Qualify Leads: Claude + Make

A custom van-conversion shop gets the same flood every spring: dozens of “build me a camper” inquiries, a few of them serious, most of them dreamers with no budget. Sorting the real ones means reading each form, and by April the reading does not happen, so good leads go cold next to tire-kickers.

This build sorts them as they land. When someone submits your form, Claude reads the inquiry, scores it hot, warm, or cold with a one-line reason and a suggested next step, and Make logs it to a sheet. You open a sorted board, not a pile of identical-looking submissions.

We wire it in Make, the first build in our Sales and CRM set. It logs to a Google Sheet here, but the same shape writes to HubSpot or any CRM. The judgment Claude adds is triage: it reads intent, you decide who to call first.

What does this workflow actually do?

In one line: a form lead becomes a scored row. Make watches your form. When someone submits it, Claude reads their answers, returns a score with a reason and a next step, and Make appends it to your leads sheet. A pile of submissions becomes a list sorted by who is worth your time.

A few real cases, none of them the usual ones:

• The van-conversion shop above, calling the serious buyers back first.
• A wedding florist triaging inquiries by date, budget, and the vibe described.
• A commercial drone-inspection firm sorting leads by industry and how urgent the job sounds.
• A boutique tax practice qualifying new-client inquiries in the weeks before filing season.

Collecting leads is automatic; a form does it. Reading each one to find the few worth chasing is the grind that slips. That triage is exactly what Claude is good at.

Why use Make if Claude can already read and write?

Fair question. Claude is good at reading an inquiry and judging fit and intent. It is not built to watch a form, score on a schedule, and append rows to the right sheet. That is plumbing, and Make does plumbing.

Make handles the no-judgment steps: catching the submission, writing the row, running on its own. Claude handles the one step that needs reading, the score. Make is the conveyor; Claude is the person who reads each lead. I tried having the AI also manage and route the sheet, and it lost the thread; letting Make own the sheet and Claude own the judgment keeps the board clean.

What do you need before you start?

• A Make account. The free 1,000 operations a month covers a busy lead form.
• A Claude API key from the Claude console, not the chat app. New to Claude? Start with how to use Claude.
• A Jotform form collecting your leads (Google Forms or Typeform work too, with their own modules).
• A Google Sheet with columns for the lead details plus Score, Reason, and Next step.

Two Make words, once. A scenario is one automation, the whole form-to-sheet chain. A module is one box in it. Three boxes, one scenario.

How does the workflow work, step by step?

Three modules, left to right:

Module	App	What it does
1. Trigger	Jotform	Fires when someone submits your lead form
2. Brain	Claude	Scores the lead and gives a reason and next step
3. Output	Google Sheets	Appends the scored lead as a row

Step 1: Watch your lead form

Create a scenario and add Jotform, Watch for Submissions. Connect Jotform and pick the form. This trigger fires on each submission and hands the next step every field the person filled in.

Step 2: Let Claude score the lead

Add a Claude module (Anthropic), choose Create a Prompt, paste your API key, pick Sonnet. Spell out what each score means so the judgment is consistent:

Score this inbound lead. Reply on one line, pipe-separated,
nothing else.
Inquiry: {{fields from Step 1}}

Score (hot = clear budget and timeline; warm = interested, vague;
cold = no fit or just browsing) | one-line reason | suggested next
step. Base it on what they actually wrote, never invent details.

Defining hot, warm, and cold in the prompt is the difference between a useful board and one where everything looks urgent.

Step 3: Log the scored lead

Add Google Sheets, Add a Row, connect your account, pick the sheet, and map the lead fields plus Claude’s pipe-separated Score, Reason, and Next step. Now every lead lands pre-sorted. To write to HubSpot or another CRM instead, swap this one module; the rest is identical.

How do you run it and check the result?

Click Run once after sending a test submission. When I tested this with sample inquiries, the hot, warm, and cold split matched my own read once I spelled out what each level meant, which was the one thing I tuned. Adjust the Step 2 definitions, then turn the scenario on so leads score themselves as they arrive.

After that, your form stops being a flat list and starts being a ranked one. You call the hot leads back the same day and let the cold ones wait, which is the whole point of qualifying.

What does this cost to run?

Piece	Free tier	If you outgrow it
Make	1,000 operations/month free	Core plan from about $9/month
Claude API	Pay per use	Scoring one lead on Sonnet costs a fraction of a cent
Jotform	Free plan covers a few forms	Paid from about $34/month
Google Sheets	Free	Free

Each lead is three Make operations and a sliver of Claude. Even a heavy form sits inside the free plan. For tiers, see our Make beginner’s guide.

What can go wrong, and how do you avoid it?

• Everything scores hot. Define hot, warm, and cold in the prompt with real criteria. This is the one I tuned first.
• It scores spam submissions. Add a Jotform or Make filter so junk never reaches the scorer.
• The columns misalign. Tell Claude to return only the pipe-separated fields, no preamble.
• Lead data is personal. Keep the sheet locked down and mind what you send to any external model.

Want more of this pattern? Our Make AI scenarios roundup has the next ideas.

How do you build this in Zapier or n8n instead?

The three jobs do not change, only the names do.

Job	Make	Zapier	n8n
Catch a lead	Watch for Submissions	New Submission trigger	Jotform Trigger node
Score it	Claude module	Claude (Anthropic) action	Anthropic node
Log the row	Add a Row	Create Spreadsheet Row	Google Sheets node

Make and Zapier are the gentlest for a first build. Zapier vs Make vs n8n compares all three.

Common questions

Can it write to my CRM instead of a sheet?

Yes. Swap the last module for a HubSpot, Pipedrive, or other CRM action. The form trigger and the Claude scoring stay exactly the same.

How does it decide the score?

By the criteria you write into the prompt. Spell out what hot, warm, and cold mean for your business, and it follows your rules, not its own guess.

Will it qualify junk leads as real?

Not if you filter first and define cold clearly. Add a Make filter for obvious spam, and tell Claude that no fit means cold.

Can I use Google Forms or Typeform?

Yes. Swap the Jotform trigger for the matching module. Everything downstream is unchanged.

Is the Claude chat app the same as the API?

Same models, different door. Make talks to the API, so you need a key from the console.

Sources and docs

• Creating a scenario (Make Help)
• Claude API overview (Anthropic)
• Jotform Help Center
• Claude on Make (integrations)
• Lead qualification — Grokipedia

Last reviewed: May 2026. Make, Claude, Jotform, and Google update their interfaces; check the official pages for exact button names.

You may also like

• AI Automation for Beginners (the hub)
• Enrich a lead list with Claude + Make
• Draft WordPress posts from a spreadsheet with Claude
• Make.com Complete Beginner’s Guide
• How to use Claude AI
• Zapier vs Make vs n8n: which to start with
• The AI Tools Directory