Guardrail action in Microsoft Foundry that marks detected risk and also stops it; at the tool-call intervention point, this means the tool call never runs.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Annotate and block in context, with comparison tables and the common traps.
Terms in this definition
- Microsoft Foundry
Formerly called Azure AI Foundry, the Azure platform where AI models and agents are built, evaluated and run within one resource, with evaluations, guardrails and AI red teaming.
- Risk
As ISO 31000 puts it, how uncertainty affects objectives; that effect can be good or bad.
- Chat message roles
Labels on chat messages: instructions go under system, the person's input under user, the model's previous answers under assistant, and results returned by a called tool under tool (or function).
- Agents (classic) API
First-generation Foundry Agent Service API, based on threads, messages and runs. It is deprecated, replaced by conversations and responses, and retires on 31 March 2027.
Related terms
- Annotate (guardrail action)
Guardrail action that reports detection details such as detected, filtered and severity yet lets the content through. Blocking requires Annotate and block instead.