Follow-up workflows
Create follow-up workflows that combine reminders, WhatsApp or email messages, CRM context, and Max tasks.
Use this product state to connect the visible UI to the operational decision the lesson is teaching.
Learn the system by following the product states.
Use the screenshots as the primary map: start with the full context, trace the connected workflow, inspect the focused UI, then compare against the completed operating state.
Customer signalWorkflow pathVisible outcomeUse this product state to connect the visible UI to the operational decision the lesson is teaching.
Summary
Create follow-up workflows that combine reminders, WhatsApp or email messages, CRM context, and Max tasks.
Concepts covered
Step breakdown
- Define the system to deployStart from this Sales operating system and confirm the business outcome, source signals, owners, and review gates.
- Create the Frontline assetsBuild the workflow canvas, agent prompt, channels, CRM records or tables, routing logic, and Max Activity evidence described in the blueprint.
- Launch the narrow versionDeploy the smallest reliable version first, keep human review visible, then use activity and analytics to expand the system.
What you will build
A follow-up workflow system that automatically sends personalized WhatsApp or notification follow-ups after key sales moments — meetings, proposal sends, conversation endings — using CRM context to make each message specific, not generic.
After deployment: when a trigger event fires, the workflow retrieves the customer's history, generates a targeted follow-up message, schedules it within your defined window, delivers it, and logs the outcome in Max Activity.
When to use this
Your team has strong initial conversations but loses deals during the follow-up gap.
Reps send follow-ups inconsistently — some same day, some never.
You need follow-up to reference specific conversation details so it doesn't feel automated.
You want to track whether follow-ups were sent and whether they generated replies.
System components
Studio workflow triggered on CRM Deal stage change, conversation end, or scheduled wait after an event.
CRM Deal record: stage, last note, owner, product interest, close date.
CRM Person record: name, phone, language preference, last conversation snippet.
AI message drafting agent: generates a personalized follow-up referencing the specific conversation context.
Wait node: enforces send timing (e.g., 4 hours after meeting, 24 hours after proposal).
Channels: WhatsApp Send Message for delivery.
Max Activity: follow-up sent timestamp, message preview, reply received or not, next action.
Step-by-step implementation
1. Identify the trigger moments that require follow-up: meeting held, proposal sent, demo completed, no reply after 48 hours.
2. Create a Studio workflow for each trigger type. Start with the most common one — 'proposal sent' is a reliable starting point.
3. Set the trigger: Deal stage changes to 'Proposal Sent'. Retrieve the Deal, linked Person, and last conversation.
4. Add a Wait node. Set delay: 24 hours (adjust based on your sales cycle).
5. Add an AI drafting agent node. Pass: person name, deal name, proposal topic, language preference, any open question from the last conversation.
6. Instruct the agent to draft a WhatsApp follow-up: max 3 sentences, reference the specific proposal, include one clear question.
7. Add a Send Message node (Channels: WhatsApp). Use the drafted message.
8. Add a Wait node for reply. Wait up to 72 hours.
9. Reply branch: classify intent, update Deal, write Max Activity with reply summary.
10. No-reply branch: create a Max Task for the owner to follow up personally. Write Max Activity noting no reply received.
11. Repeat for each follow-up trigger. Keep workflows independent so they don't conflict.
Agent prompt
You are writing a sales follow-up WhatsApp message after a proposal was sent.
You will receive: the customer's name, the deal or proposal topic, the main question or concern from the last conversation, and the customer's preferred language.
Write a message that: starts with the customer's name, references the specific proposal or conversation topic, ends with one clear and easy-to-answer question.
Maximum 3 sentences. No generic phrases like 'just following up' or 'hope this email finds you well'.
Output only the message text in the customer's preferred language.
Workflow logic
Proposal stage, Day 1: send personalized follow-up with AI-drafted message.
Proposal stage, Day 4 (no reply): send second follow-up with slightly different angle — reference a benefit or answer a likely objection.
Proposal stage, Day 8 (no reply): write Max Task for owner — personal call required. Stop automated messages.
Reply received (any stage): stop follow-up sequence, update Deal based on reply intent, write Max Activity.
Deal moved to another stage by owner: cancel pending follow-up tasks. Do not send stale messages.
Final operating state
Every proposal send triggers a follow-up sequence automatically. Reps don't need to remember to follow up.
Follow-up messages reference the specific proposal or conversation topic — they read like personal messages, not templates.
Max Activity shows: message sent, reply received or not, next action, and whether the owner intervened.
Owners only get Max Tasks when automation has exhausted its sequence and human contact is needed.
Troubleshooting
Message content too generic: pass the proposal title, main benefit, and any specific question from the last conversation to the agent node.
Messages sent at wrong time: check the Wait node configuration — verify timezone and delay calculation.
Duplicate follow-ups: ensure only one follow-up workflow is active per deal. Add a check: if a follow-up was already sent in the last N days, skip.
Owner receiving Max Tasks even when customer replied: verify the reply detection branch is correctly linked and that the no-reply branch only fires after the Wait node times out.
Operational playbook
Use Follow-up workflows as part of the Frontline Solutions Sales operating loop: inspect the current product state, confirm the source context, and decide what should happen next.
The goal is not to memorize screens. The goal is to understand how the product surface supports repeatable work, AI assistance, and accountable handoff.
Best practices
Start with the operational job before changing configuration. Name the owner, define the trigger or source context, and decide how the result should be reviewed.
Prefer narrow, inspectable setups over broad automation. Teammates should be able to explain why the system took an action from the visible product state.
Platform layers involved
Studio defines the workflow and AI agent behavior. Channels capture the customer interaction. CRM provides customer memory. Max Activity shows what the system did and what needs follow-up.
Use the solution page as the business-facing map, then open the related product tutorials when you need configuration detail.
Outcome metrics
Track a small set of operational signals: response time, handoff rate, completion rate, escalation quality, CRM field completeness, reply rate, and repeated failure patterns.
The metric should reflect the business outcome, not only whether the automation ran.
Agent Builder visual map
FAQs
What does Follow-up workflows teach?
Create follow-up workflows that combine reminders, WhatsApp or email messages, CRM context, and Max tasks.
How should teams use this lesson?
Use it as an implementation guide: create the assets, connect the systems, verify the completed state, and operate the blueprint with review gates.
Which Frontline products are involved in this solution?
Most solution playbooks connect Studio workflows, Channels, CRM records, AI agents, and Max Activity. The business outcome is the entry point; the platform layers make it operational.
How should we decide whether to automate this use case?
Automate when the path is repeated, has clear source context, needs consistent follow-up, or benefits from AI classification, routing, summaries, or structured capture. Keep human review where judgment or risk is high.
What should be visible before this goes live?
Verify the workflow trigger, CRM context, channel permissions, AI agent instructions, handoff owner, logs, and Max Activity output so the team can trace what happened.
How do we keep the customer experience personal?
Use CRM context, conversation history, and approved message patterns. AI should use relevant customer memory, not generic copy, and workflows should escalate when context is missing.
What is the best first version of this playbook?
Start with one channel, one workflow, one owner group, and a narrow success metric. Expand only after logs, activity, and customer-facing outputs are trustworthy.