Operational AI / Small companiesOperational AI
AI tools for work that still depends on spreadsheets, records and manual checks.
I build focused systems around the information a company already keeps, and publish what they do with it. They handle what can be checked and hand the uncertain cases back to a person.
Position
The question is rarely which model. It is which part of the process can be handled without becoming harder to check.
Public Laboratory
Working experiments · Invented data, disclosed on every entry
Working demonstrations of AI handling real business tasks. Each experiment shows what information it used, what it checked, what it found, and what still needed a person.
Deciding which customer messages a chatbot may answer
It answers from the company's own documents, so the real question is which messages should get that far. Six were checked: two were answered with named sources, one was sent back to be reworded, and three were refused.
- Date
- 2026-09-04
- Run time
- 2 min 7 s
Finding the three records that needed attention
The system checked 212 reconciled records, filtered out 209, and passed three exceptions to a person for review.
- Date
- 2026-08-31
- Run time
- 37 s
Checking overdue invoices against written rules
Six overdue invoices were checked against two company limits. The system showed which rule applied and did not guess the missing contract details.
- Date
- 2026-08-24
- Run time
- 29 s