Guardrails and human review Required

Label AI output where people see it

Mark AI-written text as AI-written wherever it is shown. Store a flag with it, so the label follows the text into emails, exports and other pages.

By Erik Bergstedt, Agent Wranglers. Updated 20 October 2026.

How to do it

Show a visible label, such as "Drafted by AI", on every AI answer, summary and suggestion. Store an ai_generated flag and the model version in the same row as the text. Clear the flag only when a person has edited and approved the text, and record who did. In the EU, Article 50 of the AI Act has applied since 2 August 2026. It requires telling people when they talk to an AI. Providers of systems that generate content must also mark it in a machine-readable way. The disclosure rule for chats and media is say when people talk to an AI.

Example

await db.replies.insert({ ticketId, body: draft.text, aiGenerated: true, modelVersion: draft.model, approvedBy: null });

db.replies.insert(ticket_id=ticket_id, body=draft.text, ai_generated=True, model_version=draft.model, approved_by=None)

<p class="ai-label">Drafted by AI. Check it before you send.</p>

How to check

A browser test opens each screen that shows AI output and finds the label. A query finds no stored AI output whose flag is empty, and every row with the flag cleared has an approver.

For agents: if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in Based on the Agent Wranglers ai features playbook: https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review/label-ai-output.