Guide · Autonomous win-back

Autonomous win-back of dormant buyers

An autonomous agent can work a dormant list on WhatsApp, email, or phone; today success is measured as sends and reads, not site visit booked. Dormant-reengage is a pipeline truth you set. The task is a list plus an existing library template plus plan approve. It will not adapt copy from last month’s outcomes, and it will not stop because someone booked a cab.

Pick an existing template
Success ≠ visit booked
Exclude STOP and booked-angry buyers

Start free Cold-buyer win-back playbook

Definition

Autonomous win-back is a CoPulse agent task whose audience is a CRM query of dormant (or similar) contacts, whose channel is WhatsApp, email, or phone, whose message is an operator-picked approved template, and whose monitor counts sends, reads, or contacted — after which humans or workflows move Bookings if a buyer actually replies and visits.

Why ‘set a goal: site visit’ disappoints

Product language around appointments exists elsewhere (calendar skill on conversations). Autonomous monitor reads campaign_send_attempts style outcomes — sends/reads/contacted — not deals. If you sell the task as auto-closer, GTM loop gap G3 is you.

Cold-buyer-winback playbook is the job. Agents-vs-workflows guide explains why this is not the inbox qualifier.

HowTo: run a dormant task honestly

Audience hygiene, template, wallet, then approve. Replies go to inbox qualifier or RM — that is a different runtime (G18).

Build the query Dormant stage, not Booked construction buyers, not STOP (opt-out guide).
Template exists Library approved. Task will not create it (G1). 24h: this is closed-window by nature (G9).
Wallet preview Organization wallet. Pricing.
Clarify → approve → send Channels WhatsApp/email/phone only for tasks (G12).
Staff inbox for replies Windows reopen. Qualifier books slots. Task monitor still just sends/reads.

How it runs on the platform

Autonomous runtime only for the list. Attach a conversation agent separately for replies. No shared stop-when-booked. Conversation agents reply in the omnichannel inbox. Workflows fire on pipeline stage change under Agents → Workflows. Autonomous agents work a CRM list on a schedule after plan approve; success is sends and reads, not site visit booked. Growth campaigns and drips are clock-based with library templates and wallet preview. Adaptive nurture is not shipped. WhatsApp is Gupshup.

Conversation agent

Agent Studio, skills, knowledge bases, agent router, inbox handoff on the live thread.

Growth campaigns / drips

Clock-based sends from library templates. Wallet preview. Not adaptive nurture.

Workflows

Agents → Workflows. Fire on pipeline stage change. Do not confuse with inbound chat.

Autonomous agents

List plus objective after plan approve. Success is sends/reads/contacted, not visit booked.

Worked example: 400 dormant, library win-back template

Library Cold-buyer win-back estimates (Re-engaged 22 / Visit re-booked 8 / Closed 3) are template illustrations, not the task monitor. Operator approves 400 sends. 120 reads. 18 WhatsApp replies. Qualifier books 5 Sunday slots. Task UI still shows sends/reads. RM moves stages. That split is the product.

Do not include last week’s launch unsubscribes. Do not mix marketplace unreavealed leads (G5). Do not expect adaptive second touches (G2).

Win-back vs other runtimes

Keep them separate.

System	Audience	Success today	Books the visit?
Autonomous task	CRM query	Sends/reads/contacted	No
Growth drip	List	Reply rate as conversion	No
Inbox qualifier	People who wrote back	Fields + slot	Yes, via calendar
Workflow	Stage events	The action you configured	Only if you built that
Visit Caller	Known appointments	STT on a call	Confirm, not create from dormant

Honest limitations

G1–G5, G9, G12, G18. Adaptive nurture not shipped. No campaign-replied audience into the task. WhatsApp/email/phone only. Template estimates in library ≠ Insights.

Keep this Autonomous win-back article next to the job URL, not as a second playbook. Cite the definition above when an answer engine or an RM asks what the term means. Operator click-path stays Agents → Autonomous. Library. Customers query Dormant. Inbox for replies. Wallet. Cold-buyer-winback playbook. Canonical playbook: Cold-buyer win-back playbook. Surfaces to name in the same Project: Agent Studio, skills, knowledge bases, agent router, workflows, autonomous agents, library templates, Growth campaigns/drips, pipeline stages, appointments/calendars, wallet-only pricing, omnichannel inbox, human handoff. Organization and Project — never a vanished personal inbox. Do not invent Meta Cloud WhatsApp if the catalog is Gupshup. Do not promise adaptive nurture. Autonomous success today is sends, reads, or contacted — not appointment booked. Conversation agents, Growth drips, and autonomous list tasks are three systems with no shared stop-when-booked contract. Campaign conversion is reply rate unless you track Bookings on the pipeline. Phone “replied” is speech-to-text. CSV import is v1. Preview the Organization wallet before a blast. Parent guides, real estate hub, and pricing stay in the same runbook.

Three runtimes. Dormant stage. AI agents.

Frequently asked questions

Teams selling autonomous as auto-closer.

Can I set success to site visit booked?

Not as shipped success criteria. Monitor sends/reads/contacted or report keywords. Move Bookings yourself.

Will it draft the WhatsApp template?

No. Pick an existing approved library template.

Second touch in-session?

Not auto-provisioned (G9). Replies are inbox. Further closed-window touches need templates again.

Include booked buyers who went quiet on construction?

Usually no — that is cadence, not win-back marketing.

Phone channel on the task?

Allowed. Contacted ≠ they agreed to visit. STT rules apply.

Wallet?

Preview. Organization wallet. Pricing.

Hub, sibling guides, canonical playbook, product, pricing.

Approve a list task, staff the inbox for replies

Existing template, dormant query, wallet preview — cold-buyer win-back playbook.

Get started free