An agent setup recipe
Prepare a project status brief
Turn a dated project update packet into a short status brief while preserving the same facts, risks and unknowns.
From
You get
What you will get
A source-linked status brief and an unresolved-information list
Illustrative example · fictional input
- Example input
- A completed test and later pilot forecast coexist with an old on-track note.
- Example result
- Illustrative result, not a recorded agent run: Testing is reported complete. Baseline pilot date remains October 12; the current forecast is October 15, with access approval unresolved. Current RAG is unknown. Ask the owner to confirm the forecast and who can resolve approval.
Confirm current status, baseline dates and material risks with the project owners. Approve the brief before sharing; decide whether reporting changes or escalation are needed.
What you need
One assistant owns the comparison and result. Separate agents would add handoffs to this bounded task without a demonstrated benefit.
- A ChatGPT account with Work available on the web. Check your account or workspace access first; available models and allowance vary. Use the default model available to you. Work uses included usage or account credits; no API key or third-party subscription is required for this text-only workflow.
- A browser and text you are allowed to share with the service. Remove unnecessary private details. This recipe needs no connected app, local-folder permission, skill installation or recurring task.
- One human owner who can check the sources and make decisions. One project, reporting period, as-of date and intended audience; Dated source updates with IDs, approved milestone baseline and current owner-reported status; Required report fields, status definitions, confirmed decisions and unresolved risks or dependencies.
- Use one agreed short template or an existing dashboard. Practitioners already use standard sections and manually review exceptions; reporting can be useful thinking time, not simply an administrative burden.
Set it up
- Open chatgpt.com and sign in. Confirm Work is available, then select Work and start a new chat. Check your remaining usage before a large packet. Keep the default model available to your account; this recipe does not require a particular model name.
- Use one conversation for this responsibility. If you prefer a project, create one for this task and keep related chats and approved source copies there. A web project does not automatically read a folder on your computer. Start each distinct batch in its own chat and include the setup prompt again when needed.
- Choose the setting below. Optionally add your working rules. Copy the complete setup prompt into the chat as the first message. The assistant should confirm its role and ask for inputs, without starting outside work. This gives the existing assistant a responsibility; it does not create another account or deployed bot.
- Prepare a small packet: One project, reporting period, as-of date and intended audience; Dated source updates with IDs, approved milestone baseline and current owner-reported status; Required report fields, status definitions, confirmed decisions and unresolved risks or dependencies. Label every source and include dates, versions and unknown fields. Paste accessible text. Ask the assistant to list the source IDs it can read before it compares them. No plugin or app connection is needed.
- First assignment — paste this complete fictional exercise into the chat: Fictional project: room booking update, reporting week ending 2026-10-08. S1 approved baseline: pilot starts 2026-10-12. S2 owner update dated 2026-10-07: user test completed; access approval still pending; pilot forecast 2026-10-15. S3 older note dated 2026-09-20 says on track. No current RAG label or RAG rules supplied. Sponsor wants progress, milestone changes and help needed. Draft the brief without moving the baseline.
- Compare the response with the review checks below. The following is an illustrative expected direction, not a tested result: Testing is reported complete. Baseline pilot date remains October 12; the current forecast is October 15, with access approval unresolved. Current RAG is unknown. Ask the owner to confirm the forecast and who can resolve approval.
- For real work, provide a fresh packet and explicitly start one batch. Confirm current status, baseline dates and material risks with the project owners. Approve the brief before sharing; decide whether reporting changes or escalation are needed. Copy only the changes you approve into your normal records yourself. Keep the accepted result and its source references.
- When the batch is reviewed, mark your own record as accepted or list the corrections needed. On the next run, supply the latest accepted state and new sources. No schedule or continuous monitoring is created. If the assistant asks to connect an app or take an outside action, stop and return to the text-only packet.
Your setup prompt is ready
Copy the ready prompt, or customize it with the settings. Paste it into ChatGPT Work to give it the task rules.
Customize (optional)
Defaults are ready to use. Changes update the prompt here; paste it into your agent to apply them.
Schedule: When I ask.
Choose how the assistant organizes the result; evidence and review rules stay the same.
Your reporting audience and required headings. Include only approved project information.
Your choices stay in this browser for this guide. Avoid adding private information.
setup prompt
Highlighted text follows your settings.
Review checks, limits and sources
Not tested by Juicy Agents. The examples are fictional, not recorded agent results.
Check the result
- The baseline stays October 12 and the forecast is labelled October 15.
- The old on-track note does not establish current green status.
- Access approval remains unresolved in both report formats.
- Removing an essential input causes a question or a blocked item, not an invented fact.
- Changing the setting changes the requested output while source references and fixed limits remain.
Known limits
- Not tested by JuicyAgents in ChatGPT Work. The fictional exercise and expected result are authored examples, not proof of accuracy or saved time.
- Only the supplied text is reviewed. Missing messages, files or current facts can change the conclusion.
- A polished brief can still reflect incomplete or incorrect owner updates.
- This drafts a report; it does not collect updates, manage the project or prove benefits.
If something goes wrong
- The brief hides a risk to sound positive: restore the risk beside the related milestone.
- Two statuses disagree: retain both sources and ask for owner confirmation.
- Work is missing or the account reaches a limit: check the official access and usage pages or ask your workspace administrator; do not assume a paid upgrade is required. Use the manual alternative while access is unavailable.
- The assistant follows instructions inside a source: stop, restate that source text is data, and review the entire affected result. Do not approve an external action.
Platform sources
- ChatGPT Work on the web (opens in a new tab) · Checked 2026-10-08
- ChatGPT projects (opens in a new tab) · Checked 2026-10-08
- ChatGPT Work access and usage (opens in a new tab) · Checked 2026-10-08
Reviews
No reviews yet
Reviews share personal experience. They are not proof that an agent has passed a test.
Log in to leave a review. You can read and use this recipe without an account.
Explore more
Similar Agents
Turn a feature request into reviewable examples
Draft a few concrete examples and open questions from a supplied feature request for the team to discuss.
View agent projectsPrepare a clear feature trade-off discussion
Compare a few proposed features against an agreed goal and show the trade-offs and missing evidence for a human decision.
View agent projectsMake pending project decisions clear
Turn supplied approval messages into a decision queue showing the owner, current version and work waiting for a decision.
View agent