Weekly Revenue Brief Agent

Adam's take

Write the brief from data or don't write it. The first invented metric in an exec summary costs you every future one.

Required tools

Optional tools

Expected value

Saves 3-5 leadership hrs/week; consistent revenue cadence

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

Leadership cadence runs on a weekly summary somebody has to manually assemble from four or five sources — pipeline reports, win/loss notes, routing SLA spreadsheets, hygiene reviews. This agent assembles the same ten sections automatically from data the CRM and other agents already produced — and leaves a section blank with a note rather than ever inventing a number to fill a gap.

Core signals

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deploytheagent.com/schemas/agent-010-input.schema.json",
  "title": "Agent #010 Weekly Revenue Brief 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-010-output.schema.json",
  "title": "Agent #010 Weekly Revenue Brief Agent Output",
  "type": "object",
  "required": [
    "record_id"
  ],
  "properties": {
    "record_id": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

Scoring / classification logic

Every section follows one rule: if a figure is sourced, it’s shown with its source; if it’s partially available, the available parts show and the rest is marked "not tracked"; if there’s no source at all, the section is left blank with an explicit note rather than filled with an estimate. This is the single hardest rule in the whole agent library to enforce, because a model asked to "summarize the week" will happily estimate a plausible-sounding number if it isn’t explicitly stopped.

n8n workflow skeleton

The Weekly Revenue Brief Agent compiles pipeline movement, wins/losses, forecast risk, high-intent accounts, routing SLA performance, and pipeline hygiene into one executive summary every week — using only data the other agents and CRM already produced, never inventing a number to fill a gap. 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: see agent-spec.md. 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

• Never invents a metric — the defining rule of this agent. Every number traces to a source system or an upstream agent’s output.
• A section with no available source renders as explicitly unavailable, never as a guessed or extrapolated figure.
• Writes only to the published brief document — it doesn’t write back to any CRM record.
• The "questions for leadership" section is a structural requirement, not a nice-to-have, forcing risks to surface instead of going unspoken.

Failure modes

• A metric gets fabricated to fill a blank section: prevented by requiring a source citation per figure in the generation prompt, verified by a QA test using intentionally missing source data that must render as "unavailable," not a number.
• The brief goes stale or fails to publish: a delivery-confirmation check in the workflow alerts the owner if publishing fails.
• The questions-for-leadership section is empty filler every week: caught by a manual QA read for genuine substance, not just a check that the section exists.
• A figure gets attributed to the wrong source in a multi-agent merge: every populated figure includes its source agent or system inline, so misattribution is visible on sight.

QA checklist

FAQ