Customer Health Scoring One score per account, weekly, from usage, support and billing
One health score per account, a reason for every drop, and a draft check-in ready before the customer goes quiet.
- Installed for you · one-time$249
- Run for you$297/month
- Custom build · this process$4,500–8,000 one-time
- Starts whenSchedule Trigger (weekly) + event triggers
Covers up to 2,000 accounts across one analytics, one help desk and one CRM. Predictive (ML) churn models trained on your history are a custom build once you have 12+ months of outcome data. Custom builds start at $2,000 site-wide; this band is for this process and its integrations.
Customer Health Scoring is an automation Agentmelt installs in your own tools. The free template is a file you import yourself; the kit ($49) adds the setup guide and prompts. Installed for you costs $249 one-time and is live within two working days of access, with a recorded walkthrough and 30 days of fixes. Run for you costs $297/month, with setup and maintenance included. A custom build of this process is $4,500–8,000 one-time; custom builds start at $2,000 site-wide. No call is needed for any option. Written by Max Zeshut; last revised 2026-09-18.
Reference stack: Claude + n8n. Node names are on each step; the file is under the template.
Founder at Agentmelt
Reviews every build before it goes live; the workflow escalates to a person, never past one.
What is customer health scoring?
A customer health score is one number per account that says how likely the customer is to renew, built from signals you already have: product usage and its trend against the previous eight weeks, support volume and sentiment, billing behaviour, engagement with your team and your emails. Customer health scoring automation collects those components weekly from the analytics, help-desk, billing and CRM tools, turns each into a 0–100 sub-score with thresholds per segment, weights them, stores the history, and alerts the account owner when the score drops — with the two components that moved and a drafted check-in. The score is calibrated quarterly against actual churn, so the weights earn their place.
- Our health score is a colour a CSM sets by feel at the quarterly review.
- Usage lives in the analytics tool, tickets in the help desk, invoices in billing — and nobody joins them.
- We learn a customer is unhappy from the cancellation email.
- The alerts we have fire on everything, so they are ignored.
- The CSM knows the score dropped but not why, or what to say.
If two of these are yours, this is the process to look at first. Free audit — or read on.
What it looks like once it runs.
A customer health score is only useful if it moves before the customer leaves and tells the CSM what to do. The workflow computes one score per account every week from usage trend, support experience, billing behaviour, engagement and sentiment, alerts on drops with the cause, and has an AI agent draft the check-in — so the CSM's day starts with the accounts that need them.
- Monday 6:00 Usage, support, billing and engagement signals are collected for every account.
- 6:10 Each becomes a sub-score; recent tickets are read for frustration, not just volume.
- 6:15 A drop above the threshold, or a score turning red, raises an alert with the two things that changed.
- 6:20 The owner gets the alert with a drafted check-in; the CRM health field and timeline are updated.
Churn surprises. The renewal call reveals the champion left months ago, usage halved in the spring, and three support tickets went badly. All of it was visible in different systems and nobody assembled it.
Every account has a score with a trend and the components behind it. A drop of more than a set number of points in a week alerts the owner with the reason (“admin user inactive 21 days; two negative-sentiment tickets”) and a drafted message. Renewal forecasts stop being a guess because the score is calibrated against actual churn every quarter.
Trigger, then 8 steps.
All eight steps run without anyone; a person sees only what the guardrails escalate.
Schedule Trigger (weekly) + event triggers
Collect the components
Usage (active users, sessions, key actions, trend vs previous 8 weeks), support (ticket volume, sentiment, resolution time), billing (late payments, downgrades), engagement (QBR attendance, email responses), and relationship (champion still active, number of contacts).
Score each component
Each component becomes a 0–100 sub-score with segment-specific thresholds (an enterprise account's normal usage differs from an SMB's). Weights live in a sheet.
Analyse ticket sentiment
Recent tickets are scored for sentiment and frustration markers; a single furious ticket outweighs three neutral ones.
Compute score and trend
Weighted score, 8-week trend, and the top two components that changed. Score history is stored per account.
Detect drops and thresholds
Drop above the threshold, or score crossing into red, creates an alert; accounts already in an active save play are not re-alerted.
Draft the intervention
From the components and the account's history the agent drafts a check-in that names the observed change without sounding like surveillance, and suggests the play (re-onboard a new admin, executive check-in, training session).
Alert the owner and update the CRM
Owner gets the alert with score, cause and draft; the CRM health field and a timeline note are updated so the score is visible in every view.
Calibrate quarterly
Compares scores from 90 days ago to actual churn and downgrades, reports precision/recall by score band, and proposes weight changes for RevOps to approve.
No step waits for a person.
What the workflow hands to someone, by rule:
- Outreach is drafted for a person to send; nothing goes to the customer automatically.
Every account has a score with a trend and the components behind it
Every account has a score with a trend and the components behind it.
No decisions needed. Anything the guardrails flag is handed to a person; the rest ran alone.
Each pattern page explains it in plain words and lists every automation that uses it.
The template is built on n8n (how the n8n AI Agent node works); the same steps run on Make, Zapier or plain code. The tool is chosen to fit your accounts, you own the result, and the template comes in all three formats.
