Lead capture
Capture leads from channels and campaigns with structured fields, CRM records, AI qualification, and sales handoff.
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.
Customer signalWorkflow pathVisible outcomeThis is the state to compare against when the system is configured, connected, or ready for review.
Summary
Capture leads from channels and campaigns with structured fields, CRM records, AI qualification, and sales handoff.
Concepts covered
Step breakdown
- Define the system to deployStart from this Marketing 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 lead capture system that extracts structured data from WhatsApp conversations, Instagram DMs, and form submissions; creates CRM Person and Deal records with captured fields; and routes each lead to the correct next step based on captured data.
After deployment: a prospect arrives on any channel. Frontline asks for the required fields conversationally, validates key identifiers (phone, email, company), creates the CRM record, and routes to qualification or a sales owner — no manual data entry.
When to use this
Inbound leads are arriving on WhatsApp or Instagram but information is inconsistent and incomplete.
Your sales team receives leads without the basic fields needed to qualify or route them.
Form submissions go to email but don't automatically create CRM records.
You want to standardize what information is captured before a lead reaches a human.
System components
Channels: WhatsApp and Instagram as the primary capture channels.
AI capture agent: conducts a short, structured intake conversation to collect required lead fields.
CRM Person record: name, phone, email, company, role, source, intent.
CRM Company record: created or matched based on domain or name.
CRM Deal record: created with stage = 'New Lead' once required fields are captured.
Validation logic: confirms phone format, email format, and required fields are present before creating records.
Conditional Routing: complete capture → qualification or owner handoff; incomplete → follow-up for missing fields.
Max Activity: captured fields, validation outcome, record created, routing decision.
Step-by-step implementation
1. Define the minimum required fields for a lead to enter your pipeline: name, phone, company, and one intent indicator (what are they interested in).
2. Create a Studio workflow. Trigger: new WhatsApp or Instagram DM.
3. Add Person lookup by phone. If found (returning contact): skip capture, go to qualification. If not found: start capture.
4. Add AI capture agent node. Instruct it to collect required fields conversationally — one field at a time, not a form dump.
5. After each reply, extract the field value. Validate format if applicable (phone digits, email @-sign).
6. Add a completeness check. If all required fields are captured: proceed to record creation. If any required field is missing: ask the follow-up question.
7. Create Person record with captured fields. Link to Company (lookup by domain or create new). Create Deal at stage 'New Lead'.
8. Add Conditional Routing: if captured intent signals high qualification → route to AI SDR or sales owner. If low intent → route to nurture.
9. Write Max Activity: fields captured, validation results, records created, routing decision.
10. Test with a real conversation. Send fragmented information across multiple messages. Verify all required fields are captured and CRM records appear.
Agent prompt
You are a lead intake agent. Your job is to collect basic information from a new prospect in a friendly, natural way.
Required fields to collect: full name, company or organization, their role, and what they are looking for (their main goal or challenge).
Collect fields one at a time. Do not ask multiple questions in one message. Start by greeting them and asking their name.
If they volunteer information without being asked, capture it and move to the next missing field.
Output after each exchange: { collected_fields: { name: string | null, company: string | null, role: string | null, intent: string | null }, missing_fields: string[], next_question: string | null, capture_complete: boolean }.
Workflow logic
Final operating state
Every lead from WhatsApp or Instagram results in a CRM Person record with standardized fields — no free-text notes replacing structured data.
Deal records are created at stage 'New Lead' with intent captured at the time of contact.
Max Activity shows: channel source, captured fields, validation outcome, and routing decision for every lead.
Sales owners receive only leads where required fields are captured — incomplete leads are held until capture is complete.
Troubleshooting
Agent asking too many questions at once: the prompt must explicitly say 'one field at a time'. Also limit the number of required fields — start with 3 maximum.
Duplicate Person records created: add a pre-creation check — search by phone AND by name+company before creating a new record.
Company record not being created: verify the Company lookup step uses the correct identifier (domain extracted from email, or company name as free text).
Capture stalls after first message: verify the workflow is waiting for the next reply before advancing to the next capture step. Check the Wait node or conversation loop configuration.
Operational playbook
Use Lead capture as part of the Frontline Solutions Marketing 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 Lead capture teach?
Capture leads from channels and campaigns with structured fields, CRM records, AI qualification, and sales handoff.
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.