10 — AI Evaluation and Governance Checklist#

Review whether a proposed AI use is appropriate, its risks are understood, the system has credible evaluation evidence, human oversight is operational, and organizational accountability is maintained across its lifecycle. This cross-cutting checklist complements detailed model, RAG, agent, red-team, data, and monitoring templates in their respective AI domain checklists.

Scope: Frontend-specific. This file is one part of the 10_AI_Evaluation_and_Governance.md checklist. Apply the domain-wide release gate across all applicable scope files; each checklist ID remains unique.

Review details#

• Project / product:
• Release / version / environment:
• AI use case / intended users and deployment context:
• Model(s), providers, and system-version references:
• Risk category and applicable jurisdictions / markets:
• Governance, evaluation, human-oversight, and compliance owners:
• Reviewer / owner:
• Review date:
• Decision: Pending / Approved / Approved with documented exceptions / Blocked

How to use#

1. Copy the shared template to project-specific review records; leave all repository checkboxes unchecked.
2. Define the AI system boundary, intended purpose, affected people, risk tolerance, and responsible human approvers before selecting evaluation and release controls.
3. Mark [x] only after verifying the check through a risk assessment, versioned model/system documentation, evaluation result, control test, supplier review, or authorized governance decision. Record evidence, failures, accepted exceptions, and justified N/A outside the shared template, keyed by AIG ID.
4. Complete ## API Checks and ## Frontend Checks independently where applicable. For non-API or non-interactive products, document why relevant checks do not apply.
5. Adapt tests and oversight to foreseeable harms and actual system authority. Re-evaluate after significant model, policy, prompt, data, tool, market, or regulatory changes. Do not treat a benchmark pass as proof of safety or legal compliance.
6. Route deep specialist reviews to the appropriate specialized AI checklists; keep this file focused on cross-cutting risk, evidence, approval, and accountability.

Frontend Checks#

• AIG-111 Tell users when they are interacting with an AI system or viewing AI-generated outputs where appropriate or required.
• AIG-112 Explain the AI feature's intended use, major limitations, and the kinds of decisions that still require human verification.
• AIG-113 Distinguish AI-generated suggestions from verified source material, user-authored content, and completed system actions.
• AIG-114 Present citations, retrieved evidence, and confidence indicators accurately, without implying proof that a cited source supports an unsupported claim.
• AIG-115 Provide clear feedback when the system lacks information, declines a request, or cannot reliably complete a task.
• AIG-116 Make important prompts, generated content, and pending changes reviewable before committing irreversible actions.
• AIG-117 Provide clear confirmation of what tool actions were actually executed and how users can undo or contest them.
• AIG-118 Offer a practical way to edit, reject, regenerate, correct, or report AI-generated outputs as the workflow permits.
• AIG-119 Provide an accessible path to a qualified human or non-AI alternative for high-impact or failed interactions when warranted.
• AIG-120 Explain the handling and retention of user-entered information, uploads, and feedback as required by applicable policy.
• AIG-121 Avoid interface language that overstates model reliability, expertise, consciousness, authority, or guaranteed correctness.
• AIG-122 Display important data-privacy, sensitive-information, and unsafe-use warnings at the point users may submit relevant content.
• AIG-123 Ensure safety interventions, refusals, and escalation messages are comprehensible with keyboard and assistive technology.
• AIG-124 Design clear loading, streaming, timeout, cancellation, and partial-result behavior without implying unfinished content is final.
• AIG-125 Prevent accidental repeated purchases, submissions, or privileged tool actions from duplicate clicks and retries.
• AIG-126 Label generated or modified images, audio, and video where the product's applicable disclosure obligations require it.
• AIG-127 Test the user experience when results contain misleading claims, discriminatory language, personal data, or prohibited content.
• AIG-128 Ensure feedback and appeal controls preserve enough context for authorized review without exposing another user's information.
• AIG-129 Use user research to assess automation bias and whether people understand when AI output should not be trusted.
• AIG-130 Confirm frontend release flags, model versions, content notices, and human-review paths match approved production policy.

Release gate#

• The AI use case, appropriate non-AI alternatives, intended population, system boundaries, and responsible owners have been documented and approved.
• Significant foreseeable harms and applicable prohibited uses or legal/contractual obligations have been reviewed, with risk classification and accountable decisions recorded.
• Representative evaluation evidence meets predeclared task-quality and safety thresholds, including tests for consequential failures, adversarial inputs, and relevant population differences.
• Human-review, appeal, intervention, and emergency-disablement procedures have been tested for high-impact or externally acting AI workflows where appropriate.
• Model/provider licensing, processing terms, data handling, versioning, and change controls are reviewed; unauthorized access and unbounded tool actions are not permitted.
• API and frontend behavior clearly communicates AI limitations and errors and enforces approved roles, output handling, and user-facing disclosures where applicable.
• Monitoring, incident-response ownership, complaint intake, and change-triggered reevaluation are established for the deployed system.
• Material gaps or residual risks are either resolved or explicitly accepted by authorized owners with mitigation, review date, and conditions for suspension.

