Write quote follow-ups for day 1, day 3, and day 7, each ready for you to approve

What this does

You give the AI the quote facts. It drafts three follow-ups (about 24 hours, 3 days, and 7 days after sending), each in a short email version and a short text version. You approve and send.

Who it’s for

Owners and small-business sellers with open quotes and no time to chase them. Not for sending texts to people who haven’t agreed to receive them. Not for pricing changes; decide those yourself.

What you need

• Job or product and what you quoted (price, date, validity as you set them)
• Customer’s first name (or placeholder)
• How they prefer to be contacted, and whether they agreed to texts
• Your name and business
• Tool: Any AI chat tool (for example ChatGPT, Claude, Gemini, or Grok), Your email or phone (manual send)
• Cost: $0 with a free AI chat tier (limits change)
• Setup: 3 minutes (estimate)

Steps

1. List the quote facts exactly as sent: price, scope, date sent, how long it’s valid.
2. Check whether the customer gave you permission to text (for example, they texted you first or said text is fine). If not, use the email versions only.
3. Run the prompt.
4. Check every price and date against your actual quote. Fix anything off.
5. Add your opt-out line and your business postal address to the emails (the AI reminds you but does not write them). Send each one yourself on the right day. Stop if they reply, book, or say no.

The prompt

Write quote follow-up messages for a small-business owner. Use ONLY the facts below. Do not offer discounts, change prices or dates, add deadlines I didn't mention, or invent reasons for urgency.

NO-ADDITIONS RULE: Do not add facts, tips, statistics, scarcity or urgency, promises, references or testimonials, or the gender of any person that I did not supply.

Business and what I quoted: [JOB/PRODUCT AND SCOPE]
Price and terms exactly as sent: [PRICE, VALIDITY]
Date quote was sent: [DATE]
Customer first name: [NAME]
Customer agreed to texts: [YES / NO / NOT SURE]
My name and business: [NAME, BUSINESS]
My style: [e.g. friendly, short, no pressure]

Write three follow-ups: about 1 day, 3 days, and 7 days after the quote. For each:
- EMAIL: subject (under 6 words) and body under 60 words
- TEXT: under 300 characters. If I said "NO" or "NOT SURE" about texts, write "SKIP - no consent" instead of a text.

Angles: Day 1 = confirm they received it and offer to answer questions. Day 3 = ask if anything is unclear or if they'd like a different option (don't offer one). Day 7 = friendly last check, say I'll hold the quote through [VALIDITY] as stated, and make it okay to say no.

Do not use "just checking in" more than once. No pressure, no guilt, no fake scarcity. End texts with how to opt out if I'm using a business texting tool: "Reply STOP to opt out."

Do not write an opt-out line or postal address for the emails. At the very end add this line exactly:
"Reminder for you (not part of any message): add your opt-out line and your business postal address to the emails before sending. I have not written them."

Sample input (fake data)

All names and companies are fictional. This is the input for run 4 (the output below), on the current prompt. Runs 5 and 6 used different inputs; see the test log.

Business and what I quoted: Repaint two bedrooms and a hallway (fake business)
Price and terms exactly as sent: $1,850 as quoted; valid through Nov 15
Date quote was sent: Oct 12
Customer first name: Rosa
Customer agreed to texts: YES (she texted me first)
My name and business: Eli, Northline Painting
My style: friendly, short, no pressure

Sample output

Real output from run 4 on 2026-10-14, using the current prompt, from an unspecified AI assistant (Grok Bot agent session; model name not shown). Copied as produced. Nothing was fixed after the fact; the problems we found in it are listed under “How it went”.

**Day 1 (Oct 13)**
EMAIL
Subject: Did the quote arrive?
Hi Rosa,

I sent the $1,850 quote for repainting the two bedrooms and hallway yesterday. I wanted to make sure it reached you. Happy to answer any questions.

Eli, Northline Painting

TEXT
Hi Rosa, it's Eli from Northline Painting. Did the $1,850 quote for the two bedrooms and hallway come through okay? Happy to answer questions. Reply STOP to opt out.

**Day 3 (Oct 15)**
EMAIL
Subject: Anything unclear in the quote?
Hi Rosa,

Is anything in the $1,850 quote unclear? If you'd like a different option, tell me what you have in mind and I'll let you know what's possible.

Eli, Northline Painting

TEXT
Hi Rosa, Eli again. Anything unclear on the $1,850 quote? If you'd like a different option, let me know. Reply STOP to opt out.

**Day 7 (Oct 19)**
EMAIL
Subject: Last check on your quote
Hi Rosa,

A friendly last check on the $1,850 quote. I'll hold it through Nov 15, as stated. If it's not the right fit, that's completely okay. A quick "no thanks" is fine.

Eli, Northline Painting

TEXT
Hi Rosa, last check from Eli on the $1,850 quote. It's valid through Nov 15. If it's not for you, no problem at all. Reply STOP to opt out.

Reminder for you (not part of any message): add your opt-out line and your business postal address to the emails before sending. I have not written them.

Check before you send

• Price, scope, and validity match the actual quote.
• No discount, deadline, or promise you didn’t approve.
• Texts are only for people who agreed to them; STOP handling is in place.
• Opt-out line and business postal address are on the emails (the AI does not write them).
• Stop the sequence when they respond or decide.

