Prospect List Builder

Adam's take

Nobody demos list building at a conference, but bounced emails and missing personas tax every sequence you run.

Required tools

Optional tools

Expected value

Review-ready prospect lists in minutes instead of hours; fewer bounces

Deployable workflow pack

The full pack includes the agent spec, deployment guide, architecture diagrams, n8n workflow skeleton, Clay template, HubSpot properties, JSON schemas, OpenAPI spec, cost and ROI calculators, demo data, QA checklist, and governance notes.

How to deploy this agent

"Find me a VP of RevOps at these 40 accounts" is an hour of manual sourcing, then another hour catching duplicates and bounced emails afterward. This agent wires the actual gap — the specific persona a target account is missing — to a sourced, validated, review-ready contact list, instead of a generic name export.

Core signals

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deploytheagent.com/schemas/agent-005-input.schema.json",
  "title": "Agent #005 Prospect List Builder Input",
  "type": "object",
  "required": [
    "record_id"
  ],
  "properties": {
    "record_id": {
      "type": "string",
      "description": "CRM record ID (company/contact/deal depending on agent)."
    },
    "domain": {
      "type": "string"
    },
    "config_version": {
      "type": "string",
      "description": "Versioned config used for this run."
    }
  },
  "additionalProperties": true
}

Output schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deploytheagent.com/schemas/agent-005-output.schema.json",
  "title": "Agent #005 Prospect List Builder Output",
  "type": "object",
  "required": [
    "record_id",
    "prospect_relevance_score",
    "prospect_source",
    "prospect_duplicate_flag",
    "prospect_approval_status"
  ],
  "properties": {
    "record_id": {
      "type": "string"
    },
    "prospect_relevance_score": {
      "type": "string",
      "description": "Agent #005 output field."
    },
    "prospect_source": {
      "type": "string",
      "description": "Agent #005 output field."
    },
    "prospect_duplicate_flag": {
      "type": "string",
      "description": "Agent #005 output field."
    },
    "prospect_approval_status": {
      "type": "string",
      "description": "Agent #005 output field."
    }
  },
  "additionalProperties": false
}

Scoring / classification logic

Relevance score is the product of persona-match weight and deliverability weight, capped 0–100. Candidates below a configured relevance floor (default 40) aren’t surfaced at all — the review list stays high-signal instead of exhaustive, so SDRs aren’t wading through weak matches.

HubSpot CRM properties

n8n workflow skeleton

The Prospect List Builder sources persona-specific contacts for the buying-committee gaps Agent #002 finds, validates and dedupes them, and hands SDRs a review-ready list instead of a raw export from a sourcing tool. Configure every node marked CONFIGURE before enabling the trigger.

1. Trigger
   CONFIGURE: set cadence per agent-spec.md's What It Does section. Leave disabled until Step 6 of deployment-guide.md.
2. Load versioned config
   CONFIGURE: replace with your versioned config built from real data (see deployment-guide.md Step 1).
3. Fetch source data
   CONFIGURE: {{HUBSPOT_CREDENTIAL}}. Pull the fields listed in agent-spec.md's Inputs table.
4. Validate + gate records
   Drops records missing required inputs or failing suppression/gate checks defined in agent-spec.md. Logs every drop.
5. Apply workflow logic
   Implements the Workflow Logic table from agent-spec.md. Writes model/config version alongside every derived value for auditability.
6. Write agent-owned CRM fields
   CONFIGURE: {{HUBSPOT_CREDENTIAL}}. Writes only: prospect_relevance_score, prospect_source, prospect_duplicate_flag, prospect_approval_status. Never writes sales-owned fields.
7. Route to human review / alert
   CONFIGURE: {{SLACK_CHANNEL}}. Fires for records requiring human review per agent-spec.md's Governance section.

Cost calculator

ROI calculator

Governance notes

• The agent never creates a CRM contact without explicit human approval in the review list — sourcing and CRM creation are two separate steps by design.
• Suppressed and unsubscribed individuals are never sourced or surfaced, full stop, regardless of how good a persona match they might otherwise be.
• Every candidate stores its source (Clay, Apollo, Sales Navigator) and relevance score, so a reviewer can see why a name showed up.
• Batch size matters for adoption, not just cost — small batches keep the human review step from becoming a backlog nobody clears.

Failure modes

• Contacts created without review: the workflow deliberately has no contact-create node — creation only happens through a separate, manually-triggered approved-list flow.
• Suppressed contact sourced anyway: the suppression check is the first node in the pipeline, not the last, specifically to prevent this.
• Low-relevance candidates flooding the list: a QA test asserts nothing below the configured relevance floor ever appears in the output.
• Rubber-stamp approvals: if SDRs start approving without reading, that’s a signal the relevance scoring needs to be tighter — not a reason to skip the review step.

QA checklist

FAQ

Related agents