microsoft-foundry

Orchestrate Microsoft Foundry agent workflows from deployment to evaluation.

Updated Jul 3, 2025

Search Tags:#troubleshooting #evaluation #rbac #capacity planning #agent deployment #continuous monitoring #azure ai foundry

Ready to run

npx skills add https://github.com/isakawar/crmKvitkovaPovnya --skill microsoft-foundry-isakawar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: microsoft-foundry
Source: https://github.com/isakawar/crmKvitkovaPovnya/tree/main/.agents/skills/microsoft-foundry
Command: npx skills add https://github.com/isakawar/crmKvitkovaPovnya --skill microsoft-foundry-isakawar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the friction of setting up Azure AI Foundry agents by guiding you through deployment, invocation testing, evaluation/optimization loops, and production troubleshooting with required validation steps.

Core Features & Use Cases

End-to-end Foundry agent lifecycle: create/deploy agents, invoke them for functional checks, and troubleshoot failures using the right sub-skill for each workflow.
Eval-driven quality and continuous monitoring: run batch evaluations, analyze results, optimize prompts/instructions, compare versions, and optionally enable continuous production evaluation.
Capacity, quota, and RBAC-aware operations: route model deployment decisions through quota/capacity discovery and ensure the minimum RBAC and permissions needed for invocation.

Quick Start

Use the microsoft-foundry skill to deploy an Azure AI Foundry agent, test it with an invocation, then run evaluations to identify and fix quality gaps.

Frequently Asked Questions about microsoft-foundry

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I deploy and test Azure AI Foundry agents end-to-end?▼

Deploy and test Azure AI Foundry agents by orchestrating project onboarding, agent creation, invocation testing, and troubleshooting workflows. The process uses mandatory Foundry MCP tool discovery and environment resolution from agent-metadata files to ensure safe, repeatable operations.

How does eval-driven prompt optimization work for Azure AI Foundry?▼

Eval-driven prompt optimization works by running batch evaluations, analyzing trace-to-dataset pipelines, comparing versions, and refining instructions. It uses strict eval/trace parameter conventions to identify quality gaps and optionally enable continuous production monitoring.

Do I need specific RBAC permissions for Azure AI Foundry agent invocation?▼

Yes, Azure AI Foundry agent invocation requires minimum RBAC permissions and capacity planning. The deployment process routes model decisions through quota and capacity discovery to ensure the necessary access rights and infrastructure are configured.

What is the best way to troubleshoot Azure AI Foundry agent failures?▼

The best way to troubleshoot Azure AI Foundry agent failures is by using structured sub-skills for each workflow, reading mandatory sub-skill documents, and applying structured cache and metadata conventions to isolate and resolve issues across hosted and prompt agents.

Can I set up continuous monitoring for Foundry agents in production?▼

Yes, you can set up continuous monitoring for Foundry agents by enabling continuous production evaluation and utilizing evaluator management. This integrates with trace-to-dataset evaluation pipelines to maintain agent quality over time.