Front page / By role / Manage the inbox

Manage the inbox

Sort mail, answer routine requests and track open threads.

For Executive assistant · Knowledge pack

Who is it for, and what do you need from them?

One line is enough. Step 1 asks the rest in your AI app, and nothing is done until you approve the brief it writes.

In the case folder's materials/: The facts and documents the message rests on.

One writer, facts quoted, the person sends. Not found and out of scope are valid answers here: it says so instead of guessing.

How the field does this well: Draft from the project's own data with links to every task or document a claim rests on.
Reuse the structure of the last update and show the change since then explicitly.
Keep risks, assumptions, issues and dependencies apart, and require owner, date, probability and impact on every risk.
Validate required fields in code.
Ground it first: Ask for, or look in materials/ for: the previous report or plan, the project data, and the required fields for risks and actions. If there is none, say plainly that the result rests on general defaults, and name them.
What stays with the person: Status calls, escalations, and owner assignment. Prepare these; never decide them.
The check that makes it trustworthy: Every status claim links to its source, required fields are validated in code, and the delta since the last report is shown.
The person's own data: If the person has connected Jira + Confluence, Linear, Notion, Google Drive / Docs / Sheets, Microsoft 365 (Excel, SharePoint, Teams), Slack, read their data through that connector instead of asking for exports, and say which source each number or fact came from. Without one, work from materials/.

On your computer: Your files in materials/, every result in outputs/, the work itself. It runs in your AI app, on the plan you already pay for.
With Cheatcode: The steps, the gates and how far each case has come, so a case survives closing the app. See your cases.