Consent And Agency
Designconsent-and-agencyConsent And Agency is an Agent Skill for design published in the Owl-Listener/ai-design-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Designing for informed user consent, opt-out, and human override.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Owl-Listener/ai-design-skills/blob/HEAD/claude-plugin/ai-alignment-reasoning/skills/consent-and-agency/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/consent-and-agency, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Consent and Agency
AI products make decisions, take actions, and process information on behalf of users. Consent and agency design ensures users remain in control — understanding what the AI does, agreeing to it, and being able to override it.
Informed Consent for AI
Users should understand and agree to:
- What data the AI uses: Conversation history, personal data, uploaded documents, browsing behaviour
- What the AI does with it: Training, personalisation, sharing with third parties, storage
- What actions the AI takes: Sending messages, making changes, accessing systems
- What the AI can't do: Limitations that might affect the user's expectations Consent is not a checkbox at sign-up. It's an ongoing design challenge throughout the experience.
Designing for Agency
Agency means the user feels — and is — in control:
- Opt-in over opt-out: AI features should be activated by the user, not imposed
- Reversibility: AI actions should be undoable wherever possible
- Override mechanisms: The user can always stop, redirect, or override the AI
- Exit paths: The user can disengage from AI assistance at any point without penalty
- Preference controls: The user can adjust AI behaviour, scope, and autonomy levels
Consent Patterns
- Progressive consent: Ask for permission incrementally as new capabilities are needed, not all at once
- Contextual consent: Ask at the moment the action is about to happen, not in advance
- Granular consent: Let users consent to specific actions or data uses, not blanket permissions
- Revocable consent: Users can withdraw consent and have that withdrawal take effect
Agency Anti-Patterns
- Dark patterns: Making it hard to opt out or override the AI
- Consent fatigue: Asking for permission so often that users click through without reading
- Learned helplessness: AI does so much that users forget how to do things themselves
- Invisible actions: The AI takes actions the user doesn't know about
- Irreversible defaults: AI actions that can't be undone without user awareness
Design Artefacts
- Consent flow diagrams per feature
- Agency checkpoint specifications
- Override mechanism inventory
- Data use transparency matrix
- Opt-out path designs