Buying Committee Mapper

Adam's take

Single-threading kills more deals than pricing does. This one pays for itself the first time a champion goes quiet and you already know who else to call.

Required tools

Optional tools

Expected value

Reduces single-threaded deal risk; earlier multi-threading

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

Single-threaded deals are one of the most common, and most preventable, causes of lost or stalled opportunities. This agent classifies every known contact at a target account into a buying role, scores committee coverage, and flags gaps before a deal stalls.

Core signals

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deploytheagent.com/schemas/agent-002/input.schema.json",
  "title": "Buying Committee Mapper — Input",
  "description": "One contact record on a target account entering classification. Identity fields required; enrichment and engagement may be null.",
  "type": "object",
  "required": ["account_domain", "contact_id", "full_name", "is_target_account"],
  "additionalProperties": false,
  "properties": {
    "account_domain": { "type": "string" },
    "contact_id": { "type": "string", "description": "HubSpot contact ID, or 'sourced:<provider>:<ref>' for candidates not yet in CRM" },
    "full_name": { "type": "string", "minLength": 1 },
    "email": { "type": ["string", "null"] },
    "job_title": { "type": ["string", "null"] },
    "department": { "type": ["string", "null"] },
    "seniority": { "type": ["string", "null"], "enum": ["c_level", "vp", "director", "manager", "ic", "owner", null] },
    "is_target_account": { "type": "boolean", "description": "Gate: only true records are processed" },
    "is_sourced": { "type": "boolean", "default": false, "description": "True when the contact came from Apollo/Sales Nav and does not exist in CRM yet" },
    "unsubscribed": { "type": "boolean", "default": false },
    "engagement": {
      "type": "object",
      "additionalProperties": false,
      "properties": {
        "replies_90d": { "type": ["integer", "null"], "minimum": 0 },
        "meetings_90d": { "type": ["integer", "null"], "minimum": 0 },
        "last_activity_date": { "type": ["string", "null"], "format": "date" },
        "rep_flagged_objection": { "type": "boolean", "default": false }
      }
    }
  }
}

Output schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deploytheagent.com/schemas/agent-002/output.schema.json",
  "title": "Buying Committee Mapper — Output",
  "description": "Contact-level classification plus account-level coverage. Champion/Blocker appear only as candidate_* pending human confirmation; the rules engine may not emit them as confirmed roles.",
  "type": "object",
  "required": ["contacts", "account"],
  "additionalProperties": false,
  "properties": {
    "contacts": {
      "type": "array",
      "items": {
        "type": "object",
        "required": ["contact_id", "buying_committee_role", "buying_role_confidence", "buying_role_model_version", "review_required"],
        "additionalProperties": false,
        "properties": {
          "contact_id": { "type": "string" },
          "buying_committee_role": {
            "type": "string",
            "enum": [
              "economic_buyer",
              "technical_buyer",
              "user_buyer",
              "influencer",
              "unknown",
              "candidate_champion",
              "candidate_blocker"
            ],
            "description": "Confirmed 'champion' and 'blocker' values are written only by the human review workflow, never by this agent"
          },
          "buying_role_confidence": { "type": "number", "minimum": 0, "maximum": 1 },
          "buying_role_model_version": { "type": "string" },
          "classification_basis": { "type": "string", "description": "Which rule or signal produced the role, for audit" },
          "review_required": { "type": "boolean", "description": "True for candidates and sourced contacts" },
          "unreachable": { "type": "boolean", "default": false, "description": "Unsubscribed; mapped for completeness, excluded from outreach suggestions" }
        }
      }
    },
    "account": {
      "type": "object",
      "required": ["account_domain", "committee_coverage_score", "committee_gaps", "single_threaded_risk", "committee_scan_date"],
      "additionalProperties": false,
      "properties": {
        "account_domain": { "type": "string" },
        "committee_coverage_score": { "type": "integer", "minimum": 0, "maximum": 100 },
        "committee_gaps": {
          "type": "array",
          "items": { "type": "string", "enum": ["economic_buyer", "champion", "technical_buyer", "user_buyer"] }
        },
        "single_threaded_risk": { "type": "boolean" },
        "committee_scan_date": { "type": "string", "format": "date" },
        "engaged_contacts_90d": { "type": "integer", "minimum": 0 }
      }
    }
  }
}

Scoring / classification logic

Confirmed roles weigh 1.0 toward committee coverage; candidates and sourced-but-unconfirmed contacts weigh 0.5. An account is flagged single-threaded risk when two or fewer contacts have engaged in the last 90 days, independent of total contact count.

