← Back to library

Build a dashboard page your agent refreshes on approval

Michael Fenech (@Michael_Fenech_) listed ten ways he uses Grok Bot Pages as working dashboards, from a daily command center to a decision tracker and sales view, plus a starter prompt. The prompt makes the agent ask about sources and timing, date-stamp the data, flag gaps and wait for approval before scheduling refreshes. We show it word for word with credit.

  • OutcomeHave your agent interview you about what a dashboard should track, where each number comes from and how fresh it must be, then build one page with the most important items on top, a last-checked time on every section, clear flags for missing or stale data, and a proposed refresh schedule that waits for your approval.
  • SetupUnder an hour
  • LevelStarter
  • CreditMichael Fenech (@Michael_Fenech_)
View original
Works with
Grok BotClaude CoworkChatGPT agentCustom agent

Published Nov 7, 2026Updated Nov 7, 2026AI dry run on sample input: passed Nov 7, 2026Source verified Nov 8, 2026

When should you use it?

  • You keep asking several agents for the same status update every morning
  • A sales, project or routine overview lives in scattered chats instead of one place
  • You want a shareable page that shows when each figure was last checked

Not for: Numbers that must be exact to the minute, such as live trading or payroll runs; Data the agent cannot reach through a connected app or file you approve; Anyone wanting the agent to schedule background refreshes without being asked first

What do you need, and what do you get?

You need

  • The purpose of the page, for example weekly pipeline review or routine health
  • The connected apps, sheets or files the agent may read
  • How often each section really needs to change

You get

  • A single dashboard page with the priority items first
  • Separate sections for results, changes since last check and items needing you
  • A last-checked time per section and flags for anything missing or out of date
  • A suggested refresh routine, held until you approve it

How does it work, step by step?

  1. Pick one purposeStart with a single page, such as your sales pipeline or the health of your scheduled routines, rather than a page for everything.
  2. Answer the interviewFill in [PURPOSE] in Fenech's prompt and answer the agent's questions about sources and update timing honestly.
  3. Check the first buildOpen the page and compare two or three figures against the source app before you rely on it.
  4. Approve the refreshAccept, shorten or slow down the refresh routine the agent proposes; a page only stays current if something updates it.
  5. Prune after a weekDelete sections you never looked at, so the page stays quick to read.

The prompt

The original prompt by Michael Fenech (@Michael_Fenech_), word for word, with a link to where it was published. Below it is our adapted version with fill-in blanks, if you want it. Works in Grok Bot, Claude Cowork, ChatGPT agent and others. Values in lime are placeholders.

Original prompt by Michael Fenech (@Michael_Fenech_)

Word for wordby Michael Fenech (@Michael_Fenech_)
Help me build a Grok Bot Page for [PURPOSE].

Ask me what information matters, where it comes from and how often it should be updated.

Create a clean dashboard showing the most important information first, with clear sections for results, changes and anything requiring my attention.

Use verified information from connected sources. Show when the data was last checked, flag anything missing or outdated, and don't invent results.

Recommend a suitable refresh routine, but ask for my approval before creating it.

Exactly as published by Michael Fenech (@Michael_Fenech_) in X post: ten ways to use Grok Bot Pages as dashboards, with a starter prompt.

Our adapted version (optional)

Fill in the blanks (optional; the copied prompt uses your values)

Adapted prompt3 variables
Build me a one-page dashboard for {purpose}.

Before you start, ask me which figures matter most, which connected sources each one comes from ({sources}) and how fresh each needs to be.
Put the items that need my attention at the top, then results, then what changed since the last check.
Stamp every section with the time its data was pulled. If a source is unreachable or older than {max_age}, say so in that section instead of filling the gap.
Propose a refresh schedule with an estimate of how often it would run, and do not create it until I say yes.

What can go wrong?

  • A page does not update itself. Without an approved refresh routine the numbers quietly go stale.
  • If a source is not connected, the agent may fill the gap with an estimate. Keep the rule against invented results and read the flags.
  • Frequent refreshes on many sections can cost real usage. Match the schedule to how often you actually look.
  • Shared pages can expose client or pipeline data. Check who can open the link before you send it.

