# DenQAI AI field-work prompt pack

Version: July 24, 2026
Use with approved, authorized data only. Do not upload PHI or restricted deal information to a consumer or otherwise unapproved AI service.

## 1. Evidence guardrail

You are assisting with dental-practice decision analysis. Work only from the material I provide or current primary sources you can open.

1. Do not invent missing numbers, identities, locations, codes, contract terms, coverage, clinical facts, or legal conclusions.
2. Label each material statement DIRECT RECORD, OFFICIAL GUIDANCE, INDEPENDENT ANALYSIS, ATTRIBUTABLE ACCOUNT, INFERENCE, or ILLUSTRATIVE EXAMPLE.
3. Cite every extracted fact to file name plus page/row/cell, or URL plus issuer, publication/effective date, and access date.
4. If a source cannot be opened, say so. Never use a search snippet as final evidence.
5. Keep facts, calculations, assumptions, and recommendations in separate columns.
6. Show formulas and units. Reconcile control totals before interpretation.
7. Assign a verification state—verified, probable, unverified, or exclude—and state what would change it. Keep source kind, support relationship, recency, commercial interest, contradictions, and missing evidence separate.
8. Do not diagnose, choose treatment, invent documentation, select a higher-paying code, auto-submit a claim, or replace legal/accounting/clinical review.
9. Stop and ask questions when a missing input could materially reverse the decision.

Return: executive answer; evidence table; calculations; contradictions; downside case; decision-reversal conditions; next request with owner and deadline; and required human reviewers.

## 2. Market capacity census

I am evaluating [GEOGRAPHY] for [PATIENT SEGMENT / PAYER PRODUCT / SERVICE SCOPE]. Build linked PERSON, SITE, and CONTROL tables. Reconcile duplicate people across sites. Treat licenses, NPIs, biographies, brands, and directories as leads—not proof of active capacity. Capture source and verification dates, observed provider days, scope, new-patient status, exact payer product, wait time, verification state, contradiction, and next recheck. Calculate confirmed physical FTE and segment-effective FTE as ranges with every factor visible. Add probable capacity and credible planned entrants separately. Return CSV-ready tables, contradictions, verification calls, control questions, and confirmed/probable/adverse cases.

## 3. Pre-sale performance normalization

Using five years of annual and monthly records, build three separate schedules:

1. Bridge SELLER REPORTED COLLECTIONS to BUYER-REPEATABLE COLLECTIONS using five non-overlapping dollar lines: seller-only/nonrecurring activity; buyer clinical-model exclusions; patient/referral loss; buyer-specific payer/fee effect; and collection loss.
2. Show first-year cash timing with prior-service receipts and current-service deferral.
3. Calculate cash available for debt after recurring operating cost, market clinical compensation, replacement management, recurring capital, and a stated free-cash buffer.

Keep prepayments, credit balances, working capital, practice reserves, and assumed obligations in a separate closing sources-and-uses schedule. Do not multiply stacked retention percentages. Tie every dollar adjustment to quantity × price × provider × cohort × period, show overlap controls, produce reported/base/downside cases, and identify every adjustment that lacks evidence.

## 4. Payer fee-schedule comparison

Compare OFFERED ALLOWED AMOUNTS with OFFICE FEES, CURRENT ALLOWED AMOUNTS, and trailing units using only authorized current code data. Calculate weighted revenue change, collection probability, direct cost, chair minutes, contribution/hour, volume required to offset the discount, and share of total variance. Flag missing/zero fees, bundling/downcoding/LEAT, non-billable restrictions, network leasing, amendments, credentialing/portability, and termination. Return the 20 decision-driving codes, negotiation request, counsel questions, and participation conditions.

## 5. Treatment-mix and values alignment

Analyze procedure mix by provider, year, patient cohort, active patients, clinical days, units, dollars, payer, new/established status, and referrals. A high or low rate is a signal—not a quality judgment. Do not diagnose or infer overtreatment from a percentage. Specify the blinded chart sample and evidence an independent dentist must review: assessment, diagnosis, images/findings, alternatives, consent, documentation, follow-up, longevity, remakes/refunds/complaints, and open cases. Return the buyer clinical-model dollar exclusion, philosophy-transfer risks, separate ethical safety checks, and the evidence that would explain or invalidate each outlier.

## 6. Documented-work billing review

In an organization-approved, access-controlled environment only, review each authorized clinical or administrative event, performer, date/location, materials, time, images/orders/messages, ledger entry, claim status, and missing evidence. For each event create a candidate pathway only: payer claim, patient administrative charge, patient noncovered service, included/bundled, appeal/correction, write-off review, or not billable. List the current licensed code source, payer policy, plan/contract, notice, law, documentation, qualification, and human approval needed. Do not supply a final code when authorized current content is absent. Never paste patient records into DenQAI or an unapproved AI service; never invent work, alter notes, upcode, auto-post, or auto-submit.

## 7. Fair role assessment

Build a role-specific assessment for [ROLE] using only future-state job requirements. Exclude age, health, disability, family status, personality stereotypes, retirement assumptions, and protected information. For each competency create an observable work sample, allowed tools, time box, 1/3/5 anchors, evidence, escalation expectation, backup/teaching test, and environment dependency. Separate employee skill from missing authority, software, training, or delegation. Convert results into a 30/60/90-day plan.

## 8. Investment red team

Act as the independent opposing reviewer. Identify unsupported facts, stale sources, circular assumptions, double counting, denominator errors, seller dependence, clinical/philosophy transfer gaps, payer non-portability, staffing/wage realism, capital deferral, authority/signature dependencies, privacy/security risk, family burden, and favorable summaries masking failed safety checks. Recompute the decision under lower patient continuity, staff exit, credentialing/cash delay, credible entrant, immediate capital need, and one market-specific shock. Return the strongest case against the preferred decision, the evidence that rebuts it, and conditions precedent.