In a two-day, 10-task business test, a reviewer scored Dots 9/10 on meeting prep, but a promised visual deliverable was unfinished. Inbox triage scored 7.5/10: priorities were sensible, but it treated an already-resolved issue as still open.
- First reported
- aiagentslibrary.com · 1 Oct 2026
- Added
- 11 Oct 2026
- Source checked
- 11 Oct 2026
What they did
The founder of the review site AI Agents Library tested a dot over two days on her own business accounts, with Gmail, Calendar, Drive and other tools connected. She asked it to prepare her for a real editorial planning meeting from her connected context, and to review seven days of email, work out what still needed a reply or action, and take no inbox actions itself.
What happened
Meeting prep scored 9/10: the information was strong, and after she asked for visuals it switched to cards with open items marked "to confirm", though a promised one-page visual was still unfinished when she checked. Inbox triage scored 7.5/10, with sensible, scannable priorities.
Keep in mind
Triage treated an issue she had already fixed elsewhere as still urgent, because nothing told it the work was done, so inbox output still needs a human check. Scores are one reviewer's judgment over two days.
Try it with your agent
I have a meeting about <topic> with <attendees> on <date>. Using my email, calendar and docs, give me a one-page brief: background, decisions already made, open questions, and anything still to confirm, as short cards with links to the source. Then review the last seven days of my inbox and list what still needs a reply, but check whether I already answered before you flag anything, and do not send or archive messages.
Replace the <angle brackets> with your own details.
Original source
aiagentslibrary.comHands-on reviewA journalist or reviewer used the agent and wrote up what happened.
Tools for this kind of work
- RepoRun Gmail, Drive, Calendar and Sheets from your agent with gws
- RepoTurn PDFs, Word, Excel and slides into Markdown with MarkItDown
