Research & data: AI agent use cases
Answering questions from fresh sources, ranking accounts and analysing business data.
Research tasks: answering questions from fresh documentation, ranking accounts, and analysing business data. We check the answers against the original source, not the agent's own summary.
Every card shows two ratings: whether we reproduced the result (V2 reproduced, V1 partly, F failed, V0 not yet run) and how much account access the task needs, from L0 (public web only) to L4 (spends money or deletes). How we test.
3 cases: 1 reproduced, 1 failed, 1 not yet run.
Answer a question that needs this week's docs
Reproduced (V2) on 2026-10-19: the official docs say Sign in with ChatGPT usage is for eligible ChatGPT Plus and Pro subscribers, while the search engine's own summary hedged wrongly.
Build a 'who to follow in AI' list from X
Failed (F) on 2026-10-19: a 25-post X search produced a 'who to follow in AI' list with accounts of 5-21 followers in its top 20.
Amazon replenishment: find high-refund, low-profit ASINs
Sourced only (V0), listed 2026-10-19: “Amazon replenishment: find high-refund, low-profit ASINs” is not yet verified by triedagents because it needs L1 access (reads private data).
Search and filter all 19 cases → · How we test
Get one verified case every weekday
One agent use case we actually re-ran, every weekday. Free.
We only store your email address. Every issue has a one-click unsubscribe link. Privacy