Skip to content

Contact form triage with draft replies

Sorts each website contact form message as lead, support, spam or other before it lands in your inbox, pulls out the stated service, budget and timeline, and adds a draft reply in the sender's language for you to check. If the model fails, the plain email still arrives.

SupportWorks with n8n · Zapier Agents+1Community example
Build your promptSee requirements

What it does

  • Reads the form submission and classifies it
  • Writes a one sentence summary and extracts service, budget and timeline
  • Drafts a reply in the sender's language
  • Tags the email subject so a mail filter can sort it
  • Falls back to the plain email on any error or timeout

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Sending any reply to the sender

You decide what happens next.

More about this workflow

This setup is for support leads and small teams who answer customers every day. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it reads the form submission and classifies it. Next, it writes a one sentence summary and extracts service, budget and timeline. Then it drafts a reply in the sender's language. After that, it tags the email subject so a mail filter can sort it. Finally, it falls back to the plain email on any error or timeout. It works with your email, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before sending any reply to the sender, and says plainly if a step cannot be undone.

“The draft reply comes to you.”
Tengubyte tengubyte on GitHub · Oct 10, 2026
Before you startEmail accessScoped permissionsn8n or Zapier Agents
Explore required tools and model recommendations

Tools and access

  • Gmail

    Handles the email part of this job. Grant read-only plus compose (drafts) scopes.

    API required: Yes. Needs a Google Cloud project with an OAuth app and the Gmail API turned on. The agent signs in through OAuth with only the scopes you pick.

    Sign up: Google Workspace

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Sonnet 5.5

Writes careful replies and reads long ticket threads.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

Claude Haiku 5.5

Made for sorting and routing at high volume.

From $0.10 per million input tokens and from $0.50 per million output tokens.

Anthropic docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

one or two sentences

name, email, company, message

2Your prompt

4 of 4 still empty
Fill these in before you run it: [WHAT YOU SELL: one or two sentences] [FORM FIELDS: name, email, company, message] [INBOX FILTER RULES BY TAG] [REPLY LANGUAGE DEFAULT] You are the Contact form triage with draft replies agent. Sorts each website contact form message as lead, support, spam or other before it lands in your inbox, pulls out the stated service, budget and timeline, and adds a draft reply in the sender's language for you to check. If the model fails, the plain email still arrives. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Reads the form submission and classifies it - Writes a one sentence summary and extracts service, budget and timeline - Drafts a reply in the sender's language - Tags the email subject so a mail filter can sort it - Falls back to the plain email on any error or timeout What you must never do without a yes from a person: - Sending any reply to the sender Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: n8n, Zapier Agents, LangGraph

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect Gmail with its own login, not yours. Grant read-only plus compose (drafts) scopes.
  2. 2Paste the prompt where your harness takes instructions. See the note under the Copy button.
  3. 3Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  4. 4Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval27 / 30

Waits for a yes on: sending any reply to the sender.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope20 / 20

Runs on its own login across 1 tool. Fewer connections means a smaller blast radius.

How to raise it

  • Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
  • Human approval: Add a second named stop next to "sending any reply to the sender", so every step that leaves your hands waits for a yes, and have the confirm say plainly what cannot be undone +3
  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3

Do all of these to reach 91, up from 79.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Contact form triage with draft replies](https://trustcase.dev/badge/contact-form-triage-with-draft-replies.svg)](https://trustcase.dev/use-cases/contact-form-triage-with-draft-replies)
HTML
<a href="https://trustcase.dev/use-cases/contact-form-triage-with-draft-replies"><img src="https://trustcase.dev/badge/contact-form-triage-with-draft-replies.svg" alt="Trustcase trust score for Contact form triage with draft replies" height="20"></a>

More support workflows

  • Ticket triage

    Sorts new tickets by topic and urgency so the right person sees them first.

  • Reply suggester

    Drafts answers to common questions using your help docs.

  • Refund checker

    Checks refund requests against your policy and lays out the facts.

  • Help doc gap finder

    Spots questions customers keep asking that your docs do not answer.

Other workflows that use the same tools

  • Follow up drafter

    Sales. Writes the follow up email after a sales call so nothing goes cold.

  • Pipeline cleanup

    Sales. Finds stale deals and tells you which ones to close or chase.

  • Meeting prep

    Sales. Gives you a short brief on everyone in tomorrow's sales meetings.