Domain-specific approval rule: Block AI governance sign-off if a prohibited use or unaccepted serious harm remains, a critical system action lacks required human authorization, major security/privacy exposures remain uncontrolled, or representative evaluation cannot support the intended use. Human approval must not be inferred from automated quality scores. This checklist does not establish ISO certification, NIST endorsement, or compliance with any specific jurisdiction's AI law.

Trusted references and scope#

These are primary and authoritative sources for cross-cutting AI risk and governance decisions. Recommendations from non-binding frameworks are not universal legal duties, and management-system standards do not themselves certify a particular AI deployment.

• NIST — AI Risk Management Framework — voluntary AI risk framework and lifecycle-level assessment; NIST states the 1.0 framework is being revised.
• NIST — AI RMF Playbook — Govern, Map, Measure, Manage actions; voluntary guidance, not an exhaustive mandatory checklist.
• NIST — Generative AI Profile (AI 600-1) — cross-sector generative-AI risk categories and suggested mitigations.
• ISO — ISO/IEC 42001:2023 AI management systems — requirements and guidance for an organizational AI management system; full standard requires separate access.
• ISO — ISO/IEC 23894:2023 AI risk management — contextual AI risk identification, evaluation, and treatment; full guidance requires separate access.
• OECD — AI Principles — non-binding principles for human rights, fairness, transparency, safety, and accountability.
• OWASP — GenAI LLM Top 10 (2026) — current OWASP 2026 risks covering model-integrated application security; detailed threat modeling belongs in the Security and Red Teaming checklists.
• European Commission — EU AI Act implementation timeline — changing phased application dates and categories for EU applicability review.
• EUR-Lex — Regulation (EU) 2024/1689 (consolidated) — official consolidated legal text; consult qualified advisers about the current provisions and their application.
• European Commission — Navigating the AI Act — provider, deployer, transparency, and phased-application guidance.
• NIST — AI RMF Manage function — risk acceptance, monitoring, mitigation, and go/no-go decisions.
• W3C WAI — How to Make Your Presentations Accessible to All — illustrative accessible information and communication practices where relevant.

Applicability: NIST AI RMF 1.0 and its Playbook are voluntary and were under revision as of this source review. ISO/IEC 42001 and 23894 are published standards with full texts subject to license/access; these links identify their scope but are not a substitute for reading licensed requirements. The EU AI Act has phased, revised application dates as of 2026; distinguish providers, deployers, risk classes, markets, and effective dates with qualified legal counsel. OWASP GenAI LLM Top 10 2026 applies primarily to relevant LLM-integrated systems. Only implement controls proportionate to system risk and actual interfaces.

Source review date: 2026-11-12.

Suggested testing tools#

Choose tools appropriate to the project's stack and risks; automation supports evidence but does not approve the checklist.

• Test focus: AI policy thresholds, task/safety slices, escalation, and traceable evaluations; include browser and client behavior where applicable.
• Cross-stack: promptfoo + OpenTelemetry.
• Python: DeepEval + pytest; for pytest-based suites, run python -m pytest -q.
• TypeScript: promptfoo + Vitest; for Vitest-based suites, run npx vitest run (or npx playwright test for E2E).
• JavaScript: promptfoo + Jest; for Jest-based suites, run npx jest --ci (or npx playwright test for E2E).
• Evidence: Save tool versions, configuration, test environment, fixtures, results, and links in project-specific review records using the existing checklist IDs. Expert review remains necessary where relevant.

Suggested AI skills for verification#

These are optional agent review aids, not automated passes or release approval. Each linked repository had at least 1,000 GitHub stars when checked on 2026-11-12; counts are per repository, not per skill, and do not indicate security or correctness.

• agent-governance — Assess AI oversight and operational policies (github/awesome-copilot, 41,073 repo stars).
• llm-evaluation — Review quality/safety metrics and datasets (wshobson/agents, 42,437 repo stars).
• agentic-eval — Check repeatable evaluations and failure thresholds (github/awesome-copilot, 41,073 repo stars).

How to check: In a project-specific copy, have the agent audit the frontend scope and map findings to this file's existing checklist IDs, with code/configuration references, reproducible test results, failed or inapplicable cases, and uncertainties. Independently verify findings; keep shared template boxes unchecked and retain human approval requirements.

Before use: Read the skill's SKILL.md, referenced scripts, license, and requested tool permissions. Only execute vetted skills with appropriate access in a controlled environment.

Important warning: reference only#

⚠️ Reference only — not a definitive or exhaustive checklist. This template is a starting point for review, not the ultimate authority or a guarantee of project safety, quality, regulatory compliance, accessibility, security, or launch readiness.

Use project-specific judgment and independent verification. Requirements and risks evolve and differ by project, technology, and jurisdiction. Adapt the checks, consult current authoritative sources, perform relevant tests, and obtain qualified specialist review or approval when appropriate. Checking every box does not replace these steps.