Our take

The strongest line in this prompt is the one about time: every section has to say when its data was last checked. Dashboards built by agents tend to look authoritative long after the numbers behind them went stale, and a visible timestamp is the cheapest defense against acting on yesterday's pipeline. Fenech pairs that with two habits we already recommend across the site: forbid invented results, and make the agent ask before it creates a recurring job. The interview step matters too, because most bad dashboards come from the builder guessing which metrics the owner cares about. We would add one thing he hints at but does not spell out: decide how often you will really open the page, then set the refresh to match, since an hourly update on a page you read on Mondays is wasted usage. In our dry run for a fictional landscaping company's sales pipeline, the agent asked five sourcing questions, marked the quotes sheet as last checked two days earlier, and held the daily refresh for approval.

Where the time goes back: One page with dated figures replaces the round of status questions you send to separate agents each day, and the flags tell you which numbers to double-check instead of re-checking all of them.

FAQ

Does this only work with Grok Bot Pages?
The prompt names Grok Bot Pages, but any agent that can publish a document, canvas or web page and run a scheduled task can follow the same instructions.
What kinds of pages does Fenech suggest?
His list includes a daily briefing, a view of what each agent owns, routine health, a sales overview, research comparisons, a decision log, project tracking, an improvement scoreboard, calculators and shareable reports.
Why ask for approval before the refresh routine?
A scheduled refresh runs whether or not you need it, so it uses capacity every time. Approving it keeps you in control of cost and of which data gets pulled.

Source and credit

The original prompt on this page is by Michael Fenech (@Michael_Fenech_), shown word for word with a link to where it was published. The summary, notes and adapted version are ours.

Original
X post: ten ways to use Grok Bot Pages as dashboards, with a starter prompt
Creator
Michael Fenech (@Michael_Fenech_)
Published on
X
Original date
Nov 6, 2026
License
Not openly licensed; the original prompt is shown word for word with credit and a link to the original
Originally for
Grok Bot
AI dry run
Nov 7, 2026: passed. Dry-run tested by our AI test agent on sample input. Asked about sources first, stamped each section, flagged stale and missing data without inventing figures, held the refresh routine for approval.
AI dry run on sample data; not run with live connected accounts. The playbooks.bot test agent filled the prompt with synthetic inputs, produced the output and checked it against the page's stated outputs and guardrails.
Verified
Nov 8, 2026: source link resolves to the original, the credited creator published it, our excerpt or prompt matches it, and the license allows our use.

Are you the creator? Claim or correct this page.

More in Operations & Admin

All 203 Operations & Admin playbooks →

Related playbooks

Operations & AdminPrompt✓ AI dry run

Give email-writing agents six standards and a learning rule

Have your lead agent apply one shared drafting process to every agent that writes or sends email (purpose, context, tone, accuracy, clarity and a pre-send check), learn from the edits you make, and propose instruction changes that you approve before they take effect, without touching existing sending permissions.

Credit: Michael Fenech (@Michael_Fenech_)

Under an hour
Operations & AdminPrompt✓ AI dry run

Make your agents read websites the cheapest reliable way

Give your lead agent a standing rule for pulling information from websites: use a connector first, then a plain script, then a browser page read by a script, and only fall back to screenshots and clicking when nothing else works, with result checks, clear failure reports and saved scripts for repeat jobs.

Credit: Michael Fenech (@Michael_Fenech_)

Under an hour
Operations & AdminPrompt✓ AI dry run

Talk through a meeting with your agent right after it ends

As soon as a client meeting, phone call or on-site visit wraps up, start a voice conversation with your agent, talk through what happened while it is fresh, and get back a written list of decisions, commitments, due dates and open questions plus a follow-up draft you check before anything is sent.

Credit: Michael Fenech (@Michael_Fenech_)

Minutes
Operations & AdminPrompt✓ AI dry run

Turn one recurring task into a repeatable Claude workflow

Choose one chore you repeat every week, such as a status update or a meeting brief, and set it up in Claude as a reusable project: a clear deliverable and reader, saved background, an approved example, tidy inputs, questions before drafting and a review step, so later runs need only light edits before you think about scheduling it.

Credit: Paul Storm

Under an hour
Operations & AdminPrompt✓ AI dry run

Check which of your agents should be merged or retired

Have your lead agent map every agent on your team with its jobs, routines, skills, connections and recent activity, find overlap and unused output, recommend keep, absorb, retire or hand back to you for each, and draft a safe wind-down plan covering routines, open work, saved instructions, files and sign-ins, with nothing removed until you approve.

Credit: Michael Fenech (@Michael_Fenech_)

Under an hour