Run personal sales emails and follow-ups with ChatGPT, Gmail and a spreadsheet
Jeremy C. Jones sent 133 emails, including follow-ups, to 76 prospects with ChatGPT, Gmail and a spreadsheet. He reports 14 replies, 8 booked calls and 2 clients at $4,000 each.
Who this is about: B2B coach selling to other businesses
What it takes
- Cost
- Free planChatGPT: Free plan. ChatGPT Plus costs $20 a month. Go, Pro, Business and Enterprise plans are listed on chatgpt.com/pricing.Price checked Oct 15, 2026 on help.openai.com. Prices change; check before you buy.
- Setup time
- An afternoonOur estimate from the source, for one business.
- Skill needed
- No codeApps and settings only.
Explain it simply
A ChatGPT project is a saved workspace with standing instructions. He told it who to target. It collected prospect details into a Google Sheet, then drafted a short email that mentions one real fact about that person and asks one low-pressure question. He read every draft and sent it from Gmail. Follow-ups lived in the sheet so nobody was forgotten. He started with a small list so the mailbox did not look like a blast.
How do small businesses use AI for sales follow-up?
AI researches each prospect, drafts a short personal first email and the follow-ups, and logs everything in a spreadsheet so nobody is forgotten. Coach Jeremy C. Jones contacted 76 prospects with 133 emails, including follow-ups, using ChatGPT, Gmail and Google Sheets: 14 replies, 8 booked calls, 2 clients at $4,000 (X, Oct 2026).
| Workflow / use case | Primary AI role / tool slot | Input data | Expected business output / time saved |
|---|---|---|---|
| Prospect emails and follow-ups | ChatGPT project + Gmail + Google Sheets | A target-client profile, prospect list, email drafts | 133 emails to 76 prospects: 14 replies, 8 calls, 2 clients at $4,000 each, self-reported |
How does this differ from other ways to do this job?
This page is about starting and following up conversations with new prospects. The page on quotes that went quiet covers proposals nobody answered. The reply-only bot page answers people who already wrote in. Clay researches at a larger volume. This route uses ChatGPT, Gmail, and a spreadsheet.
What was done
On Oct 22, 2026, coach Jeremy C. Jones posted his outreach system on X. oEmbed lists him as Jeremy C. Jones. The same text was also posted from @jeremy3102.
He used a ChatGPT project, Gmail, and Google Sheets. The post says he contacted 76 prospects with 133 emails, including follow-ups, and got 14 replies, 8 booked calls, and 2 clients at $4,000 each.
The post is self-reported. It ends by asking people to reply for a free ebook. This page does not link that ebook.
Commercial email in the United States needs a working opt-out and your real postal address. The FTC's CAN-SPAM guide is linked below. He reviewed and sent every email himself. Copy that part.
How it went
The numbers come from his own X post, not from a client list we could audit. They are specific: 76 prospects, 133 emails, 14 replies, 8 calls, 2 clients at $4,000 each.
- He drafted with ChatGPT, sent from Gmail, and tracked follow-ups in a sheet.
- Put your opt-out line and postal address in the prompt before you send the first email.
Prompt
- Context / Role
You sell a service to other businesses and want more first conversations without hiring a salesperson.
- The copy-paste prompt
PromptWritten by our editors from the source Act as my business development assistant for [BUSINESS_NAME]. We help [IDEAL_CLIENT] with [OFFER]. A good prospect shows this signal right now: [BUYING_SIGNAL] For each prospect in [PROSPECT_LIST]: 1. Write one specific, checkable fact about them, with the source link. If you can't find one, write "No fact found" and skip the email. 2. Draft email 1 (under 90 words): the fact, why I'm writing, one idea relevant to them, one low-pressure question. No hype, no fake familiarity. 3. Draft follow-up 1 for day [FOLLOW_UP_DAYS] (under 50 words, adds one new useful point). 4. Draft follow-up 2 (under 40 words, gives an easy way to say no). Return a table: Name | Email | Fact + source | Email 1 | Follow-up 1 | Follow-up 2 | Status (blank). Include my opt-out line: [OPT_OUT_LINE]. I will review and send every email myself.- Variables to customize
- [BUSINESS_NAME]
- [IDEAL_CLIENT]
- [OFFER]
- [BUYING_SIGNAL]
- [PROSPECT_LIST]
- [FOLLOW_UP_DAYS]
- [OPT_OUT_LINE]
- Expected output / next step
A sheet-ready table of researched facts and three-step email drafts. You review and send every email yourself, with your opt-out line included.
Written by our editors for any AI chat. It is not a built-in ChatGPT sales feature. You send every email yourself.
Setup notes
- Write who you help, the offer, and the signal that someone might need it now.
- Research a small list. Skip anyone you cannot find a real, sourced fact about.
- Draft the first email and two follow-ups. Include an opt-out line and your postal address.
- Read every draft. Send from Gmail. Log replies and the next follow-up date in the sheet.
- Start small so a new sending pattern does not hurt delivery.
Business fit
Who this helps, and how:
Bookkeeper targeting new restaurants: research each restaurant, draft a short note, and follow up from a sheet.
Solo foundersWeb designer targeting businesses that are hiring: use a hiring post as the fact in the first email, then two short follow-ups.
AgenciesCleaning company targeting new offices: build a short list of new tenants and send personal notes you approve.
Local & service
Related
- Approval gates: Bots do the work, you keep the irreversible clicksBot structure
- Grok Bot + n8n or Make: fixed workflows hand the judgment to a BotStack
- Evidence grade BChoose which industry to sell to with a 15-minute AI research passStrong evidence, using ChatGPT, Claude and Clay
- Evidence grade DFollow Up on Quotes That Went Silent With an AI-Written Three-Touch PlanLight evidence, using ChatGPT, Claude and Quo
- Evidence grade BA Reply-Only Bot Booked 20 Sales Calls in 8 Days From Cold EmailStrong evidence, using Grok Bot, Cold-email sending tool and Booking calendar
- AI use cases for sales teamsDepartment hub: AI for sales, 34 examples
Similar tools
Other tools for this job, and how they differ. Chosen by our editors, never paid for.
- Clay
Finds and enriches lead lists from many data sources, aimed at higher-volume outreach.
See it in use: An Outbound Agency Has Grok Bot Build Clay Workflows and Review Every Campaign Daily
- Lindy
No-code agent builder. One page here uses it to log demo calls into a CRM.
See it in use: A Sales Team Turned Demo Calls Into HubSpot-Ready Notes and Follow-Ups With a Lindy Agent
- Grok Bot
Can remind you when a follow-up is due and draft it for approval before it is sent.
Stack: Grok Bot + n8n or Make: fixed workflows hand the judgment to a Bot
“Strong evidence” (grade B) means: The person who did the work describes the setup and results in detail. How we grade. Spotted a mistake? Suggest a correction.
