Sample AI Scorecard
What the $5,000 AI Scorecard delivers.
A sample scorecard for Civara Help, a fictional payment assistant already live on a county tax portal. Yours tests one AI feature you have built, on your own cases.
What you get
- The scorecard, with each question and its result
- The ranked fix list, with impact and effort
- The test cases, ready to run again after every release
- Draft answers for your agencies' security questionnaires about AI
- Cost per agency, and a packaging recommendation
- A fixed-price quote to fix or extend it; the $5,000 counts toward it
Illustrative demo on a fictional county. Not client work.
What we tested
One AI feature, on your own cases.
Two weeks, in staging. Your reviewer picks the questions with us, so the grades reflect what the public actually asks.
Scope
- One live AI feature: the portal payment assistant
- 50 questions from real support tickets, with names and contact details removed
- Test accounts on two agencies, to check scoping
- Your staging environment and model settings as they run today
01 · The scorecard
Seven areas, each graded on evidence.
Every result links back to the questions behind it. All figures here are illustrative, on a fictional product.
| Area | Grade | What we found |
|---|---|---|
| Amounts | C | Interest quoted from last year's rate in 4 of 50 answers |
| Sources | C | No notice line shown in 11 of 50 answers |
| Declines | D | A payment plan promised the office does not offer |
| Agency scope | B | Another office's fee schedule cited once |
| Prompt injection | C | Text in a protest letter changes the answer |
| Handoff to staff | B | Disputes reach staff, without the case summary |
| Cost per agency | B | Within target; tax season drives the peaks |
02 · Ranked fix list
What to fix first, by impact and effort.
Ranked so your team can start on the top items the week the scorecard lands, with us or on its own.
Top fixes
- Read amounts only from the person's own notice, never from model memory.
- Offer only the payment options set in the agency's settings.
- Filter fee schedules and letters by agency before anything else, and fail closed.
03 · Security questionnaire answers
Draft answers to the AI questions your agencies send.
Written from what we tested, with the details your team confirms in brackets. They describe how the feature works; they are not compliance claims.
04 · Packaging and quote
Include it, or sell it. Then fix it at a fixed price.
With the cost per agency in hand, we recommend whether to include the feature in every plan or sell it as a tier, and quote the fixes. The fixed quote is in your Scorecard; the $5,000 counts toward it.
Get a scorecard for your own AI feature.
Bring the AI feature you have built and what agencies ask about it. In 30 minutes we agree what the Scorecard would test.
Calls run in US Central time. No generic AI presentation: we discuss your product, users and production constraints.