Convoy AI

Process Station · Sales

Lead qualification

CommunityTemplate

Enrich, score and route a lead according to your rules.

The control station, in brief

This station links several tools into one journey. The agent follows the steps in order, and every step goes through the rules below.

Linked toolsCRMEnrichment

It can

  • Enrich a lead
  • Score it
  • Route it to the right team

It asks a human for

  • Nothing in particular

It never has access to

  • Route without a score
  • Send a personal address to enrichment

Scenario Replays

An agent works through the station. Simulated scenarios, no real data, no key required.

Qualify a lead

What you will see: Three steps in order: enrichment never exposes personal data.

Agent connected to the station through MCP
  1. HumanQualify the lead that came from the website this morning.
  2. AgentI'll enrich, score, then route.
  3. MCP callenrichLead(company: "Acme")
  4. StationCompany of 200 people. The address is professional, enrichment allowed.OKRule applied: mask-personal-email
  5. MCP callscoreLead(lead: 4410)
  6. StationScore 78 out of 100.OKRule applied: playbook qualify-a-lead
  7. MCP callrouteLead(lead: 4410, team: "grands-comptes")
  8. StationLead routed to the Key accounts team.OKRule applied: score-before-route
These rules are not yours?

Copy the station, change a limit or an approval step in its configuration file, and get your own station.

Copy and adapt

The configuration in detail

lead-qualification.yamlRead the docs →

Everything the station does fits in this file. The replay above applies it, and a copy starts from it. The values are examples to adapt, not a recommendation.

station:
  id: lead-qualification
  kind: process
  policies:
    - {policy: mask-personal-email, at: submit}
    - {policy: score-before-route, at: submit}

global:
  language: en
  timezone: Europe/Paris

apis:
  - id: crm
    operations:
      scoreLead:           {access: write, risk: low}
      routeLead:           {access: write, risk: medium}
  - id: enrichment
    operations:
      enrichLead:          {access: read}

profiles:
  sdr-assistant:
    allow: [scoreLead, routeLead, enrichLead]

policies:
  mask-personal-email:
    type: rule
    when: "action == enrichLead and email_is_personal"
    effect: deny
    reason: "Personal addresses do not leave the CRM."
  score-before-route:
    type: rule
    when: "action == routeLead and not scored"
    effect: deny
    reason: "A lead is routed only after being scored."

skills:
  - {id: score-lead, uses: scoreLead}
  - {id: route-lead, uses: routeLead}
  - {id: enrich-lead, uses: enrichLead}

playbooks:
  - id: qualify-a-lead
    tasks: [enrich-lead, score-lead, route-lead]

Shared copies

Copies that their authors choose to share will appear here. Each one keeps a link to this original station.