One AI agent, four jobs, 46 accounts
A US lead-generation company for land investors runs one AI voice agent across every client account. We worked on the system as part of the engineering team: the GoHighLevel sub-accounts, pipelines and fields every client runs on, and the n8n workflows that connect each call to the CRM, Supabase and Slack.
Same persona, different jobs
From the outside it sounds like one bot. In production it is four agents with different prompts, triggers and data paths, sharing one voice and one set of rules: disclose it is an AI if asked, never make an offer, never negotiate. The company, its clients, numbers and prompts are not named or shown here.
| Agent | What it does |
|---|---|
| Qualifier | Takes warm transfers from human cold callers and runs the qualification interview: property, motivation, price, timeline |
| Inbound | Answers inbound calls to each client's number, day or night, and books a callback window |
| Callback | Calls back prospects whose cold call dropped in under 30 seconds, within 5 minutes |
| Nurture | Long-term SMS, email and voice follow-up for leads that did not close on first contact |
From a phone call to a pipeline stage
One shared Retell agent serves every client; the client is identified by the number called and its context is injected per call. Everything after the call is n8n, Supabase and GoHighLevel.
Follow-up that knows when to stop
Cold calls that drop in under 30 seconds are found every 5 minutes and called back with the property already in context, retrying at 1 h, 2 h, 2 h and 24 h for up to 7 days inside business hours. Leads not reached after six attempts move into a 10-day text, email and voice sequence run by six n8n workflows, which answer replies in real time and pull a human in the moment a seller sounds ready.
One pending action per lead
A unique constraint on the queue makes runaway message loops impossible.
Idempotent by design
Every event carries an external ID, so a retried webhook never doubles a message.
One worker per session
Callback sessions are claimed atomically, so two runs never call the same person twice.
Where the agent meets the business
An agent is only as useful as where its output lands. From February to September 2026 we worked on wiring it into 46+ client accounts and keeping them consistent as the system grew.
One build, every client
Pipeline, required custom fields and tags set up the same way in each sub-account so every workflow finds them by name.
GoHighLevel to n8n
Stage moves into nurture, customer replies, stop tags, signed contracts and speed-to-lead stamps.
AI output back into the CRM
Summary notes, tags and stage moves written back after each call, so operators work from the CRM.
Three things we learned
The full case study as a PDF
The full write-up with the screenshots above, formatted for printing or forwarding. Client details are hidden in the PDF too.
Download the PDFRunning a voice agent whose calls never make it into your CRM properly?
Tell us what you are trying to automate or move. We will say what fits, what does not, and what it would cost.
Book a free 15-minute call