Practitioner notes on applied AI.
Choosing useful work, building the right system, and checking whether it helped.
The reference note
The 12 Factors of AI Value Engineering
How to decide what to build, whether it works, and whether it’s worth the cost.
Read the twelve factorsExplore the topics
- Value engineeringIs this work worth changing?
- Intelligence selectionWhat should do each part of the job?
- Workflow designWhere does the work get stuck?
- Data and contextWhich facts and definitions can this system rely on?
- Adoption and human workCan people use and review the result?
- Verification and operationsHow will you know it worked?
- System design and integrationWhere do the components, records, and boundaries belong?
Latest notes
What changes for the customer?
A customer can have a ready account and still be unable to do the job they bought the software for. Follow that job before choosing an AI feature.
Read the noteWhere does unfinished work live?
A request can outlive the chat, the worker, and an approval. Save what was requested, what happened, and who must follow up so another person can continue safely.
Read the noteRead-only can still expose the wrong data
Permission to fetch a record does not automatically include permission to send every field to a model.
Read the note