Lead Nurture Automation A check-in with a reason, not a drip, until the lead replies
Cold leads and past clients hear from you when there is a real reason — a listing, a rate change — never a drip.
- Installed for you · one-time$249
- Run for you$197/month
- Custom build · this process$2,000–3,500 one-time
- Starts whenSignal events (listing feed, rate feed, CRM dates, calendar)
Per agent or small team, up to 2,000 nurtured contacts and four signal types. Custom signals from your own data, SMS as a channel, or a team with shared leads are a custom build. Custom builds start at $2,000 site-wide; this band is for this process and its integrations.
Lead Nurture Automation is an automation Agentmelt installs in Slack. The free template is a file you import yourself; the kit ($49) adds the setup guide and prompts. Installed for you costs $249 one-time and is live within two working days of access, with a recorded walkthrough and 30 days of fixes. Run for you costs $197/month, with setup and maintenance included. A custom build of this process is $2,000–3,500 one-time; custom builds start at $2,000 site-wide. No call is needed for any option. Written by Max Zeshut; last revised 2026-09-21.
Reference stack: Claude + n8n. Node names are on each step; the file is under the template.
Founder at Agentmelt
Reviews every build before it goes live; the workflow escalates to a person, never past one.
What is lead nurture?
Lead nurture automation replaces the drip — the same seven emails to everyone who ever enquired — with a check-in that has a reason: the workflow watches for a signal that makes writing worthwhile — a new listing that matches what the lead wanted, a rate change that moves their budget, the anniversary of a purchase, a life event they mentioned — matches it to the leads it applies to, checks the guardrails (frequency, quiet hours, consent), drafts a short message that names the reason in the agent’s voice, sends it after approval or automatically once the type has earned it, logs it, and stops the sequence the moment the lead replies. Leads get fewer messages and answer more of them.
- The CRM drip sends the same seven emails to everyone, and everyone ignores them.
- A listing that matched exactly what a lead wanted went out in a newsletter, three weeks later.
- Leads from two years ago are never contacted again, and some are buying now.
- Nurture messages keep going after the lead replied.
- Nobody knows which reason for writing actually gets a reply.
If two of these are yours, this is the process to look at first. Free audit — or read on.
What it looks like once it runs.
Most nurture is a drip: the same seven emails to everyone who ever enquired. The workflow watches for a reason to write — a new listing that matches what a lead wanted, a rate change that moves their budget, the anniversary of a purchase, a life event they mentioned — drafts a short message that names the reason, sends it in the agent's voice, logs it, and stops the sequence the moment the person replies. Cold leads get two or three well-timed touches a quarter instead of a weekly newsletter, and the agent only hears about the ones who answered.
- Every hour New listings, rate moves and dates in your CRM are compared to what each lead said they wanted.
- On a match A short message naming the reason and what they told you last time is drafted, with one question.
- First month Every draft waits for your tap. After that, the message types you approved go out on their own.
- On a reply The sequence stops and you get the thread with the lead's history in three lines.
Follow-up dies after the first week. The CRM has 400 leads tagged 'nurture' that nobody has written to in months, a monthly newsletter with a 2% open rate, and past clients who list their next home with whoever called last.
Every lead and past client is touched when there is a reason, never when there is not. Replies land in the agent's inbox with the context; the rest runs itself. Past clients hear from you before they need you.
Trigger, then 8 steps.
Seven of the eight steps run without anyone. Step 05 waits for a person.
Signal events (listing feed, rate feed, CRM dates, calendar)
Detect the reason
Hourly: new listings, rate changes and CRM dates are compared against every lead's stated wants (area, beds, budget, timeline) and their history.
Match leads to the signal
A listing matches a lead when area, price band and beds fit; a rate move matches leads whose budget was near the edge; an anniversary matches one person. No match, no message.
Check the guardrails
Skip anyone contacted in the last 14 days, anyone who unsubscribed, anyone with an open conversation, and anyone whose CRM stage is 'active' — the agent is already talking to them.
Draft the message
Two to four sentences in the agent's voice that name the reason, reference what the lead said last time, and ask one question. Fair-housing wordlist applied.
Approve or auto-send
For the first month every draft goes to the agent for a tap; afterwards, message types the agent has approved ten times run without review.
Send and log
Sent from the agent's own address, threaded where a thread exists; the CRM gets a note and the 'last touched' date.
Stop on reply
A reply ends the sequence for that person and forwards the thread to the agent with the lead's history in three lines.
Report
Monthly: touches sent by reason, replies, showings and listings that came from a nurture touch, so the agent sees what a reason is worth.
Every lead and past client is touched when there is a reason, never when there is not
Every lead and past client is touched when there is a reason, never when there is not.
One decision, at step 05. Seven steps ran without you.
Each pattern page explains it in plain words and lists every automation that uses it.
The template is built on n8n (how the n8n AI Agent node works); the same steps run on Make, Zapier or plain code. The tool is chosen to fit your accounts, you own the result, and the template comes in all three formats.
