New Feature: Agent Invocation Filter

[eavanvalkenburg]

---

name: Feature request about: Suggest an idea for this project

---

Similar to the existing Function Invocation Filters, a filter that wraps the Agent invocation, allowing for scenario's like guardrails etc. This is for both Python and .Net

[unsafecode]

We have many asks about "agentic guardrails" to provide some business guidelines or "fencing" around agent execution:

• Check if an agent instructions comply with high-level policies, regardless of its current config
• Check if an input provided to an agent is "safe", for instance by calling Azure Content Safety
• Check if an agent output complies with some corporate guidance, and possibly either review it or provide feedback to the agent to fix it