Six questions for an AI analyst
I put the assistant through six questions on demo data. A number it must prove, comparisons it must date, a headline it must catch, a query no widget can express, and a request it must refuse.
Research
Working notes on making AI-assembled analytics trustworthy: what the AI may build, when it must refuse, and how its work is checked against real numbers. There is no publishing schedule. I write when something has survived contact with production. RSS if you want the next one.
-
5 min read
I asked the AI for a revenue dashboard
Eleven plain sentences on demo data became an executive dashboard. The walkthrough, the specifications behind each widget, and the requests it narrowed or refused.
-
6 min read
Where trusted numbers come from
A dashboard number is the last inch of a long pipeline. What actually happens between an operational system's API and a figure an operator can check, told from production.