microsoft-foundry

Name: microsoft-foundry
Availability: InStock
Author: qprjack86

Manage Azure AI Foundry agent and model workflows from deployment through evaluation.

Updated Apr 20, 2026

Search Tags:#deployment #azure #evaluation #agents #tracing #quota #foundry

Ready to run

npx skills add https://github.com/qprjack86/apexbase --skill microsoft-foundry-qprjack86

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: microsoft-foundry
Source: https://github.com/qprjack86/apexbase/tree/main/.github/skills/microsoft-foundry
Command: npx skills add https://github.com/qprjack86/apexbase --skill microsoft-foundry-qprjack86

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the complexity of building, deploying, invoking, evaluating, and troubleshooting Azure AI Foundry agents and models by providing an end-to-end operational workflow.

Core Features & Use Cases

Agent lifecycle management: Create prompt or hosted agents, deploy containers, start and stop runtimes, and manage versions.
Model and capacity operations: Deploy Azure OpenAI models, find capacity across regions, and handle quota or PTU planning.
Observability and improvement: Query traces, correlate evaluations, build datasets from production traces, and iterate on prompts with regression checks.
Use case: A team can create a Foundry project, deploy a hosted agent, test it, inspect failures in Application Insights, and then optimize the agent based on evaluation results.

Quick Start

Use the microsoft-foundry skill to deploy my Foundry agent, verify it is running, and help me evaluate and troubleshoot it.

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 manage Azure AI Foundry agents end to end?▼

Azure AI Foundry agent deployment involves creating prompt or hosted agents, deploying containers, starting runtimes, and managing versions. You can handle the entire workflow from project creation through deployment, invocation, evaluation, tracing, and troubleshooting using Foundry MCP tools and Azure CLI.

What is the best way to evaluate and troubleshoot Foundry agent failures?▼

Evaluating and troubleshooting Foundry agents requires querying traces in Application Insights, correlating evaluation results, and inspecting runtime failures. You can build datasets from production traces and iteratively optimize prompts with regression checks to improve agent performance.

Can I check Azure OpenAI model quota and capacity across regions before deploying?▼

Yes, Azure AI Foundry capacity planning lets you find available quota across regions and handle PTU planning for Azure OpenAI models. You can deploy models, verify regional capacity, and manage quota allocations before committing to production deployments.

Do I need Azure CLI and Docker to run Foundry agent workflows?▼

Azure CLI and Foundry MCP tools are required for core agent operations, while Docker or Azure Developer CLI provide optional support for production-grade container deployments. Application Insights queries are also needed for tracing and troubleshooting agent behavior.

How does RBAC work with Azure AI Foundry projects and agents?▼

Azure AI Foundry project management includes RBAC configuration to control access to agents, models, and project resources. You configure role-based permissions across Foundry projects to ensure proper authorization for deployment, invocation, and evaluation workflows.

How do I curate datasets from production traces to optimize agent prompts?▼

Dataset curation from production traces involves querying Application Insights for agent invocation data, extracting successful and failed interactions, and building evaluation datasets. You then iterate on prompts using these datasets with regression checks to validate improvements.