Journal
Notes from assessments, not essays about the industry
These pieces come out of work in Petaling Jaya and the wider Klang Valley. They are written to be used before an intake call, not as decoration around one.
2026-04-14
What belongs in a model call inventory
A call inventory is not a log dump. It is a named list of every place an app asks a model for something, written so a product lead and an engineer can point at the same row.
2026-05-06
When people say the model is slow
Latency complaints in an AI-assisted app often describe a route, a retry loop, or a screen that waits on work it did not need to wait on — not a model that suddenly forgot how to type.
2026-06-11
User-facing completions and the quiet ones behind them
A week of model usage is often two stories: the completions a person asked for, and the completions the app decided to run while nobody was looking.
2026-07-02
What to send before we read a week of usage
Assessments stall on access, not on analysis. A short, specific pack of materials will tell us whether a window can be reconstructed at all.
2026-07-28
How to read a usage brief without drowning in token counts
A useful brief can be read in one sitting. It names sites, waiting versus not, and the questions the logs still cannot answer. Token totals are a footnote.