MicrosoftLearning/mslearn-ai-agents

This repo contains instructions and assets for building agents on Azure

What it solves

This repository gives developers a structured, hands-on way to learn how to build AI agents on Microsoft Azure. Instead of just reading theory, you work through practical exercises that cover common tasks in agent development, helping you gain real experience.

How it works

The repo contains exercise files you can follow step by step. These exercises are designed to complement Microsoft Learn modules, so you can get deeper conceptual background if needed. You'll need an Azure subscription with enough permissions and quota to provision the required Azure resources and generative AI models. The code can be run locally if you have Python 3.13+ installed, and you can also view the exercises on a GitHub Pages site.

Who it's for

This is for developers who want to learn how to build AI agents on Azure. It's ideal if you have an Azure account (or can sign up for a free trial) and are comfortable with Python 3.13+. The exercises assume you can provision resources and work with generative AI models.

Highlights

  • Hands-on exercises that cover common AI agent development tasks.
  • Complements Microsoft Learn modules for deeper conceptual learning.
  • Can be run locally with Python 3.13+.
  • Requires an Azure subscription with access to generative AI models.
  • Exercises are also available on a GitHub Pages site.

Related

  • Project
    Floe-Labs/floe-guard

    floe‑guard is a Python/TypeScript library that tracks the real USD cost of every LLM, speech‑to‑text, text‑to‑speech, and other AI‑vendor call in‑process, and can hard‑stop a call before it would exceed a user‑defined dollar ceiling. It ships with adapters for OpenAI, Anthropic, Gemini, LangChain, CrewAI, LiteLLM, Vercel AI SDK, and voice platforms (Pipecat, LiveKit, Vapi, Retell). A bundled public‑price cost map provides offline pricing; you can override it with your own rate card. Budgets can be persisted across processes via SQLite, and an optional hosted Floe service adds a Coverage Score and 7‑day history. The core API is `BudgetGuard(limit_usd)`, with `check()` (pre‑call) and `record()` (post‑call) methods, plus atomic `reserve_tool`/`settle_tool` for paid tools.

  • Project
    wong2/cf-mailroom

    A self-hosted email system built on Cloudflare that enables humans and AI agents to share an inbox, featuring AI-powered drafting and triaging with human approval.

  • Project
    OrgoAI/bops

    Bops is an open‑source macOS app that lets you run a team of AI bots to automate business tasks. Bots execute on real cloud VMs (Orgo), can be chatted with in‑app or via Slack/Telegram/Discord, email, and phone, and integrate with ~1,400 apps. Free, Pro, and Max plans provide cloud compute and AI credit; the repo also supports full self‑hosting with your own API keys.

  • Project
    beevibe-ai/beevibe

    An agent-native operating system that creates a shared workspace for humans and AI agents to collaborate, preventing the loss of shared intelligence across a team.