At-risk accounts surfaced early
Weakening engagement, slipping usage and rising support load are picked up while there is still time to act, rather than at renewal.
— Sales & Growth
Keeps a standing weekly read on the health of every client account, scoring each one on the signals that actually predict trouble, tracking how it moves over time and putting the accounts that need attention in front of the person who owns them.
2–3 weeks → ~25 minutes
For a full population, not a sample
No coding required
— USE CASES
Weakening engagement, slipping usage and rising support load are picked up while there is still time to act, rather than at renewal.
Because each week is recorded on the same basis, you can see which accounts are genuinely deteriorating and which had a quiet fortnight.
Each account owner gets the accounts that are theirs, with the reason behind the score, so the follow-up is specific rather than a general warning.
Leadership gets the same short weekly view of where the client base stands, without anyone assembling it by hand.
— HOW IT BEHAVES
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Each row of your export is processed on the same basis, so no account is skipped however long the table is.
Movement across the pipeline in scope is visualised from the computed data, so the trend is legible at a glance.
Findings on the pipeline in scope are written up as a document that reads like professional output, with each claim tied back to a account.
Derived columns are added row by row, keeping your source data and the judgement about each account side by side.
Detail rows are summarised into the grouped view of the pipeline in scope without losing the underlying accounts.
Account health is usually known unevenly: one owner senses a relationship cooling, another notices a renewal creeping up, and leadership only hears about it when the account is already in difficulty. At-risk accounts surfaced early is the typical trigger — weakening engagement, slipping usage and rising support load are picked up while there is still time to act, rather than at renewal. Get it right and the conclusion holds up in the room; get it rushed and it gets picked apart. Either way it costs roughly 2–3 weeks of experienced attention.
As a Skill, the work is already sequenced. You bring the evidence, and the run produces a health score for every account with the reasoning behind it plus a week-on-week view of how the health mix is shifting. The criteria, ordering and review points that make the answer trustworthy are encoded in the Skill itself — which is the difference between a structured method and a prompt someone pastes in. The practical effect: 2–3 weeks of manual work becomes a ~25 minutes run, held to an identical standard on the tenth engagement as on the first.
Client Health Pulse exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
Forecast risk & pipeline hygiene audit
Tests every open deal for stalled activity, unholdable close dates, single-threading and missing next steps, then computes the forecast dollars at risk and an action list per rep.
Churn early-warning & save plan
Combines NPS movement, ticket velocity, usage drop-off and billing changes into a churn score per account, then drafts the save play with the ARR at risk quantified.
Campaign response predictor
Learns from past campaign results to score every contact by likelihood to convert, reports which channels, creative and audience attributes actually drive response, and recommends where the budget should go.