# DenQAI: policy evidence plan

File-specific companion · 2026-09-10

## Purpose

Which measures and comparisons are needed to evaluate one policy question?

**Who:** Policy analyst and independent methods reviewer

**Records:** Defined question; authority/implementation evidence; baseline and after-period data; comparison series; source locators.

## Complete the file

1. Link project_code and policy_id to a specific decision_question and chain_stage.
2. Define each measure and unit consistently across baseline, after, and comparison periods.
3. Record source_locator, status, and limitation; preserve Unknown when data have not been collected.

## Definitions

- **Baseline period:** Defined period before the relevant exposure.
- **Comparison unit:** Unexposed or otherwise justified reference used in the evaluation.
- **Chain stage:** Authority-to-outcome step the particular evidence row addresses.

## Fictional example

Fictional example: PEV-001 asks whether a schedule was published; baseline_value and after_value stay Unknown until dated official versions are collected.

## Review and next action

Obtain the missing measure or improve the comparison before analyzing the apparent change.

This raw evidence plan does not estimate an effect; before/after differences alone do not establish causation.

[Related DenQAI guide](https://denqai.com/policy/prepare)

## AI coach prompt

Help me use DenQAI’s policy evidence plan. My question is: Which measures and comparisons are needed to evaluate one policy question? Explain these terms in plain language: Baseline period, Comparison unit, Chain stage. Ask one question at a time about the required records: Defined question; authority/implementation evidence; baseline and after-period data; comparison series; source locators. Walk through the supplied fictional example before asking me for inputs. Treat every missing value as unknown, not zero. Do not invent source records, contract terms, legal conclusions, or clinical facts. Use only permitted fictional or aggregate, non-identifying information. Follow this boundary: This raw evidence plan does not estimate an effect; before/after differences alone do not establish causation. End with the missing evidence and this next step: Obtain the missing measure or improve the comparison before analyzing the apparent change.

## AI review prompt

Review my permitted fictional or aggregate draft of DenQAI’s policy evidence plan against the file instructions. Check each required field and period, units, evidence locator, assumptions, arithmetic where formulas are actually supplied, and unresolved contradictions. Check the sequence: Link project_code and policy_id to a specific decision_question and chain_stage. Define each measure and unit consistently across baseline, after, and comparison periods. Record source_locator, status, and limitation; preserve Unknown when data have not been collected. Separate facts from assumptions and missing records. Do not supply unsupported numbers or make a professional decision for me. Apply this limitation: This raw evidence plan does not estimate an effect; before/after differences alone do not establish causation. Return corrections, questions for the responsible reviewer, and the next action.