AI Disclosure
Make it clear that users are interacting with AI, and what it can and can't do.
Patterns
Choose a category, or narrow by oversight, phase or principle. Each pattern covers when to use it, what to clarify at kickoff, an example, and the anti-pattern to avoid.
Provenance Disclosure
Mark which parts of a document were generated by AI, edited by a person or written by a person.
Confidence Translation
Express how certain the agent is in words a reviewer can act on, not as a raw number.
Inline Evidence
Show the evidence for each claim right next to it, so people can judge it without leaving the page.
Data Freshness Signal
Show reviewers when the information the agent used may be out of date, before they act on it.
Separated Confidence Scores
When the agent checks several things, show each result on its own. Never blend them into one number.
Multi-Audience Split
Present the same AI output differently for each person who looks at it, without duplicating the underlying data.
Accessible Communication
Use simple, plain words when the agent produces outputs people use every day.
Multi-Audience Explanation
Explain the same issue differently to the reviewer who resolves it and the person it affects.
User Action Recovery
Keep actions correctable after they happen, with a clear path to reverse, compensate and re-approve.
Fallback Mechanism
Keep the system working when an agent or pipeline fails, with a designed path for people or simpler processes to take over.
Audit Trail
A readable record of what the AI did, in which mode, on what basis, and who approved it.
Hard Gate
Ask people to confirm they've seen the AI's uncertainty before continuing, at high-stakes points only.
Decouple Review Actions
Separate “Mark as reviewed” from “Send”, so approval is a real review and not one click.
Monitoring Dashboard
A view for people monitoring an agent over time: what it did, what it flagged, what needs a person.
No published patterns match these filters yet.