Knowledge Systems
Identify Conflicting Business Rules
Compare supplied business rules, expose contradictions and scope gaps, and prepare an evidence-based conflict register without guessing which rule wins.
Quick facts
- Best for
- Owners · Founder-operators
- Prompt type
- Quality
- Expected result
- An evidence-based Unresolved conflict register with source attribution, rule scope, authority gaps, operational exposure, and neutral questions for named human owners.
- Time saved
- 30-45 minutes per rule review
- Required inputs
- BUSINESS RULES · SOURCE OWNERS · SYSTEMS OR LOCATIONS · SENSITIVITY · AUTHORITY · LAST-REVIEWED DATES · CONFLICT CONTEXT
- Works with
- ChatGPT + Claude
What this prompt does
- Finds direct contradictions, scope overlaps, version mismatches, and authority gaps in supplied rules.
- Builds an unresolved conflict register with source attribution and questions for the documented decision owner.
When to use
- When teams, documents, or systems appear to apply different rules to the same workflow or decision.
When not to use
- Do not use it to decide a policy winner, publish a rule, replace a canonical source, change access, or operate a live workflow.
- Do not place unauthorized source data or unnecessary personal, sensitive, or confidential data in an AI system.
The prompt
#CONTEXT:
Identify conflicts among supplied business rules. Create decision support for human reconciliation; do not select, rewrite, publish, or enforce a rule.
#INPUTS:
- Exact rule text with source references: [BUSINESS RULES]
- Documented source owners: [SOURCE OWNERS]
- Systems or locations containing each rule: [SYSTEMS OR LOCATIONS]
- Sensitivity labels or classifications: [SENSITIVITY]
- Supplied authority, precedence, scope, and decision rights: [AUTHORITY]
- Last-reviewed dates and version evidence: [LAST-REVIEWED DATES]
- Workflow, event, or case in which conflict appears: [CONFLICT CONTEXT]
#INSTRUCTIONS:
1. Normalize formatting only. Quote or faithfully paraphrase each rule and retain source attribution.
2. Compare rule trigger, scope, audience, exception, outcome, effective date, source owner, and documented authority.
3. Classify only evidenced conflict types: direct contradiction, overlapping scope, version mismatch, missing exception, or authority gap.
4. For every finding, state an evidence status. Use Unknown for missing facts and Unresolved conflict whenever evidence does not establish an authorized winner.
5. Do not invent, infer, or fabricate rules, owners, authority, dates, facts, sources, or approvals. Do not choose a winner or declare a rule authoritative without documented supplied authority.
6. Prepare neutral questions for the named decision owner. Recommend what evidence would resolve each conflict without recommending the substantive decision.
7. Describe downstream workflows or documents that a human should inspect after resolution. Do not update or enforce them.
8. Maintain source attribution for every fact, rule, owner, authority claim, and date.
9. For each item, state its evidence status: Verified, Reported, Unknown, or Unresolved conflict.
10. Do not invent, infer, or fabricate rules, owners, authority, dates, facts, sources, or approvals.
11. Do not choose a winner or declare a source authoritative without documented supplied authority.
12. Use only authorized knowledge data in an approved AI workspace or approved AI vendor. Minimize the data; redact or omit unnecessary personal, sensitive, or confidential data. Preserve each sensitivity label or sensitivity classification and follow company retention and vendor policy.
13. Do not publish. Do not update a canonical source. Do not grant, revoke, or change access or permissions. Do not send material externally. Do not change a live system.
14. A named human owner must approve publication before action. A named human owner must approve every canonical-source update before action. A named human owner must approve every access or permission change before action. A named human owner must approve every external action or live system change before action. A named human owner must approve every policy exception before action.
#RESPONSE FORMAT:
## Rule evidence table
| Rule | Source attribution | Owner | Scope | Authority | Last reviewed | Evidence status |
|---|---|---|---|---|---|---|
## Unresolved conflict register
| Conflict | Type | Competing evidence | Operational exposure | Named decision owner | Evidence needed |
|---|---|---|---|---|---|
## Unknowns
- Missing fact — why it matters — proposed human question
## Post-resolution review map
- Artifact or workflow — reason to inspect — approval boundaryInput checklist
- BUSINESS RULES
- SOURCE OWNERS
- SYSTEMS OR LOCATIONS
- SENSITIVITY
- AUTHORITY
- LAST-REVIEWED DATES
- CONFLICT CONTEXT
Example input
Fictional example — BUSINESS RULES: Northstar sales handbook says deposits are due at booking; delivery checklist says work may start after a signed order form. SOURCE OWNERS: Sales—Ari; Delivery—Maya. SYSTEMS OR LOCATIONS: Approved sales wiki and delivery handbook. SENSITIVITY: Internal. AUTHORITY: Neither document states precedence; Finance authority is Unknown. LAST-REVIEWED DATES: Sales 2026-05-01; Delivery 2026-06-10. CONFLICT CONTEXT: A coordinator is preparing a kickoff checklist for a fictional customer.Expected output structure
- An evidence-based Unresolved conflict register with source attribution, rule scope, authority gaps, operational exposure, and neutral questions for named human owners.
Customize this prompt
- Include effective dates and supersession markers when your policy system records them.
- Keep legal, tax, employment, or regulatory interpretations with the qualified professional who owns them.
Guardrails
- Maintain source attribution and an evidence status for every material claim; unsupported items remain Unknown and disagreements remain Unresolved conflict.
- Do not invent, infer, or fabricate rules, owners, authority, dates, facts, sources, or approvals.
- Do not choose a winner or declare a source authoritative without documented supplied authority.
- A named human owner must approve publication before action.
- A named human owner must approve every canonical-source update before action.
- A named human owner must approve every access or permission change before action.
- A named human owner must approve every external action or live system change before action.
- A named human owner must approve every policy exception before action.
- A named human owner and the qualified professional must approve every legal, tax, employment, or regulatory interpretation before action.
- A named human owner must approve every payment or financial decision before action.
- A named human owner must approve every deletion, closure, suspension, termination, revocation, deactivation, or archive action before action.
- A named human owner must approve every promise or commitment before action.
- Use only authorized knowledge data in an approved AI workspace or approved AI vendor; minimize data, redact or omit unnecessary personal, sensitive, or confidential data, preserve every sensitivity label or sensitivity classification, and follow company retention and vendor policy.
- The assistant provides a reviewable draft only and must not publish, alter canonical sources, change access or permissions, act externally, or mutate a live system.
Related articles
NEXT STEP