How Account Health Intelligence Agent Scores Accounts

Your support team closed 340 tickets last week. Average resolution time: 4.2 hours. But 23 of those tickets were escalations that sat for 6+ hours before anyone noticed the SLA clock. A team lead spends 1–2 hours daily pulling reports from Hubspot, Slack, cross-referencing with CRM data, and writing up findings. By the time the analysis is done, the queue has moved on.

The result is reactive support instead of proactive operations. SLA risks surface after the breach. Routing problems persist because nobody has time to audit the rules. Agent coaching happens based on gut feel, not pattern data. Account Health Intelligence Agent automates the customer intelligence and account management workflow, delivering structured analysis from Hubspot, Slack data without manual report-building.

Three Agents. Weekly Cadence. Health Brief for Every Account.

The Account Health Intelligence Agent pipeline runs 3 agents in sequence. Assembler pulls data from Hubspot and Slack, and Formatter delivers the output. Here is what happens at each stage and why it matters.

• Assembler (HTTP + Code): Weekly scheduled trigger pulls account data from HubSpot: companies, associated deals (open and closed), support tickets, engagement history (emails, calls, meetings), and contact activity.
• Analyst (Tier 1 Reasoning): Single the analysis model call receives the pre-aggregated account data and assigns one of four health statuses: HEALTHY (active engagement, deals progressing), AT_RISK (engagement drop, open tickets, deal stalls), GROWING (increasing engagement, expansion signals, upsell activity), or CHURNING (no activity, multiple tickets, lost deals).
• Formatter (HTTP): Routes output based on health status.

When the pipeline completes, you get structured output that is ready to act on. The blueprint bundle includes everything needed to deploy, configure, and customize the workflow:

• ITP-tested 24-node n8n workflow — import and deploy
• Weekly automated health assessment for every HubSpot account
• 4-status health taxonomy: HEALTHY, AT_RISK, GROWING, CHURNING — with evidence chains
• the analysis model analysis at $0.014/account — cheapest per-unit cost in the catalog
• Slack alerts for AT_RISK and GROWING accounts only (noise filtering)
• HubSpot company notes for all accounts (full audit trail)
• CS lifecycle integration: COIA onboards → AHIA monitors → ERD catches expansion
• ITP test results with 20 records and 14/14 milestones

SLA thresholds, escalation rules, and routing logic are configurable in the system prompts — customize for your ticket volume and priority structure. This means Account Health Intelligence Agent adapts to your specific process, terminology, and integration requirements without forking the entire workflow.

Understanding how the pipeline works helps you customize it for your environment and troubleshoot issues when they arise. Here is a step-by-step walkthrough of the Account Health Intelligence Agent execution flow.

Step 1: Assembler

Tier: HTTP + Code

The pipeline starts here. Weekly scheduled trigger pulls account data from HubSpot: companies, associated deals (open and closed), support tickets, engagement history (emails, calls, meetings), and contact activity. Pre-computes engagement velocity, ticket resolution rates, deal pipeline coverage, and activity recency per account. All metrics computed in code before the LLM call — no token waste on raw API payloads.

This stage ensures all downstream agents receive clean, validated input. If this step returns incomplete data, every downstream agent works with a degraded picture.

Step 2: Analyst

Tier: Tier 1 Reasoning

Single the analysis model call receives the pre-aggregated account data and assigns one of four health statuses: HEALTHY (active engagement, deals progressing), AT_RISK (engagement drop, open tickets, deal stalls), GROWING (increasing engagement, expansion signals, upsell activity), or CHURNING (no activity, multiple tickets, lost deals). Each assessment includes an evidence chain citing the specific data points that drove the classification. Not a score — a reasoned status with explanation.

Why this step matters: This is where the pipeline applies judgment — not just data retrieval, but analysis.

Step 3: Formatter

Tier: HTTP

This is the final deliverable — what lands in your inbox or dashboard. Routes output based on health status. Slack alerts fire only for AT_RISK and GROWING accounts — noise filtering keeps the channel actionable. All accounts (including HEALTHY and CHURNING) get a HubSpot company note logged with the full health brief and evidence chain for audit trail. CS managers see only the accounts that need attention in Slack, while the complete record lives in HubSpot.

The entire pipeline executes without manual intervention. From trigger to output, every decision point follows a documented path. Every execution produces a traceable audit trail.

All nodes have been validated during Independent Test Protocol (ITP) testing on n8n v2.7.5. The error handling matrix in the bundle documents the recovery path for each failure mode.

Webhooks send event_id, Calendar sends id, test fixtures send record_id. Three input sources, three different field names for the same concept. We detect format by field presence, not flags or configuration. If event_id exists, it is webhook format. If id exists without event_id, it is calendar format. No ambiguity.

— ForgeWorkflows Engineering

Every metric is ITP-measured. The Account Health Intelligence Agent assembles HubSpot CRM data, classifies account health with the analysis model, and delivers weekly briefs at $0.014/account — the cheapest per-unit cost in the catalog.

The primary operating cost for Account Health Intelligence Agent is the per-execution LLM inference cost. Based on Independent Test Protocol (ITP) testing, the measured cost is: Cost per Account: $0.014/account (ITP-measured average). This figure includes all API calls across all agents in the pipeline — not just the primary reasoning step, but every classification, scoring, and output generation call.

To put this in context, consider the manual alternative. A skilled team member performing the same work manually costs $40–60/hour for a support team lead’s analysis time at a fully loaded rate (salary, benefits, tools, overhead). If the manual version of this workflow takes 1–2 hours daily, the per-execution cost in human labor is significant. The blueprint executes the same pipeline for a fraction of that cost, with consistent quality and zero fatigue degradation.

