preset

Deploy Azure OpenAI models to regions with available capacity.

66|41|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/olivomarco/vbd-copilot --skill preset-olivomarco
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: preset
Source: https://github.com/olivomarco/vbd-copilot/tree/main/skills/microsoft-foundry/models/deploy-model/preset
Command: npx skills add https://github.com/olivomarco/vbd-copilot --skill preset-olivomarco

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates optimal Azure OpenAI model deployment by evaluating capacity across regions and performing current-region checks to ensure high availability and fast startup.

Core Features & Use Cases

  • Intelligent region selection based on capacity across all regions
  • Supports creating new AI Foundry projects and selecting the best region for deployment
  • End-to-end deployment workflow: authentication, model selection, capacity checks, deployment, and monitoring

Quick Start

Deploy an Azure OpenAI model to the optimal region with capacity checks and automatic region/project selection.

Frequently Asked Questions about preset

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

FAQPage Schema
How do I deploy Azure OpenAI models to the best available region automatically?

To deploy Azure OpenAI models to the best available region automatically, this Skill evaluates capacity across all regions and handles current-region checks to ensure your deployment lands in an optimal, high-availability zone. It manages the end-to-end workflow including authentication and monitoring.

What is the best way to check Azure OpenAI capacity across multiple regions before deployment?

The best way to check Azure OpenAI capacity across multiple regions is using an automated region-optimization workflow that evaluates current-region checks across all regions to find the most suitable deployment target for high-availability setups.

Can I use this to set up multi-region high-availability deployments for AI Foundry?

Yes, you can use this for multi-region high-availability deployments in AI Foundry. It supports creating new AI Foundry projects and automatically selecting the best region based on capacity checks and proximity for your workloads. It handles end-to-end deployment.

Does the Azure OpenAI deployment workflow handle authentication and monitoring?

Yes, the Azure OpenAI deployment workflow handles authentication and monitoring. It provides an end-to-end process that includes authentication, model selection, capacity checks, deployment, and monitoring via CLI and REST workflows to ensure fast startup.

Why does my Azure OpenAI model deployment fail due to region capacity constraints?

Azure OpenAI model deployments fail due to region capacity constraints when the current region lacks available resources. This Skill solves the problem by evaluating capacity across all regions and redirecting the deployment to the best available alternative automatically.