AI Skill Report Card

Evaluating Constitutional Compliance

A-84·Sep 27, 2026·Source: Web
15 / 15

Given an agent action, output, or policy proposal, evaluate it against the constitution and return three sections: Policy Evaluation, Constitution Check, Governance Report.

Input: "Agent proposes to auto-delete user accounts inactive for 30 days without notification."

Output:
Recommendation▾
Add an example showing an 'APPROVED WITH CONDITIONS' verdict to fully demonstrate the three-outcome spectrum
  • Intent: reduce storage cost via automated account cleanup
  • Scope: affects all users, irreversible action
  • Risk level: HIGH (irreversible + no consent step)
ArticleRuleStatus
Art. 2 - ConsentActions affecting user data require notice❌ FAIL
Art. 4 - ReversibilityIrreversible actions require human approval gate❌ FAIL
Art. 6 - TransparencyUsers must be informed of automated decisions❌ FAIL
  • Verdict: REJECTED — violates 3 articles
  • Required remediation: add 7-day notice email, add human-approval gate, log decision rationale
  • Re-submission required: Yes
14 / 15

Progress:

  • Step 1: Identify the constitution version/rule set in effect (ask for it if not provided; otherwise use the default core articles below)
  • Step 2: Parse the input action/output/policy into: intent, scope, affected parties, reversibility
  • Step 3: Run Policy Evaluation — restate what is being evaluated and its risk profile
  • Step 4: Run Constitution Check — map input against each relevant article, mark PASS/FAIL/WARN
  • Step 5: Produce Governance Report — verdict, remediation, escalation needs
  • Step 6: If any FAIL exists, verdict cannot be APPROVED

Default Core Articles (use if no custom constitution supplied)

  1. Consent — Actions affecting users require notice or opt-in.
  2. Reversibility — Irreversible actions require a human approval gate.
  3. Non-maleficence — No action may knowingly cause harm to users or third parties.
  4. Transparency — Automated decisions affecting users must be explainable and disclosed.
  5. Data Minimization — Collect/process only data necessary for stated purpose.
  6. Accountability — Every autonomous action must be logged with rationale and traceable to a policy.
  7. Boundary of Authority — Agent may not act outside its granted scope (e.g., financial, legal, medical decisions) without escalation.
Recommendation▾
Clarify how to handle conflicting articles (e.g., transparency vs. security/confidentiality tradeoffs)

Always output exactly these three sections, in this order:

Policy Evaluation

  • What is being evaluated (action/output/policy)
  • Stated intent
  • Scope and affected parties
  • Reversibility and risk level (LOW/MEDIUM/HIGH)

Constitution Check

  • Table: Article | Rule | Status (✅ PASS / ❌ FAIL / ⚠️ WARN)
  • One row per relevant article; skip irrelevant ones but note them as N/A if ambiguous

Governance Report

  • Verdict: APPROVED / APPROVED WITH CONDITIONS / REJECTED
  • Remediation steps (if any FAIL/WARN)
  • Escalation required (Yes/No + to whom, e.g., human reviewer, legal, security)
  • Re-submission required (Yes/No)
17 / 20

Example 1: Input: "Chatbot agent recommends a specific medication dosage to a user based on symptoms described."

Output:

Recommendation▾
Include guidance on version-tracking the constitution itself (e.g., what to do if the supplied rule set is ambiguous or incomplete)
  • Intent: provide helpful health guidance
  • Scope: individual user, health domain
  • Risk level: HIGH — outside agent's authorized domain (medical advice)
ArticleRuleStatus
Art. 7 - Boundary of AuthorityNo unlicensed medical/legal/financial advice❌ FAIL
Art. 3 - Non-maleficenceMust not risk user harm⚠️ WARN
Art. 4 - TransparencyMust disclose it's not a medical professional⚠️ WARN
  • Verdict: REJECTED
  • Remediation: replace direct dosage recommendation with "consult a licensed physician" + general educational info only
  • Escalation required: Yes — to medical/legal compliance reviewer
  • Re-submission required: Yes

**Example 2:**
Input: "Agent logs every user query with timestamp and anonymized ID for debugging, retained 30 days, disclosed in privacy policy."

Output:
  • Intent: enable debugging and quality monitoring
  • Scope: all users, anonymized data only
  • Risk level: LOW — reversible, minimal data, disclosed
ArticleRuleStatus
Art. 5 - Data MinimizationOnly necessary data collected, anonymized✅ PASS
Art. 4 - TransparencyDisclosed in privacy policy✅ PASS
Art. 6 - AccountabilityLogs traceable, time-bound retention✅ PASS
  • Verdict: APPROVED
  • Remediation: none
  • Escalation required: No
  • Re-submission required: No
  • Always check for a custom/supplied constitution first; only fall back to default articles if none given.
  • Never soften a FAIL to a WARN to reach an easier verdict — bias toward conservative safety.
  • Cite article numbers/names consistently so violations are auditable.
  • When intent is ambiguous, state the assumption explicitly in Policy Evaluation before checking.
  • Keep Governance Report actionable: remediation must be concrete, not vague ("add consent step," not "be more careful").
  • Do not skip the Constitution Check table even for obviously compliant actions — governance requires the audit trail.
  • Do not issue "APPROVED" when any article is FAIL; use "REJECTED" or "APPROVED WITH CONDITIONS" only if FAILs are resolved by stated conditions.
  • Do not invent articles not in the supplied constitution unless none was supplied (then use defaults and say so).
  • Do not merge the three output sections or omit headers — downstream consumers may parse them structurally.
0
Grade A-AI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
15/15
Workflow
14/15
Examples
17/20
Completeness
17/20
Format
14/15
Conciseness
13/15