preset

Analyze Azure region capacity and deploy OpenAI models to the optimal region.

Updated Apr 7, 2026
One-click install
npx skills add https://github.com/bzellman/earp-kit --skill preset-bzellman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: preset
Source: https://github.com/bzellman/earp-kit/tree/main/skills/system/microsoft-foundry/models/deploy-model/preset
Command: npx skills add https://github.com/bzellman/earp-kit --skill preset-bzellman

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Deploys Azure OpenAI models to the best region by analyzing capacity across regions, reducing deployment time and increasing availability.

Core Features & Use Cases

  • Region-aware deployment: automatically selects the optimal region based on capacity and current region status.
  • Flexible workflow: supports creating new AIFoundry projects or using existing ones, deploying GlobalStandard SKUs with deterministic naming.
  • Use cases: rapid production deployments, multi-region failover readiness, and streamlined onboarding for new AI projects.

Quick Start

Authenticate with Azure, specify your AIFoundry project, choose the model and version, and run the preset deployment to automatically select the best region and deploy the model.

Frequently Asked Questions about preset

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

FAQPage Schema
How do I automatically select the best Azure OpenAI region for model deployment?

To select the best Azure OpenAI region, this skill analyzes capacity across regions and deploys models to the optimal location, reducing deployment time and increasing availability. It performs deterministic deployment steps based on capacity calculations.

What prerequisites do I need to deploy Azure OpenAI models to an optimal region?

Prerequisites for optimal region deployment include having the Azure CLI installed, an active Azure subscription, and a valid AI Foundry project resource ID. You authenticate with Azure and specify your AIFoundry project before running the deployment.

Can I use an existing AI Foundry project for region-aware Azure OpenAI deployment?

Yes, you can use an existing AI Foundry project for region-aware Azure OpenAI deployment. The workflow supports creating new AIFoundry projects or reusing existing ones to deploy GlobalStandard SKUs with deterministic naming.

How does Azure OpenAI deployment handle multi-region fallback when capacity is scarce?

Azure OpenAI deployment handles multi-region fallback by checking region capacity and applying fallback workflows when capacity is scarce. It supports fast-path deployments when capacity exists and calculates capacity to ensure deterministic deployment steps.

What is the best way to automate Azure OpenAI model deployment across multiple regions?

The best way to automate Azure OpenAI model deployment across multiple regions is to use a region-aware deployment workflow that analyzes capacity and selects the optimal region, supporting rapid production deployments and multi-region failover readiness.