1. First-touch email from evidence
When to use it: When a qualified lead deserves better than a template blast.
Inputs: Lead name, company, the evidence you found (post, funding, hire), your offer in one line.
Starting prompt:
Write a first-touch email to [name] at [company]. Evidence to reference: [paste]. My offer in one line: [paste]. Under 100 words. Open with the evidence, not with my product. One question at the end.Expected output: A short email that proves you did the reading.
Boundary: You verify the evidence is real before sending. ChatGPT will polish a wrong fact as confidently as a right one.
Ready-made: the Outreach Agent runs this as a standing workflow with gates, $19 one-time.
2. Apply the qualification rubric
When to use it: When a lead looks promising and you need a consistent read.
Inputs: The lead’s details, your qualification criteria.
Starting prompt:
Qualify this lead against my rubric: [paste rubric and lead details]. Criterion by criterion, quote the evidence, mark unknowns as UNKNOWN, and end with what I should ask next. No pass/fail verdict.Expected output: A criterion table with evidence and the exact next question to ask.
Boundary: It reads what you give it. Missing info must surface as unknowns, not assumptions.
Ready-made: the Qualification Agent runs this as a standing workflow with gates, $19 one-time.
3. The follow-up nudge
When to use it: Day 4 of silence after a good call.
Inputs: Prospect name, what you discussed, the one thing they cared about.
Starting prompt:
Write a follow-up email to [name]. We discussed: [paste]. The thing they cared most about: [paste]. 60 words max. Add one new useful angle, do not just ask if they saw my last email.Expected output: A nudge that adds value instead of begging for attention.
Boundary: You send it, and you decide when to stop nudging.
Ready-made: the Follow-up & Pipeline Agent runs this as a standing workflow with gates, $19 one-time.
4. Call prep brief
When to use it: Twenty minutes before a discovery call.
Inputs: Company URL, contact name and role, your 3 discovery goals.
Starting prompt:
Build a one-page call prep brief for [name] at [company URL]: what the company does, likely priorities for someone in this role, 5 discovery questions tied to my goals: [paste]. Mark every fact with a source or as a guess.Expected output: A brief where facts and guesses are clearly separated.
Boundary: Anything marked guess gets verified on the call, not presented as knowledge.
Ready-made: no agent for this one yet.
5. Objection handling rehearsal
When to use it: Before a call where you know the objection is coming.
Inputs: Your offer, the expected objection, your honest answers to it.
Starting prompt:
Play a skeptical buyer. My offer: [paste]. Raise this objection: [paste], then two follow-ups after each of my answers. After the roleplay, grade my answers for specificity and list what I dodged.Expected output: Practice against a skeptic, with an honest grade at the end.
Boundary: Rehearsal text is practice, not a script to read at buyers.
Ready-made: no agent for this one yet.
6. Pipeline review summary
When to use it: Friday, before the pipeline meeting.
Inputs: Your deal list with stages, amounts, last activity dates.
Starting prompt:
Summarize this pipeline: [paste]. Group by stage, flag deals with no activity in 14+ days, and list the 5 actions most likely to move revenue next week. Do not forecast - just show the state and the gaps.Expected output: A meeting-ready summary where stale deals cannot hide.
Boundary: It organizes your data; commit numbers stay with you and your manager.
Ready-made: the Follow-up & Pipeline Agent runs this as a standing workflow with gates, $19 one-time.
7. The break-up email
When to use it: When a deal has been dead for 60 days and you both know it.
Inputs: Prospect name, what they wanted, when you last spoke.
Starting prompt:
Write a break-up email to [name]. They wanted: [paste]. Last real conversation: [date]. 50 words max. Close the file politely, leave the door open, no discount offers, no guilt.Expected output: A clean close that sometimes revives the deal - and either way protects the relationship.
Boundary: You decide the deal is dead. That is a pipeline call, not a writing call.
Ready-made: no agent for this one yet.
Quick comparison
| Workflow | Effort | Cadence | Risk | Ready-made agent |
|---|---|---|---|---|
| 1. First-touch email from evidence | One paste per run | Per event | Draft-first, review before use | Outreach Agent |
| 2. Apply the qualification rubric | One paste per run | Per event | Draft-first, review before use | Qualification Agent |
| 3. The follow-up nudge | One paste per run | Daily | Draft-first, review before use | Follow-up & Pipeline Agent |
| 4. Call prep brief | One paste per run | Per event | Draft-first, review before use | none yet |
| 5. Objection handling rehearsal | One paste per run | Per event | Draft-first, review before use | none yet |
| 6. Pipeline review summary | One paste per run | Weekly | Draft-first, review before use | Follow-up & Pipeline Agent |
| 7. The break-up email | One paste per run | Daily | Draft-first, review before use | none yet |
Free download
Get the Qualification rubric template (CSV) - the companion file for these workflows, with sample rows filled in.
Platform notes
ChatGPT is a third-party product (https://chatgpt.com). We are not affiliated with or endorsed by them. Capabilities and names verified 2026-09-13; re-check before relying on specifics. The prompts above are platform-agnostic - they work in any capable assistant.
Want the job done instead of prompted? Browse the sales teams agent menu or the AI agents for sales teams guide.
Questions people ask
Are these ChatGPT workflows free?
Yes - every item includes a starting prompt you can copy free. Matching $19 standing agents are linked where they exist.
Are you affiliated with ChatGPT?
No. AI Agent Skills is an independent store; ChatGPT is named only because these workflows run on it. Facts checked 13 September 2026.
Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.