An agent setup recipe
Prepare the sales handover for onboarding
Prepare a source-linked handover packet that separates approved commitments, customer requests and open questions.
From
You get
What you will get
A draft onboarding handover with evidence, missing fields and a receiving-owner review checklist
Illustrative example · fictional input
- Example input
- A won deal contains an open migration request outside approved scope.
- Example result
- Illustrative result, not a recorded agent run: The packet retains the two-hour session and migration exclusion under O1. The import question remains open under N1, with no promise that migration is included. Noor is the receiving owner, while kickoff date and handover acceptance remain unconfirmed.
Sales checks every promise against approved scope. The receiving owner accepts the handover and confirms unresolved matters through the normal process.
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. The onboarding team’s required handover fields and named receiving owner; Approved scope or order summary and permitted sales notes with source IDs; Confirmed contacts, known open issues and agreed next steps.
- Use a short required form and a live handover call, with the account history available to the receiving team. Practitioners report that these simple methods remain valuable. If the CRM already gives the receiving team usable context, another summary may add work.
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: The onboarding team’s required handover fields and named receiving owner; Approved scope or order summary and permitted sales notes with source IDs; Confirmed contacts, known open issues and agreed next steps. 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 first assignment. Deal D1 is marked won. Approved order O1 includes a two-hour remote setup session for Cedar Workshop; migration is excluded. Sales note N1 says the customer asked whether old bookings could be imported; the representative said they would check. Customer goal G1 is to start using one shared room calendar. Receiving onboarding owner is Noor. Required fields: scope, goal, migration answer, kickoff date. No migration answer or kickoff date is supplied. Prepare the handover for review.
- Compare the response with the review checks below. The following is an illustrative expected direction, not a tested result: The packet retains the two-hour session and migration exclusion under O1. The import question remains open under N1, with no promise that migration is included. Noor is the receiving owner, while kickoff date and handover acceptance remain unconfirmed.
- For real work, provide a fresh packet and explicitly start one batch. Sales checks every promise against approved scope. The receiving owner accepts the handover and confirms unresolved matters through the normal process. 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 required handover fields, receiving owner and acceptance process.
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
- Migration is not added to approved scope.
- The customer request is kept as a question.
- No kickoff date or acceptance is invented.
- No CRM, email or task action is claimed.
- 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.
- Incomplete account history can hide important commitments.
- This does not interpret a contract, approve an exception or prove the handover was accepted.
If something goes wrong
- Sales and onboarding disagree: retain both accounts and ask the named owners to resolve the difference.
- The receiver cannot open the source: flag the access gap rather than treating the summary as sufficient.
- 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
Prepare customer enquiries before you quote
Find missing job details, suggest priority and prepare a reply for you to check.
View agent salesReview a sales discovery call
Find covered topics and gaps in a transcript, with evidence for a coaching discussion.
View agent salesDraft CRM changes from sales notes
Compare supplied notes with the current deal record and prepare field changes for a salesperson to approve.
View agent