Form Reply Drafts: Claude + Make

A wedding venue has a contact form, and everyone who fills it out gets the same auto-reply: thanks, we will be in touch. For a couple imagining the most important day of their life, that canned line is a small cold shower. The venue means well; they just cannot hand-write a warm note to every inquiry the moment it lands.

This build writes that warm note for them. When someone submits the form, Claude drafts a short, personal acknowledgment that references what the person actually said, and it lands as a Gmail draft. A human glances at it and sends. The reply feels written by a person because, in the part that matters, it was guided by one.

We wire it in Make. It closes this pillar nicely: a form is just another inbox, and like our Gmail draft-replies guide, the reply stops at a draft so a person stays in the loop on anything that matters.

What does this workflow actually do?

In one line: a form submission becomes a personal draft reply. Make watches your form. When someone submits it, Claude writes an acknowledgment that references their answers, and Make saves it as a Gmail draft addressed to them. You read it, and send.

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

• The wedding venue above, replacing a cold auto-reply with a note that sounds like a person wrote it.
• A therapy practice whose intake form deserves a careful, warm acknowledgment, not a robot.
• A custom-furniture maker whose quote form gets a real first reply referencing the piece described.
• A nonprofit volunteer-signup form thanking each person for the specific help they offered.

Collecting the submission is automatic. Writing a warm, specific reply to each one is the human touch that usually gets dropped. Claude drafts it; you keep the touch.

Why use Make if Claude can already write?

Worth asking. Claude is good at the note: reading what someone submitted and writing a warm, specific reply. It is not built to watch your form, carry the answers across, save the draft, and run on its own. That is plumbing, and Make handles plumbing.

Make does the no-judgment steps: catching the submission, saving the draft, running unattended. Claude does the one step that needs warmth and attention, the writing. And because these are often sensitive first contacts, the build stops at a draft so a person reads before anything sends. Make is the line, Claude is the writer, you are the one who presses send. On intake and inquiries, that last human step is not optional.

What do you need before you start?

• A Make account. The free 1,000 operations a month covers a busy form.
• A Claude API key from the console, not the chat app. See how to use Claude.
• A Jotform form with at least a name, an email, and a message field.
• A Gmail account to hold and send the drafts.

Two Make words. A scenario is the whole form-to-draft automation. A module is one box. 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	Watches your form and fires on each submission
2. Brain	Claude	Writes a personal acknowledgment from the answers
3. Output	Gmail	Saves the note as a draft for you to send

Step 1: Watch your form

Create a scenario and add Jotform, Watch for Submissions. Connect Jotform and pick the form you want. This trigger fires whenever someone submits it and hands the next step every field they filled in, including their name, email, and message.

Step 2: Let Claude write the acknowledgment

Add a Claude module, Create a Prompt, paste your key, pick Sonnet. The instruction that makes it feel human is to reference one real detail:

Write a short, warm acknowledgment email to someone who just
submitted our contact form. Use their details.
Name: {{name from Step 1}}
Message: {{message from Step 1}}

Reference one specific thing they wrote, in one line. Say what
happens next and roughly when. No hype, no emoji. Sign off as the
Oakhill Venue team. Return only the reply text.

That “reference one specific thing” line is the whole difference between a note that lands as personal and one that reads like a form letter.

Step 3: Save it as a Gmail draft

Add Gmail, Create a draft. Map the recipient to the email field from Step 1 and Claude’s text into the body. Keep it a draft, not a send: these are first contacts, sometimes sensitive ones, and a five-second human glance before sending is the point of the whole build.

How do you run it and check the result?

Click Run once, after sending yourself a test submission. When I tested this with a sample entry, the draft referenced the right detail and read like a person had written it, not a template. The tuning was that single line telling Claude to name one specific thing from the message, without it, the notes were warm but generic. Once the drafts read the way you want, switch the scenario on.

After that, every person who reaches out gets a reply that feels considered, within minutes, and you spend seconds approving rather than minutes writing. The cold auto-reply is gone, and the warmth scales without a script.

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	A short note on Sonnet costs a fraction of a cent
Jotform	Free plan covers a few forms	Paid plans from about $34/month
Gmail	Free	Free

Each submission uses three Make operations and a sliver of Claude. A typical contact form sits well inside every free tier here. More on Make’s tiers in our Make guide.

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

• The note sounds generic. Keep the “reference one specific thing” line in the prompt. This is the fix that mattered most in testing.
• It sends on its own. Use Create a draft, not Send, especially for sensitive intake. A person should read first.
• A missing field breaks it. Map only fields your form always collects, and mark optional ones clearly.
• It replies to the wrong address. Map the email field from the submission, never a fixed address.

The same trigger-brain-action shape powers many builds. See Make AI scenarios for more.

How do you build this in Zapier or n8n instead?

Same three jobs, different names.

Job	Make	Zapier	n8n
Catch a submission	Watch for Submissions	New Submission trigger	Jotform Trigger node
Write the note	Claude module	Claude (Anthropic) action	Anthropic node
Save as a draft	Create a draft	Gmail Create Draft	Gmail node

Make and Zapier are easiest for a first build. n8n suits self-hosting. Compare them in Zapier vs Make vs n8n.

Frequently asked questions

Does it send the reply automatically?

No. It saves a Gmail draft. You glance at it and send, which matters for first contacts and intake.

Can I use Google Forms or Typeform instead?

Yes. Make has modules for both. Swap the Jotform trigger; the Claude and Gmail steps do not change.

How does it sound personal and not canned?

The prompt tells Claude to reference one specific thing the person wrote. That single detail is what makes it land as human.

What about sensitive intake, like a clinic?

Keep it as a draft so a person always reads before sending, and keep the tone careful in the prompt. Never auto-send sensitive replies.

Is the chat app the same as the API?

Same models, different door. Make needs an API key from the console, not the chat login.

Primary sources

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

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

You may also like

• Draft WordPress posts from a spreadsheet with Claude + Make
• Turn a YouTube video into a WordPress draft with Claude
• Turn a blog post into LinkedIn and X posts 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