Data it touches
- CRM leads with wants and history (Follow Up Boss, kvCORE, HubSpot)
- Listing feed (CRM or MLS)
- Rate feed or manual rate table
- Agent voice samples
- Calendar for showings
Guardrails
- No message without a reason the lead would recognise; the model cannot invent one.
- Frequency cap: at most one touch per lead per 14 days, at most three per quarter.
- Anyone in an active conversation or an active CRM stage is excluded automatically.
- Unsubscribe and STOP are honoured on the first word; suppression is written to the CRM.
- Fair-housing language check on every draft; flagged drafts cannot be sent.
Why a reason beats a schedule
A drip is written for nobody in particular, so it reads that way. A message that says 'the two-bed on Maple you liked just sold for asking — there is a similar one on Elm' is a service, not marketing, and it gets answered. The workflow's job is to find that reason from data the agent already has, and to stay silent when there is none. Fewer messages, more replies, and no unsubscribes from people who were only ever cold because nobody had anything to tell them.
Past clients are the best leads you are not working
Referrals and repeat business come from people who bought from you three years ago, and the touch that reminds them you exist costs nothing. Anniversaries, a rate move that makes a refinance or a move plausible, a comparable sale on their street — each is a reason to write that reads as thoughtfulness. The workflow treats past clients as a segment with its own signals and its own frequency cap.
The first month runs with approvals for a reason
The drafts are good from the first day, but the agent's confidence is not, and it should not be. Every message goes to the agent for a tap during the first month; message types that have been approved ten times without edits switch to auto-send. The result is a system whose voice the agent has actually vetted, and a habit of glancing at the summary rather than writing from scratch.
What it connects to.
| Tool | Role in this workflow |
|---|---|
| n8n | Signal detection, matching, sending and logging |
| Claude | Message drafting in the agent's voice |
| Follow Up Boss / kvCORE / HubSpot | Leads, wants, history, notes |
| Gmail / Outlook | Sending from the agent's address; reply detection |
| Slack | Approvals in the first month |
Want this running without building it?
$197/month
We set it up in your tools, run it on our servershost it on our n8n cloud (or deploy it to your own n8n, Make or Zapier), watch it, and fix it when something changes. Setup included, cancel monthly; the automation stays yours if you leave.
$2,000–3,500 one-time
Your systems, your rules, your edge cases. A one-off build delivered into your accounts to keepon Claude and n8n, delivered into your accounts to keep, with documentation and a recorded walkthrough.
Per agent or small team, up to 2,000 nurtured contacts and four signal types. Custom signals from your own data, SMS as a channel, or a team with shared leads are a custom build.
Also sold one-time, installed in your own accounts, as part of the real-estate agents package — do it yourself $49 · installed for you $249 · done for you $490.
When this becomes a custom build.
The subscription covers the standard version — $197/month, setup and maintenance included. Three things move it to a custom build ($2,000–3,500 one-time), delivered into your accounts to keep. If one of them is you, say so on the audit and the plan prices both.
Signals from your own data — a portal you run, a lender's API, a home-value model — beyond the four standard types.
SMS as a channel, with the consent records and quiet hours that requires.
A team or brokerage where leads are shared and touches must be coordinated across agents.
Running the standard version first is the usual path: the exceptions it logs in the first month are the scope of the custom build, with your own numbers. How custom builds work.
Frequently asked questions.
Is this different from the CRM's own drip campaigns?
Yes. A drip sends on a schedule regardless of the person; this sends only when there is a reason that person would recognise, and stops on reply. It runs inside the CRM through its API, so nothing moves out.
How many messages does a lead get?
Typically two or three a quarter, capped at one per 14 days. Leads with many matching signals do not get more messages — the cap wins.
Can it text?
Email is standard. SMS is a custom addition because of consent records and quiet-hour rules; it is a good addition once the email version has run for a month.
Is lead nurture automation different from the CRM’s drip campaigns?
The drip sends on a schedule regardless of what happened. This sends because something happened — a matching listing, a rate move, an anniversary — and says so; a lead with no reason to hear from you hears nothing. The CRM stays; the workflow decides when it sends and why, and stops the moment the lead answers.
How many messages does a lead get?
Only as many as there are reasons, with a cap you set — typically no more than one a month — and none after a reply, an opt-out or a purchase. The point is fewer, better messages; a nurture that turns into a drip is the thing the workflow exists to prevent.
Can it text?
SMS as a channel, with the consent records and quiet hours the law requires, is a custom build on the same workflow; email from the agent’s own address is the standard install. Signals from your own data — a portal you run, a lender’s feed, a home-value model — are also custom.
What this blueprint is built on.
Vendor documentation the steps rely on, and the rules the guardrails are written against.
- Follow Up Boss — API documentation docs.followupboss.com/
- FTC — CAN-SPAM Act compliance guide www.ftc.gov/business-guidance/resources/can-spam-act-compliance-guide-business
- FCC — Telemarketing and robocalls (TCPA) www.fcc.gov/general/telemarketing-and-robocalls