Replace your CSP · Chapter 02 of 06

After the health score.Five dimensions. Evidence attached.

Your CSP renders one number nobody in the room can defend. Sturdy reads every email, call, and ticket the account produced and Claude grades five dimensions with the customer's own words attached. Not a score. A diagnostic.

This is chapter two of six. One screen at a time: last chapter was the timeline, this one is scorecards and health.

The full whitepaper and the complete Claude project instruction set. No install. No sales call.

What your CSP shows you

68↓ from 74

What moved? The support tickets from the spring?

Unfalsifiable Unactionable Weights set in 2023

What this project shows you

Stuck, not slipping

Yellow · 1 red of 5 dimensions
Statethe customer's condition
Sentiment
Engagement
Breadth
Executionours to fix
Responsiveness
Friction
"we still are not seeing the value we expected" · security review open since Feb 20 · 0 positive signals in 180 days

Rule applied: no state dimension is red, so the composite does not escalate to red. One execution red alongside two state yellows → composite yellow. The rule is printed on the artifact, with counts.

The actual construction

Four proxies, multiplied by guesses.

Open up any CSP health score and this is what you find. Not one input is the customer's own words. The pricing dispute, the champion who stopped replying, the sentence where someone wrote "we're not seeing the value": all of it sits in threads the score never read.

×

Product usage

Measures whether people open the software, not whether it works for them. A team can log in daily and be actively furious.

×

Ticket volume

Treated as negative, which inverts the truth. Engaged customers file tickets. Customers who gave up file nothing.

×

Survey responses

Single-digit response rates, self-selected, weeks late. A quarterly NPS cannot see a relationship dying in March.

×

CSM sentiment dropdown

The most informed input and the least objective. Every CSM is optimistic about their own book. That's being human.

Then the weights. Does usage deserve 40% of the score, or 15%? Nobody ran that analysis. Nobody could have. The weights were set at implementation, by the person furthest from the customer, and never touched again. precise-looking · unvalidated · not yours

What replaces it

We refused to build a score.

There is no 0-to-100 axis in this artifact. The project runs in Claude, reads the complete communication record over Sturdy's MCP connection, and returns five graded dimensions with a composite verdict. Warning lights, not a gauge.

No gauge

Grades, not integers

68 and 71 are not meaningfully different, but they look different, and people act on the difference. A grade makes a claim exactly as strong as the evidence supports: something is wrong here, in this system, and here is what tripped it.

No blending

State vs. execution

Two accounts at the same blended score can need opposite plays: one has an unhappy customer, one has a slow support queue. Averaging destroys exactly that distinction. Split into what's happening to the customer and what you're doing about it, the two can't hide from each other.

No black box

A grade you can argue with

Every color traces to a written threshold in the project instructions. When a CSM disagrees, they open the evidence: either they learn something about their account, or the rule is wrong and they fix the line that produced it. Neither outcome is available from an integer.

No crying wolf

Execution can't turn the account red

A stalled integration is a work item with an owner and a date, not a customer deciding they're done. A rollup that treats those identically teaches the team to ignore both. Only the customer's condition escalates the composite.

State · slow to reverse
Sentiment loadcritical vs. positive language, both rates
Engagement vitalitywho talks, who initiates, who replied last
Relationship breadththe human roster, not a contact count
Execution · fixable this quarter
Operational responsivenessopen loops you own · messages to resolution
Adoption frictionthe earliest actionable signal in the set

Why the output holds up

Deterministic where it counts. Honest where it can't be.

Same account, same window, same grades, every run. Put this month next to last month and any difference is a change in the relationship, not a change in how the model felt that day.

01

The thresholds are written down. And they're yours.

Inbound share below 20% is red. Friction rate above 14% is red. Plain numbers in a document your team owns, attached to quantities that mean something. When a grade disagrees with reality, you adjust one line and re-run. That's the intended workflow, not a workaround.

02

Every grade carries its evidence

Two to four cited threads per dimension: subject, date, and what each one shows, with the verbatim sentence where the wording carries the meaning. A grade you cannot open is a grade you cannot act on.

03

The fourth stateGray

A quiet healthy account and an account with broken ingestion look identical in three colors. Gray means insufficient data: a capture gap gets a flag and a fix, not a false red that sends someone into a save motion against a customer who was never leaving.

04

The attribution filter

Your customers have customers. A cancellation in a thread might be theirs, not yours, and to a naive classifier the two are identical. The diagnostic filters third-party language before grading, reports raw and attributed counts, and names what it excluded so you can check its work.

The full series

One CSP screen at a time.

Same argument, one workflow per chapter, each with its own instruction set. Start with the screen your team feels most.

01

Activity & timeline

No more manual logging. The live account timeline.

● Live — read it
02

Scorecards & health

Five graded dimensions with the evidence attached. This page.

● You are here
03

Success plans

Claude drafts and maintains the plan, from evidence of what's actually worked.

Coming soon
04

Cockpit & CTAs

A daily, prioritized action briefing — done and not-done, in one view.

Coming soon
05

Renewal center

At-risk renewal reporting anchored at the portfolio level, not one account at a time.

Coming soon
06

Customer 360

A live account picture, assembled on demand. The finale.

Coming soon

Free, no strings

Get the whitepaper and the full instruction set.

The complete "After the health score" whitepaper plus Appendix A: the entire Claude project instruction set — signal map, extraction sequence, attribution filter, every numeric threshold, and the rollup rule. Paste it into a project connected to Sturdy and run it on an account you know. Nothing needs editing before first use.

health-diagnostic-instructions.mdAPPENDIX A
## Hard rules
1. The score is deterministic. The narrative is not.
2. Never fabricate a number.
3. Gray is a real state, not a failure.
4. Resolve signal IDs at runtime. Never hardcode.
5. Apply the attribution filter.

## Step 6 · Set colors
### Sentiment load
- RED if crit_rate_pct > 12, or any attributed
  Cancellation / Value Issue names the account…
### Engagement vitality
- RED if inbound_share_pct < 20, or
  days_since_last_inbound > 30…

## Step 7 · Roll up the composite
1. Two or more dimensions gray → GRAY
2. Any state dimension red → RED
3. …
Enter your email to unlock the full set

Send me the diagnostic.

Whitepaper, instruction set, and the HTML dashboard shell. We'll email all three. No sales call attached.

Instructions land in your inbox. Run them against your own accounts today.

"An account is at 68. Last month it was 74. Nobody in the room can say what moved."

Now somebody can.