Academy
TrustLayer: Reading and Acting on the Trust Badge
Learn how to interpret the TrustLayer badge that appears on every AI answer. This intermediate course walks you through the score and color system, explains each of the five independent controls, shows you how to drill into the details behind a score, and gives you practical strategies for handling orange and red badges. You will also learn the limits of a green badge and how TrustLayer behaves differently in chat versus automated workflows.
Programa del curso
1
What Is the TrustLayer Badge?
Understand that every AI answer receives an independent trust score out of 100 with a color code, and that it is a reading aid rather than a certificate of truth.
2
The Five Controls Explained
Identify the five independent checks—source anchoring, prompt fidelity, action claims, code guard, and repetition—and understand what each one verifies.
3
Reading the Details Behind a Score
Learn how to click the badge to see each control's result and, for source anchoring, which specific claims were or were not found in the sources.
4
Why Some Answers Are Not Scored
Understand why short conversational replies are marked as not applicable and why this keeps the badge meaningful.
5
What to Do with an Orange or Red Badge
Apply practical strategies—asking the AI to cite sources, rephrasing the request, or grounding with a document—when a badge signals a warning or a serious issue.
6
Limits of a Green Badge
Recognise that a green badge means consistency with visible sources, request, and tools—not absolute truth—and that human judgment remains necessary for decisions and commitments.
7
TrustLayer in Chat vs. Automated Workflows
Distinguish between annotation-only mode in chat and agents, and blocking mode in automated workflows where a control can stop unverified output before delivery.
Seguir este curso en OUPI
Progreso, cuestionario y certificado en tu cuenta — 6 preguntas para validar lo aprendido y obtener un certificado, en tu espacio OUPI.