# AI prompt pack Updated 2026-09-19. ## Purpose How can AI help with a bounded dental-practice decision without inventing facts or assuming professional authority? ## Who uses this Owner and accountable subject-matter reviewer ## Records to gather Permitted coded or aggregate records; current primary-source excerpts; defined question; source locators; model assumptions and units. ## Steps 1. Apply Evidence guardrail before selecting the relevant task prompt. 2. Provide only authorized inputs and use the prompt for market census, transfer, fees, clinical-review planning, billing-review planning, role evidence, or red-team analysis. 3. Require citations, separated facts/assumptions/calculations, missing-evidence questions, and decision-reversal conditions. 4. Have the appropriate human reviewer check the output before using it in a decision. ## Key terms - **Direct record**: Source material documenting the particular event or amount, still subject to verification. - **Inference**: Reasoned interpretation that extends beyond what the source states directly. - **Decision-reversal condition**: Fact or assumption change that would alter the proposed decision. ## Fictional example Fictional example: Give AI a fictional five-line collections bridge and ask it to identify overlap and cite the supplied row for every adjustment; missing amounts remain questions. ## Next action Use the AI output to request missing evidence or test a calculation, then record the human-reviewed conclusion. ## Limits This prompt pack is a readable aid, not a secure AI environment or professional review. Do not upload PHI or restricted deal data to an unapproved service or let AI invent work, diagnoses, codes, or contract terms. ## AI coaching Help me complete this DenQAI file using the context below. Explain the supplied fictional example first, then ask one question at a time about my permitted fictional or aggregate, non-identifying inputs. Treat missing values as unknown, not zero. Keep example values separate from my case. Do not invent records, source verification, contract terms or professional conclusions. Identify the missing evidence and responsible reviewer before the next action. File: AI prompt pack (Markdown). Question: How can AI help with a bounded dental-practice decision without inventing facts or assuming professional authority? Records to gather: Permitted coded or aggregate records; current primary-source excerpts; defined question; source locators; model assumptions and units. Fields or sheets: DenQAI AI field-work prompt pack; 1. Evidence guardrail; 2. Market capacity census; 3. Pre-sale performance normalization; 4. Payer fee-schedule comparison; 5. Treatment-mix and values alignment; 6. Documented-work billing review; 7. Fair role assessment; 8. Investment red team. Key terms: Direct record: Source material documenting the particular event or amount, still subject to verification. Inference: Reasoned interpretation that extends beyond what the source states directly. Decision-reversal condition: Fact or assumption change that would alter the proposed decision. Steps: 1. Apply Evidence guardrail before selecting the relevant task prompt. 2. Provide only authorized inputs and use the prompt for market census, transfer, fees, clinical-review planning, billing-review planning, role evidence, or red-team analysis. 3. Require citations, separated facts/assumptions/calculations, missing-evidence questions, and decision-reversal conditions. 4. Have the appropriate human reviewer check the output before using it in a decision. Fictional example: Fictional example: Give AI a fictional five-line collections bridge and ask it to identify overlap and cite the supplied row for every adjustment; missing amounts remain questions. Limits: This prompt pack is a readable aid, not a secure AI environment or professional review. Do not upload PHI or restricted deal data to an unapproved service or let AI invent work, diagnoses, codes, or contract terms. Next action: Use the AI output to request missing evidence or test a calculation, then record the human-reviewed conclusion. ## AI review Review my permitted fictional or aggregate, non-identifying draft against the DenQAI file context below. Check the actual fields, units, periods, evidence and unresolved contradictions. Use arithmetic only where the stated model supports it; a CSV has no embedded formulas. Keep missing values unknown and separate facts, assumptions and the fictional example. Return specific corrections, questions for the responsible reviewer and the next action; do not invent professional approval. File: AI prompt pack (Markdown). Question: How can AI help with a bounded dental-practice decision without inventing facts or assuming professional authority? Records to gather: Permitted coded or aggregate records; current primary-source excerpts; defined question; source locators; model assumptions and units. Fields or sheets: DenQAI AI field-work prompt pack; 1. Evidence guardrail; 2. Market capacity census; 3. Pre-sale performance normalization; 4. Payer fee-schedule comparison; 5. Treatment-mix and values alignment; 6. Documented-work billing review; 7. Fair role assessment; 8. Investment red team. Key terms: Direct record: Source material documenting the particular event or amount, still subject to verification. Inference: Reasoned interpretation that extends beyond what the source states directly. Decision-reversal condition: Fact or assumption change that would alter the proposed decision. Steps: 1. Apply Evidence guardrail before selecting the relevant task prompt. 2. Provide only authorized inputs and use the prompt for market census, transfer, fees, clinical-review planning, billing-review planning, role evidence, or red-team analysis. 3. Require citations, separated facts/assumptions/calculations, missing-evidence questions, and decision-reversal conditions. 4. Have the appropriate human reviewer check the output before using it in a decision. Fictional example: Fictional example: Give AI a fictional five-line collections bridge and ask it to identify overlap and cite the supplied row for every adjustment; missing amounts remain questions. Limits: This prompt pack is a readable aid, not a secure AI environment or professional review. Do not upload PHI or restricted deal data to an unapproved service or let AI invent work, diagnoses, codes, or contract terms. Next action: Use the AI output to request missing evidence or test a calculation, then record the human-reviewed conclusion. ## Related guide [Open the related guide](https://denqai.com/ai-workflows)