# DenQAI: project evidence register

File-specific companion · 2026-09-10

## Purpose

What evidence supports this project decision, and what must happen next?

**Who:** Project owner and workstream reviewers

**Records:** Coded decision scope; permitted summaries; source locators; effective periods; reviewer findings and contradictions.

## Complete the file

1. Fill project_code, decision_type, posture, and target_window consistently.
2. Create one evidence_id per question or record, with status, source_locator, and effective_period.
3. Record finding_or_contradiction and assign next_action to the appropriate reviewer_role.

## Definitions

- **Evidence ID:** Stable code distinguishing one evidence item.
- **Posture:** Project decision stance; use the current project builder’s permitted vocabulary rather than inventing a code.
- **Effective period:** Period the cited record actually describes or controls.

## Fictional example

Fictional example: EV-014 asks whether Location 1 has required authority; status is Requested and next_action is obtain the executed approval record.

## Review and next action

Follow the unresolved record most likely to change the decision.

A raw evidence register is not automatic verification or submission. Keep confidential source documents in authorized systems and use coded locators.

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

## AI coach prompt

Help me use DenQAI’s project evidence register. My question is: What evidence supports this project decision, and what must happen next? Explain these terms in plain language: Evidence ID, Posture, Effective period. Ask one question at a time about the required records: Coded decision scope; permitted summaries; source locators; effective periods; reviewer findings and contradictions. 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: A raw evidence register is not automatic verification or submission. Keep confidential source documents in authorized systems and use coded locators. End with the missing evidence and this next step: Follow the unresolved record most likely to change the decision.

## AI review prompt

Review my permitted fictional or aggregate draft of DenQAI’s project evidence register 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: Fill project_code, decision_type, posture, and target_window consistently. Create one evidence_id per question or record, with status, source_locator, and effective_period. Record finding_or_contradiction and assign next_action to the appropriate reviewer_role. Separate facts from assumptions and missing records. Do not supply unsupported numbers or make a professional decision for me. Apply this limitation: A raw evidence register is not automatic verification or submission. Keep confidential source documents in authorized systems and use coded locators. Return corrections, questions for the responsible reviewer, and the next action.