HubSpot CRM properties

n8n workflow skeleton

Weekly committee mapping: pull contacts on target accounts, classify buying roles by rule, detect champion/blocker candidates from engagement, score coverage, write agent-owned HubSpot fields, queue reviews. Configure every node marked CONFIGURE.

1. Weekly mapping trigger
   CONFIGURE: default Tuesday 06:00 (after Agent #001's Monday scan). Add a webhook trigger for on-approval mapping if #001 is live.
2. Load role-mapping config
   CONFIGURE: replace with your versioned role config built from real closed-won deals. Version string flows to buying_role_model_version.
3. Fetch contacts on target accounts
   CONFIGURE: {{HUBSPOT_CREDENTIAL}}. Pull contacts on companies where icp_match_band = Target (or your manual target list). Include title, department, seniority, engagement, marketable status.
4. Fetch sourced candidates from Clay
   CONFIGURE: Clay table export URL + {{CLAY_API_KEY}}. Sourced rows carry contact_id 'sourced:<provider>:<ref>' and is_sourced=true. Only sourced for accounts with committee_gaps.
5. Validate + gate target accounts
   Drops non-target-account rows and structurally invalid rows; logs drops.
6. Classify buying roles
   Rules-first classification. Champion/blocker emitted only as candidate_* from engagement signals; this node cannot output confirmed champion/blocker. LLM fallback for unmatched titles goes here if enabled (store prompt version in model_version).
7. Score committee coverage
   Confirmed roles weigh 1.0, candidates and sourced weigh 0.5. Gaps = required roles with no confirmed contact. Single-threaded when <=1 engaged contact in 90d.
8. Write contact fields (CRM contacts only)
   CONFIGURE: writes buying_committee_role, buying_role_confidence, buying_role_model_version for contacts whose contact_id is a HubSpot ID. Sourced contacts are NEVER written here; they go to the review queue.
9. Write company coverage fields
   CONFIGURE: writes committee_coverage_score, committee_gaps, single_threaded_risk, committee_scan_date.
10. Queue reviews (sourced + candidates)
    CONFIGURE: {{SLACK_CREDENTIAL}}, channel #committee-review. Lists sourced contacts pending CRM approval and champion/blocker candidates pending confirmation. Confirmation happens in HubSpot by a human; this workflow never creates contacts or confirms roles.
11. Alert single-threaded Targets
    CONFIGURE: channel. Posts Target accounts with single_threaded_risk=true and their gaps.
12. Write run log
    Audit: run date, config version, role distribution, review queue size. Alert if influencer share of classified contacts >40% (loose config symptom).

Agent-driven Clay integration (optional)

The default deployment path pulls Clay data through a static export URL, shown above. Teams already running Clay through its official CLI/MCP (clay-run/agent-plugins) can use this agent-driven path instead.

Cost calculator

ROI calculator

Governance notes

• Champion and Blocker are never confirmed by the workflow itself — only surfaced as candidates for a human to confirm in HubSpot.
• Sourced-but-unconfirmed contacts are never written to CRM contact records directly; they route to a review queue instead.
• Every classification stores a config version and a plain-language basis (which rule or behavioral signal fired) for auditability.
• The agent does not contact anyone directly — it surfaces coverage gaps and lets a human decide how to fill them.

Failure modes

• Sparse contact data: an account with only one or two known contacts can’t be meaningfully mapped — flagged for manual contact sourcing (Agent #005) rather than forced into a classification.
• Rule-only classification without engagement data produces lower-confidence results, written as such.
• Loose config symptom: if influencer classifications exceed roughly 40% of contacts, that indicates the role config is too broad and needs retuning.
• Role drift: classification re-runs on a schedule rather than treating a role as a permanent, one-time label.

QA checklist

FAQ

Related agents