Follow Up on Quotes That Went Silent With an AI-Written Three-Touch Plan
Paste quotes from the last two months that never booked into ChatGPT or Claude and get a three-touch text and email plan without "just checking in". A cleaning-company owner says his automated Claude setup closed nearly $20K of stale leads.
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
- Under an hourOur estimate from the source, for one business.
- Skill needed
- No codeApps and settings only.
Explain it simply
Quotes that go quiet are often just busy customers. An AI chat app writes a short, specific nudge for each one, an answer to the likely objection, and a polite 'should I close your file?'. You send them yourself, only to people who gave you their number for the job.
What was done
The copy-paste version on this page is our template: list unsold quotes from 14 to 60 days ago with one note each, run the prompt and send the drafts yourself.
The owner in the source runs an automated version: Claude reads conversations in the Quo phone app and drafts follow-up texts, and the team has a 3-hour window to veto each one before it sends.
How it went
The owner posted: "Claude and @gowithquo integration has closed nearly $20K worth of stale leads since it launched". He says it "Took a few weeks to fine tune".
- That is one self-reported post about an automated setup, with no breakdown of the $20K. The copy-paste version here is untested.
- US texting needs consent. Stop at the first no and honor STOP replies.
Prompt
Context: You are an owner or salesperson with quotes from the last 14–60 days that never booked. Run it weekly on that list.
Act as a friendly, low-pressure follow-up writer for [BUSINESS_NAME], a [BUSINESS_TYPE].
These leads asked for a quote 14–60 days ago and went silent:
[PASTE_LEADS: first name | service | quote amount | quote date | one note from the conversation]
For EACH lead, write a 3-touch sequence with an SMS version and a short email version of each touch:
- Never use "just checking in", "circling back" or "touching base".
- Touch 1 (Day 1): one short, specific question: are they still planning [THEIR_PROJECT] before [SEASON_OR_DATE], or is it on hold?
- Touch 2 (Day 4): answer the most likely objection (price, timing or hassle). If price, offer [SMALLER_OPTION] if I've listed one. Use a real result only if I paste it here: [REAL_RESULT_OR_LEAVE_BLANK]. Never invent results, reviews or numbers.
- Touch 3 (Day 9): politely ask if I should close their file. Mention holding their quoted price only if this is true: [PRICE_HOLD_POLICY].
- Every SMS: under 2 sentences, from [SENDER_NAME], and ending with "Reply STOP to opt out" on the first text.
- Use each lead's note so no two messages read the same.
Our template, cleaned from an outside draft and checked against the official help pages. Replace the [brackets]; check every number before you act on it.
Business fit
Who this helps, and how:
Cleaners, installers and home services: work through last month's unsold quotes in one sitting each week.
Local & service- Agenciesfollow up on proposals that went quiet without sounding pushy.
Related
- Evidence grade CA Four-Person Landscaping Crew Cut Admin From 16 to 6.5 Hours a Week With ClaudeVendor or secondhand, using Claude and Phone voice memos
- Evidence grade DReply to Google Reviews With AI Without Sounding Robotic or Arguing in PublicLight evidence, using Claude, ChatGPT and Gemini
- Evidence grade DClaude Picked a Slow Product and Segment From Omnisend Data, and the Email Brought In $26,619Light evidence, using Claude, Omnisend and Shopify
- Evidence grade BChoose which industry to sell to with a 15-minute AI research passStrong evidence, using ChatGPT, Claude and Clay
- Evidence grade BFive Simple Agents Helped a Dallas Food Distributor Double Monthly RevenueStrong evidence, using ChatGPT, Apify and Apollo
- Evidence grade DA Claude Agent Takes Instagram DM Orders for a 7-Location Sushi ChainLight evidence, using Claude, Meta API (Instagram DMs) and The restaurant's CRM
- AI in sales examplesDepartment hub: AI for sales, 34 examples
Similar tools
Other tools for this job, and how they differ. Chosen by our editors, never paid for.
“Light evidence” (grade D) means: A brief, early or in-progress claim. Treat it as an idea to test, not proof. How we grade. Spotted a mistake? Suggest a correction.