How it went

• Test date, tool, model: 2026-10-14. Unspecified AI assistant (Grok Bot agent session; the model name is not shown to the agent). One tool only.
• Runs logged: 6, on 6 different fake inputs (see the test log). Runs 1-3 used the original prompt. Runs 4-6 are a second round on new fake inputs after the prompt was fixed, as listed below. Every run was done by the same AI assistant session that wrote the fake input, and in round 2 the same session also edited the prompt, so these are not blind or independent runs. A script counted words and characters against the prompt’s limits. No second person re-ran it from the written steps.
• Why the label is “Tried in an AI tool,” not “tested”: we reserve “tested” for plays with at least 3 logged runs in at least 2 different AI tools, and we ran one tool. We also have no independent reproduction of the steps and no timed manual baseline. The runs are real, but this is one tool’s behavior, and 3 runs per round is too few to say a problem is gone.
• Time saved: Not measured. We did not time a manual baseline or an assisted run.
• What we changed after round 1: Added: no-additions rule (naming scarcity such as ‘limited spots’); Day 3 now says don’t offer an option; a closing reminder to add an opt-out line and business postal address, not written by the model.
• Round 2 (current prompt, runs 4-6). What worked:
  • No scarcity or urgency lines in any of the 9 emails or 3 texts. In the first round run 2 wrote ‘Spots on my schedule are limited this fall.’
  • Consent handling held: ‘NO’ and ‘NOT SURE’ produced ‘SKIP - no consent’ for all 6 texts; the YES run’s texts ended with STOP language and were under 300 characters.
  • Prices, scope, and validity matched the input. No calendar date was calculated this time (the validity was written as given or as ‘through Nov 15’ because the input said so). The closing reminder was present in all 3 runs.
• Round 2: what failed or needed fixing:
  • Run 4 Day 3 email: ‘I’ll let you know what’s possible’ hints at flexibility on terms. This is the same kind of slip as the first round, and the new ‘don’t offer one’ wording did not stop it.
  • Run 6 Day 7 subject ‘A last check on your quote’ is 6 words (limit: under 6). A script caught it.
  • The emails still have no opt-out line or address in the body; only the closing reminder tells the owner to add them.
• Checked against “Check before you send”: Price, scope, and validity matched the quote in all runs; texts only where consent was YES; run 4 has one line to rewrite; run 6 subject to trim.
• Edge cases: Consent NO and NOT SURE both work again. Not tried: a validity phrased as a duration where a model might calculate a date (‘30 days from Oct 6’), which was the first-round slip.
• Round 1 (original prompt, runs 1-3): what failed, kept for reference:
  • Run 2 Day 7 email: ‘Spots on my schedule are limited this fall.’ The input said nothing about the schedule, and the prompt bans invented urgency. A keyword scan caught it; reading would too, but a skim might not.
  • Run 1: the prompt says ‘hold the quote through [VALIDITY]’ and the model turned ‘30 days from Oct 6’ into ‘Nov 5’. The arithmetic was right but it’s a date the owner didn’t write; check it against the quote.
  • Run 2 Day 3: ‘tell me what you have in mind and I’ll see what I can do’ hints at willingness to change terms; the prompt says to ask about a different option without offering one.
  • The emails have no opt-out line or postal address. The prompt doesn’t draft a footer, so the owner has to add it.
• Not yet observed: how a different model or tool handles the same prompt (a second-tool run is still to do).

Watch-outs

Texting: marketing and follow-up texts generally need prior consent in the US (TCPA and carrier rules); honor STOP immediately. If someone texted you first about a quote, that’s different from a purchased list, but when in doubt, email or call instead. Email: use your real identity and an opt-out. Not legal advice. Don’t automate sending without your approval of each message.

See the Safe Use page: AI drafts, you decide, you send.

Variations

• Contractor version: add the next available start date, only if it’s real.
• Email-only version: remove the text drafts.
• Longer-cycle version: change spacing to 2, 7, and 14 days.

Sources

None. Original wording. (Add any public framework or post used, with link and checked-on date.)

Retest

Re-check by: 2026-12-13 (60 days after the 2026-10-14 runs), or sooner when run in a second tool.

Test log

Changelog

• 2026-10-14: Draft written. Not run yet.
• 2026-10-14: Ran 3 times in one AI assistant on fake data. Filled in sample input and output, how it went, and the test log. Front matter set to runs_logged 3, last_tested 2026-10-14, retest_by 2026-12-13. The 2-tool bar for the word “tested” is not met, so the play is not labeled tested. The prompt text was not changed after the runs.
• 2026-10-14: Prompt revised after round 1. Added: no-additions rule (naming scarcity such as ‘limited spots’); Day 3 now says don’t offer an option; a closing reminder to add an opt-out line and business postal address, not written by the model. Re-ran 3 fresh runs (4-6) on new fake inputs in the same AI assistant. Updated the sample input and output to run 4, the “How it went” section, and the test log (original runs 1-3 kept, marked). Front matter set to runs_logged 6, last_tested 2026-10-14, retest_by 2026-12-13. The 2-tool bar for the word “tested” is not met, so the play is not labeled tested.
• 2026-10-15: Published with the evidence label “Tried in an AI tool” (6 runs, 1 tool, fictional inputs). Earlier wording that implied more evidence than one tool’s runs was replaced with the label; the runs, results, and limits above are unchanged.