Last updated:
Quick answer
Before you quote, run every lead through five questions: need, budget, decision-maker, timeline, and fit. The AI turns your answers into a go or no-go.
At a glance
All outcome figures are estimates from cited sources, not independent verification by us.
- What it is allowed to do
- Drafts for you
Writes drafts (emails, posts, plans, replies). You review and send. Nothing goes out without you.
- Time saved (estimate)
- About 30 to 60 minutes per bad lead avoided
- Difficulty
- Beginner
- Tools needed
- ChatGPT
- Typical cost
- Free tier of ChatGPT or Claude. Nothing to buy.
Reviewed Oct 19, 2026
Basis (estimate): Estimate only: a site visit plus a written quote for a lead who never buys typically burns an hour or more; no timed study found.
What does this setup do?
Score incoming leads against five qualifying questions so you quote the real buyers and politely pass on the rest.
Who is it for?
Solo operators and small shops that waste hours quoting tire-kickers who were never going to buy.
How do you set it up?
Tools
- A chat AI (free tier is enough)
- Your five questions, tuned to your business (template in the prompt)
- Whatever you know about the lead: their message, your call notes, their website
Steps
- Write down your five questions once: 1) What problem are they solving? 2) What is the budget range? 3) Who decides? 4) When do they need it? 5) Are they in your service area and service list?
- When a lead comes in, gather what you know: their initial message and any call notes.
- Paste the lead details plus the prompt below into the AI.
- Read the verdict: qualified, needs one more question, or not a fit.
- Qualified leads get a quote. "Needs one more question" gets a short reply asking exactly that. Not-a-fit gets a polite no.
- Track which questions catch the most bad fits, and sharpen them over time.
Example output
Illustrative. Your results will differ.
- 3 new leads logged from this week's inbox
- 1 follow-up draft ready for the lead waiting longest
- You review and send. Nothing goes out on its own.
Where to paste this prompt
ChatGPT: ChatGPT → Project instructions, or ChatGPT Tasks for scheduled reminders (once a day on Free)
Copy-paste prompt
Adapt bracketed fields to your situation.
Qualify this lead for my business. Be blunt. I would rather hear "not a fit" now than waste a quote.
My business: [WHAT YOU DO, e.g. "residential landscaping in Rutland County"]
My service area: [AREA]
Jobs I do NOT take: [LIST, e.g. "commercial properties, tree removal over 20 feet"]
My typical job range: [PRICE RANGE, e.g. "$500 to $5,000"]
Lead details:
[PASTE THEIR MESSAGE AND ANY CALL NOTES]
Score the lead on these five questions (yes / no / unknown):
1. Need: Do they have a real problem I solve?
2. Budget: Is there any sign they can pay my typical range?
3. Decision-maker: Am I talking to the person who decides?
4. Timeline: Do they need this in a reasonable window?
5. Fit: Are they in my area and asking for work I actually do?
Then give me a verdict: QUALIFIED, ASK ONE MORE QUESTION (tell me exactly what to ask), or NOT A FIT (tell me why, and draft a polite two-sentence decline).Newsletter
Get the free starter pack
Free starter pack with five beginner copy-paste prompts after you confirm, plus three sourced setups in your inbox each week. Unsubscribe anytime.
What usually goes wrong?
Where agents tend to stall on this job. More patterns in Where AI gets stuck.
- Skipping qualification because the phone is quiet. A bad job costs more than no job.
- Letting the AI be too generous. Tell it to be blunt in the prompt or it will qualify everyone.
- Asking all five questions like an interrogation. Weave them into a normal conversation instead.
Which chat tools work with this prompt?
Paste the prompt into any of these assistants (free or paid tiers).
- ChatGPT
- Claude
Common questions
- Will I lose business by turning leads away?
- You will lose bad business: jobs outside your area, budgets you cannot meet, shoppers collecting quotes. Those were never going to pay you. Qualification protects your calendar for real buyers.
- What if the lead will not share their budget?
- Give a range first. "Most of our jobs land between $500 and $5,000: does that work for what you have in mind?" That is easier to answer than naming a number cold.
- Can the AI decide for me?
- No. It scores what you feed it. You make the call, especially on gut-feel signals like tone and urgency that do not survive in notes.
What tips make it smoother?
- The budget question feels awkward and saves the most time. Ask it early, kindly, and every time.
- "Who else needs to approve this?" asked once beats three rounds of "let me check with my spouse."
- Keep a polite decline template ready. Saying no fast is a kindness to both sides.
- Review your "not a fit" pile monthly. If the same type keeps showing up, your marketing is attracting the wrong people.
Where do the claims come from?
Summaries use public sources linked below, not independent verification. How setups are picked.
- Read HubSpot’s write-up (blog.hubspot.com)
HubSpot: Lead qualification levels: company fit, business pain, decision-making power.
- Read Callbox’s write-up (www.callboxinc.com)
Callbox: Core qualifying questions: problem, budget, decision-maker, success criteria.
Related setups
- Capture estimate leads and draft quote follow-ups
Log every estimate or quote request into a tracking sheet, then draft follow-ups when a lead has waited too long for a quote, without auto-sending mail.
- Summarize customer calls and flag local leads
Post per-call summaries and to-dos to Slack or email, and optionally list local forum posts from people asking for your trade.
- Build a lead-gen site with an AI bot
Use an AI coding or copy assistant to draft a simple landing page and contact form for a local service business, then you approve hosting spend, publish, and wire leads to email or a sheet.