I find interesting.

Story points are useless when building is the easy part

If an agent can build the product before you finish estimating the backlog, what exactly are you estimating for?

02 / Operating model

Questions I keep coming back to

01

AI for
customers

Useful, trustworthy AI capabilities embedded in customer-facing products: retrieval, personalization, conversational interfaces, and the evals that keep them honest.

↗
02

AI for
employees

Governed access to models, tools, knowledge, and workflows: model gateways, usage and cost visibility, and adoption without shadow AI.

↗

03 / Recent notes

The dispatch index

View all
  1. 01 Personalization doesn’t need a six-month project anymore Adding personalization to Croozie took less than a day. Existing models and an ordinary stack make it possible to start with a useful experience, measure it, and improve.
  2. 02 Is it even worth trying to block AI or bots anymore? Blocking bots can be worth doing. But if an agent can deliver most of your product’s value by reading a few public pages, the next strategy discussion probably needs to go beyond a better CAPTCHA.
  3. 03 My AI apps keep turning into the same seven tools The product keeps changing... the infrastructure mostly doesn’t.
  4. 04 I Let AI Agents Review and Merge PRs. Then Disaster Struck. The features worked, but background jobs kept my serverless database awake. AI code review missed the operating assumption that made the design expensive.
  5. 05 OpenAI’s Dot Found Me a NYC Apartment. I Just Showed Up. I gave dot a goal, made decisions along the way, and showed up. It helped with the apartment search, viewings, paperwork, and the little things after signing.