← NotesStage

Scaling

Once something's working, the problem changes. Notes for teams making AI ordinary: reliability, cost, quality, and the things that quietly decide whether it lasts.

Reliability · Restraint
The boring layer does the real work
Businesses keep asking for an AI that does the whole job. The job usually has a part that has to come out the same every time, and that part is what AI is worst at. Build the plain, rule-based layer first. Then let the AI read it.
James Dodd18 Apr 20265 min read
Case studies · Cost
Your AI bill isn't the real bill
When an AI silently starts missing things, the invoice is the last place you'll notice. The cost lands somewhere else.
James Dodd14 Apr 20263 min read
Cost · Guides
Not every task needs the biggest model
Every time a new frontier model lands, someone proposes plumbing it everywhere. The right answer isn't a smaller model. It's a test.
James Dodd11 Apr 20264 min read

Scaling

The boring layer does the real work

Your AI bill isn't the real bill

Not every task needs the biggest model