Notes from the builds.

Featured · Patterns

Papa Claude and Baby Claude: put the expensive model at design time

We helped a tax accountant in India get an AI agent into their filing workflow. It worked on day one and was on a cost trajectory that would not survive a filing season. The fix was not a better prompt. It was changing who does the thinking, and when. Seven mechanisms, one open-source toolkit, and the measured bill for each phase.

July 2026 · 14 min read · Open source

Measured cost, by phase

Design time, frontier model

~$400

First two returns, before the fix

~$50

Per client, after the split

~$1

The first two figures are measured. The third is the design-basis projection, and stays labeled that way until a full client has run through.

Drafted and being written up, roughly in this order. Every one is grounded in something we shipped, which is the only rule the queue has.

• The annual report is the best AI project your center is not doing

  Four weeks of coordinator time, every year, in every center in the country. Nobody writes about it because it is not glamorous.

  Research centers

• How we run this firm on a dozen agents

  What we automated, what we tried to automate and then reversed, and roughly what it cost us to find out the difference.

  Running the firm

• If a user cannot check the answer, the answer is a liability

  Why we tune our systems to refuse more often than a consumer product would, and what that costs in satisfaction scores.

  Patterns

• Universities are not slow buyers. You are talking to the wrong person

  A principal investigator with grant authority can decide in four weeks. Central IT cannot decide at all.

  Research centers

• What an audit trail for an AI system actually has to contain

  Written after a review board asked us a question we could not answer, and what we changed so that we could.

  Government

Company website

Get the next one by email

Roughly monthly. Only when there is something worth sending.

Subscribe