Data it touches
- Product analytics (usage and adoption)
- Help desk tickets and CSAT
- Billing (payment behaviour, plan changes)
- CRM activity and contacts (champion status)
- Meeting and email engagement
Guardrails
- Scores show their components; no black-box number.
- Alerts are suppressed for accounts already in a save play, so CSMs are not double-pinged.
- Outreach is drafted for a person to send; nothing goes to the customer automatically.
- The score is calibrated against real churn quarterly, and the calibration report is visible to leadership.
Health scores fail when they are static
Most health scores are a one-time formula that nobody revisits, so they drift: the score says green while the account churns, and CSMs stop trusting it. Two design choices fix that. The score shows its components, so a CSM can see whether 'red' means usage or sentiment and act accordingly. And the score is calibrated every quarter against what actually happened — how many accounts that were red churned, how many green ones did — with the result reported and the weights adjusted. A score that is measured stays useful.
The champion signal
The single most predictive signal in B2B SaaS is whether the person who bought and championed the product is still there and still active. It is also the one most CRMs cannot see. The workflow checks whether the champion's user account is active and whether their login recency has changed; a deactivated champion drops the relationship component immediately and triggers a play focused on finding and onboarding the replacement. Teams that add only this signal see their surprise churn fall noticeably.
From score to action
The alert is not the point; the play is. Each cause maps to a play: usage drop → training or re-onboarding; support frustration → executive check-in and a ticket review; champion loss → new-admin onboarding; billing trouble → finance-to-finance conversation. The agent's drafted message opens the play with specifics, and the CRM note records which play ran, so calibration can also tell you which plays work.
What it connects to.
| Tool | Role in this workflow |
|---|---|
| n8n | Collection, scoring, alerting, calibration |
| Mixpanel / Amplitude / PostHog | Usage components |
| Zendesk / Intercom | Support components |
| Claude | Sentiment analysis and intervention drafts |
| HubSpot / Salesforce | Score field, alerts, timeline |
Want this running without building it?
$297/month
We set it up in your tools, run it on our servershost it on our n8n cloud (or deploy it to your own n8n, Make or Zapier), watch it, and fix it when something changes. Setup included, cancel monthly; the automation stays yours if you leave.
$4,500–8,000 one-time
Your systems, your rules, your edge cases. A one-off build delivered into your accounts to keepon Claude and n8n, delivered into your accounts to keep, with documentation and a recorded walkthrough.
Covers up to 2,000 accounts across one analytics, one help desk and one CRM. Predictive (ML) churn models trained on your history are a custom build once you have 12+ months of outcome data.
Also sold one-time, installed in your own accounts, as part of the customer success managers package and the customer success teams package — do it yourself $49 · installed for you $249 · done for you $490.
When this becomes a custom build.
The subscription covers the standard version — $297/month, setup and maintenance included. Three things move it to a custom build ($4,500–8,000 one-time), delivered into your accounts to keep. If one of them is you, say so on the audit and the plan prices both.
A predictive model trained on your own churn history — sensible once you have twelve months of outcomes.
More than 2,000 accounts, or health signals from several products, help desks or billing systems.
Interventions that run automatically in your product (in-app messages, plan changes) rather than as drafts for a CSM.
Running the standard version first is the usual path: the exceptions it logs in the first month are the scope of the custom build, with your own numbers. How custom builds work.
Frequently asked questions.
How many data sources do we need?
Usage plus support plus CRM is the minimum that produces a meaningful score. Billing and engagement improve it. Start with what you have; the weights adapt.
Is this a predictive churn model?
It is a calibrated rule-based score, which is what most teams should run first: transparent, tunable, and accurate enough. A trained model needs a year of outcome data and is offered as a custom build once that exists.
Can the score show in HubSpot or Salesforce?
Yes — it writes to a custom property on the company/account with the trend and top causes, and posts a timeline note on each change.
What tools provide real-time customer health scoring?
Customer success platforms — Gainsight, ChurnZero, Vitally, Planhat — do, priced per seat and per account, and they still need your usage, support and billing data connected to them. The workflow computes the same score from the tools you already have and writes it into a CRM field, so it shows in HubSpot or Salesforce next to the account. Real-time is rarely the need: a weekly score with a daily check for sharp drops catches churn signals months before renewal.
How do you connect product usage data to customer health scores automatically?
Through the analytics tool’s export — Mixpanel, Amplitude, PostHog or Segment — reading active users, sessions and the key actions per account each week. The workflow maps those to the account in the CRM by domain or account id, computes the usage sub-score and its trend, and stores it with the other components. If usage lives only in your own database, a read-only query does the same job.
Is a customer health score the same as a churn prediction model?
No. The score is a weighted rule set you can read and change; a churn model is trained on your past churn and needs about twelve months of outcomes before it beats the rules. Start with the score, keep the history, and the quarterly calibration report will tell you when a trained model would add precision.
What this blueprint is built on.
Vendor documentation the steps rely on, and the rules the guardrails are written against.
- Mixpanel — API reference developer.mixpanel.com/reference/overview
- HubSpot — API overview developers.hubspot.com/docs/api-reference/latest/overview
- Zendesk — API reference developer.zendesk.com/api-reference/