Infrastructure costs are separate from per-execution LLM costs. You will need an n8n instance (self-hosted or cloud) and active accounts for the integrated services. The estimated monthly infrastructure cost is <$4/month (50 accounts/week), depending on your usage volume and plan tiers.

Quality assurance: Blueprint Quality Standard (BQS) audit result is 12/12 PASS. ITP result is 20 records, 14/14 milestones PASS. These are not marketing claims — they are test results from structured inspection protocols that you can review in the product documentation.

All cost and performance figures are ITP-measured — tested against real data fixtures on n8n v2.7.5 in March 2026. See the product page for full test methodology.

9 files — workflow JSON, system prompt, configuration guides, and complete documentation.

When you purchase Account Health Intelligence Agent, you receive a complete deployment bundle. This is not a SaaS subscription or a hosted service — it is a set of files that you own and run on your own infrastructure. Here is what is included:

• CHANGELOG.md — Version history
• README.md — Setup and configuration guide
• account_health_intelligence_agent_v1.0.0.json — n8n workflow (main pipeline)
• docs/TDD.md — Technical Design Document
• system_prompts/analyst_system_prompt.md — Analyst system prompt

Start with the README.md. It walks through the deployment process step by step, from importing the workflow JSON into n8n to configuring credentials and running your first test execution. The dependency matrix lists every required service, API key, and estimated cost so you know exactly what you need before you start.

Every file in the bundle is designed to be read, understood, and modified. There is no obfuscated code, no compiled binaries, and no phone-home telemetry. You get the source, you own the source, and you control the execution environment.

Account Health Intelligence Agent is built for Customer Success teams that need to automate a specific workflow without building from scratch. If your team matches the following profile, this blueprint is designed for you:

• You operate in a customer success function and handle the workflow this blueprint automates on a recurring basis
• You have (or are willing to set up) an n8n instance — self-hosted or cloud
• You have active accounts for the required integrations: HubSpot (any plan with API access), Slack workspace
• You have API credentials available: Anthropic API, HubSpot API, Slack Bot Token
• You are comfortable importing a workflow JSON and configuring API keys (the README guides you, but basic technical comfort is expected)

This is NOT for you if:

• Does not predict churn — classifies current health status based on CRM data signals
• Does not modify HubSpot deals or tickets — read-only CRM access for data, write-only for company notes
• Does not replace CS playbooks — surfaces which accounts need attention, not what action to take
• Does not work with Salesforce, Pipedrive, or other CRMs — HubSpot only
• Does not send email alerts — delivers to Slack with HubSpot notes for audit trail

Review the dependency matrix and prerequisites before purchasing. If you are unsure whether your environment meets the requirements, contact support@forgeworkflows.com before buying.

Every pipeline has boundaries. These are intentional design decisions, not oversights — understanding them helps you deploy with the right expectations and plan for edge cases in your environment.

Does not predict churn — classifies current health status based on CRM data signals

This is intentional. We default to human-in-the-loop for actions that carry reputational or financial risk. Once your team has validated output accuracy over 20+ cycles, you can adjust the pipeline to auto-execute — the workflow JSON supports it, but the default is conservative.

Does not modify HubSpot deals or tickets — read-only CRM access for data, write-only for company notes

We scoped this boundary after ITP testing revealed inconsistent results when the pipeline attempted this. The agents handle what they handle well — extending beyond this scope requires custom prompt engineering specific to your data shape.

Does not replace CS playbooks — surfaces which accounts need attention, not what action to take

This keeps the pipeline focused on a single workflow. Adding this capability would introduce branching logic that varies by organization, and the tradeoff between complexity and reliability was not worth it for a reusable blueprint. Fork the workflow JSON if your use case demands it.

Deployment follows a structured sequence. The Account Health Intelligence Agent bundle is designed for the following tools: n8n, Anthropic API, HubSpot, Slack. Here is the recommended deployment path:

1. Step 1: Import workflow and configure credentials. Import account_health_intelligence_agent_v1_0_0.json into n8n. Configure HubSpot API key (with companies, deals, tickets, engagements scopes), Anthropic API key, and Slack Bot Token (HTTP Header Auth, Authorization: Bearer xoxb-YOUR-TOKEN) with chat:write scope.
2. Step 2: Configure HubSpot company associations and Slack channel. Verify your HubSpot companies have associated deals, tickets, and engagement records. Set the target Slack channel for health alerts. Review the health taxonomy reference for threshold guidance.
3. Step 3: Activate and verify. Enable the workflow in n8n. Trigger manually for your first health assessment run. Verify Slack alerts appear for AT_RISK and GROWING accounts. Check HubSpot company notes for all assessed accounts.

Before running the pipeline on live data, execute a manual test run with sample input. This validates that all credentials are configured correctly, all API endpoints are reachable, and the output format matches your expectations. The README includes test data examples for this purpose.

Once the test run passes, you can configure the trigger for production use (scheduled, webhook, or event-driven — depending on the blueprint design). Monitor the first few production runs to confirm the pipeline handles real-world data as expected, then let it run.

For technical background on how ForgeWorkflows blueprints are built and tested, see the Blueprint Quality Standard (BQS) methodology and the Inspection and Test Plan (ITP) framework. These documents describe the quality gates every blueprint passes before listing.

Ready to deploy? View the Account Health Intelligence Agent product page for full specifications, pricing, and purchase.