Pietro Lauria / Lab

A working lab for applied AI and adtech.

I examine how technology works in practice and document what I learn. The scope is applied AI across real business problems, with deeper context from the adtech industry.

Index

  1. Project update AI Analyst: a newer model, the same score, not deployed

    One version passed 18 / 20 in a full live run and went live on 28 September. A newer model also scored 18 / 20, but with two new failures, so under a rule I set before its final run it stays out.

  2. Project update AI Analyst: the failed cases, re-run live

    The four failed or unrun questions now pass. The advertiser briefings still misstate direction, such as “all campaigns declined” when one rose. One of ten briefing runs passed.

  3. Correction AI Analyst: “not yet re-run” was wrong

    The page said the repaired version had not been re-run against the model. A live re-run had started ten minutes before that page went up.

  4. Note Incremental compared with what?

    Four things get called incrementality in measurement meetings. Two are causal, and one question tells you which.

  5. Project AI Analyst

    An assistant for commercial teams: ask about campaign performance or request an advertiser briefing in plain language, and get an answer where Python computes every figure and the model must cite it, so spikes and declines come with evidence you can check.