Account Fit Scoring Agent

Adam's take

Scoring is where teams get religious. Keep the weights in a config file so the argument happens in version control instead of a meeting.

Required tools

Optional tools

Expected value

Objective prioritization; removes opinion-based account selection

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

Every team already has an opinion about which accounts matter — marketing chases traffic, sales chases deal size, CS chases renewal risk. This agent replaces four competing opinions with one weighted, versioned score: fit, commercial value, readiness, and engagement, rolled into a single defensible priority number.

Core signals

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deploytheagent.com/schemas/agent-003-input.schema.json",
  "title": "Agent #003 Account Fit Scoring Agent 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-003-output.schema.json",
  "title": "Agent #003 Account Fit Scoring Agent Output",
  "type": "object",
  "required": [
    "record_id",
    "account_fit_score",
    "account_commercial_value_score",
    "account_readiness_score",
    "account_engagement_score",
    "account_priority_score",
    "account_score_model_version",
    "account_score_date"
  ],
  "properties": {
    "record_id": {
      "type": "string"
    },
    "account_fit_score": {
      "type": "string",
      "description": "Agent #003 output field."
    },
    "account_commercial_value_score": {
      "type": "string",
      "description": "Agent #003 output field."
    },
    "account_readiness_score": {
      "type": "string",
      "description": "Agent #003 output field."
    },
    "account_engagement_score": {
      "type": "string",
      "description": "Agent #003 output field."
    },
    "account_priority_score": {
      "type": "string",
      "description": "Agent #003 output field."
    },
    "account_score_model_version": {
      "type": "string",
      "description": "Agent #003 output field."
    },
    "account_score_date": {
      "type": "string",
      "description": "Agent #003 output field."
    }
  },
  "additionalProperties": false
}

Scoring / classification logic

The final priority score is a weighted sum of the four sub-scores, rounded to a whole number, mapped to a tier (default: 80+ Tier 1, 60–79 Tier 2, 40–59 Tier 3, below 40 Tier 4). Accounts younger than 30 days with no engagement history yet are flagged insufficient_data rather than scored to zero — a new account isn’t penalized for being new.

HubSpot CRM properties

n8n workflow skeleton

The Account Fit Scoring Agent scores every account in the CRM against ICP, commercial value, readiness, and engagement, then rolls the four into one account priority score. RevOps and sales leaders get a single, explainable number instead of four teams arguing about which accounts matter. 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: account_fit_score, account_commercial_value_score, account_readiness_score, account_engagement_score, account_priority_score, account_score_model_version, account_score_date. 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

• Weights and tier thresholds change only through a reviewed, versioned config commit — never at runtime, and never for a single pet account.
• The agent never writes to sales-owned fields: deal stage, deal owner, and forecast category are read-only inputs, not outputs.
• Every score stores the config version it was computed under, so a score change is always traceable to a specific, dated config edit.
• Score distribution is checked on every run: if more than roughly 60% of accounts land in a single tier, that’s treated as a miscalibration signal, not a result to trust.

Failure modes

• Flat scoring: if every account lands in the same mid-band tier, the weights are too flat or the thresholds are miscalibrated — caught by the score-distribution check on every run.
• New accounts scored to zero: without the insufficient_data path, brand-new accounts would look like poor fits simply because they haven’t accumulated engagement yet.
• Silent score drift: a score that changes without an explanation is a red flag — every write carries its model/config version so changes are diffable.
• Signal double-counting: readiness and fit sub-scores are configured to draw from mutually exclusive signal sets so a single event doesn’t get counted twice.

QA checklist

FAQ

Related agents