The safeguards map / 3.2 Agent harnesses
Microsoft Agent Framework
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
An agent framework whose function tools can require human approval before they run, with a middleware system and OpenTelemetry traces.
Where it sits
3.2 Agent harnesses (primary): Lets a developer mark each function tool as requiring human approval before it executes, and wraps agent requests in middleware.
When agents require any user input, for example to approve a function call, this is referred to as a human-in-the-loop pattern.
captured
whether it requires human approval before being executed
captured
Flexible middleware system for request/response processing, exception handling, and custom pipelines
captured
Facts
- Concern
- safetysecurity
- Names the law
- no
- Subject
- agent
- Used by
- those who make it
- Runs
- at runtime
- Policy comes from
- owner-entered settings
- Can the agent bypass it
- depends
Handoffs
produces Runtime records: OpenTelemetry traces, logs and metrics (GenAI semantic conventions)
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.