Score inbound form leads for fit, alert Slack on hot ones, draft the reply
When someone fills in your website form, this workflow scores how well they fit your ideal customer, saves them to HubSpot, alerts the sales channel on hot leads and drafts a reply in Gmail for a rep to send.
Paste this into ChatGPT, Claude or your agent tool. See the prompt
- Prospecting / Outbound
- beginner
- Sales leader
- SDR manager
- SDR / BDR
- RevOps
- Category
- Prospecting / Outbound
- Difficulty
- Beginner
- Est. cost
- Not stated by source
Problem
Inbound leads sit in a queue until someone gets to them, and reps treat a student and a perfect-fit buyer the same. The best leads wait just as long as the worst.
Setup
An n8n form captures name, work email, website and message. The lead goes to OpenAI, which infers industry and company size, scores fit against an ideal-customer description from 0 to 100, assigns Hot, Warm or Cold and drafts a suggested reply as structured data. The workflow upserts the contact in HubSpot with the summary, score and priority. For Hot leads it posts a detailed alert to a chosen Slack channel and creates a Gmail draft to the lead with the suggested reply, which a rep reviews before sending.
Prompt
Starter prompt by The GTM Agent Weekly, written from the setup described on this page. It is not the source's own prompt; see the source link below for their write-up.
# ROLE
You score inbound form leads for fit and draft a reply for the rep to review.
# INPUTS
- {{FORM}}: name, work email, company website, message.
- {{ICP}}: a written description of our ideal customer (industry, size, use case, buyer role).
# TASK
1. From the website and email domain, infer industry and approximate company size. Say
"unknown" if you cannot tell.
2. Score fit from 0 to 100 against {{ICP}}, and give a one-sentence reason.
3. Priority: Hot (score {{HOT_MIN}} and above), Warm ({{WARM_MIN}} to below {{HOT_MIN}}), Cold (below {{WARM_MIN}}).
4. Summarize what they asked for in one line.
5. Draft a short reply (under {{MAX_WORDS}} words) that answers their message and proposes a next step.
# OUTPUT FORMAT (JSON only)
{"industry": "", "company_size": "", "score": 0, "priority": "Hot|Warm|Cold", "reason": "",
"summary": "", "reply_draft": ""}
# WHAT THE WORKFLOW DOES WITH IT
Update the contact in the CRM with summary, score and priority. For Hot leads, alert
{{SALES_CHANNEL}} and save the reply as an email draft for a rep to review.
# GUARDRAILS
- Personal email domains: score from the message only and say so.
- Never promise pricing, discounts or features in the reply. Never send it. Replace every {{PLACEHOLDER}} before running. Works with any capable LLM and runner.
Tools
Steps
- Import the template and connect OpenAI, HubSpot, Slack and Gmail.
- Rewrite the ideal-customer text in the prompt with your target industries, regions and qualification rules.
- Pick the Slack channel for hot-lead alerts.
- Customize the form fields and link the form from your website.
- Have reps review and send the Gmail drafts for Hot leads rather than auto-sending.
Results
Workflow template with no outcome data.
Used in recipes
What goes wrong
Gotchas
- Industry and company size are inferred by the model from a few fields, so they can be wrong; enrich or check before routing big decisions on them.
- The score is only as good as the ideal-customer text you write. (editor note)
- Warm and Cold leads get no alert, so make sure someone still works them. (editor note)
Get 5 like this every week, free.
Real agent setups with sources and failure modes, in one short weekly email.
Free. One email a week. Unsubscribe anytime.
Source and credit
Abhishek Gawade, n8n template gallery · vendor
Source dated 2026-06-15 · last reviewed 2026-10-11. Summarized in our own words; see the source for details.