![]()
Arabic | Bengali | Bulgarian | Burmese (Myanmar) | Chinese (Simplified) | Chinese (Traditional, Hong Kong) | Chinese (Traditional, Macau) | Chinese (Traditional, Taiwan) | Croatian | Czech | Danish | Dutch | Estonian | Finnish | French | German | Greek | Hebrew | Hindi | Hungarian | Indonesian | Italian | Japanese | Kannada | Khmer | Korean | Lithuanian | Malay | Malayalam | Marathi | Nepali | Nigerian Pidgin | Norwegian | Persian (Farsi) | Polish | Portuguese (Brazil) | Portuguese (Portugal) | Punjabi (Gurmukhi) | Romanian | Russian | Serbian (Cyrillic) | Slovak | Slovenian | Spanish | Swahili | Swedish | Tagalog (Filipino) | Tamil | Telugu | Thai | Turkish | Ukrainian | Urdu | Vietnamese
You prefer to Clone na your machine?
Dis repo get more than 50 language translations wey go make the download size big. If you want clone without translations, use sparse checkout:
Bash / macOS / Linux:
git clone --filter=blob:none --sparse https://github.com/microsoft/ai-agents-for-beginners.git cd ai-agents-for-beginners git sparse-checkout set --no-cone '/*' '!translations' '!translated_images'CMD (Windows):
git clone --filter=blob:none --sparse https://github.com/microsoft/ai-agents-for-beginners.git cd ai-agents-for-beginners git sparse-checkout set --no-cone "/*" "!translations" "!translated_images"Dis one go give you everything you need to complete the course with fast download.
If you want make we add more translation languages, dem dey list here.
Dis course get lessons wey dey cover the fundamentals to build AI Agents. Each lesson get e own topic so start for anywhere wey you like!
Di course get multi-language support. You fit find am for available languages here.
If na your first time to build with Generative AI models, check our Generative AI For Beginners course wey get 21 lessons on how to build with GenAI.
No forget to star (🌟) dis repo and fork dis repo to run the code.
If you jam problem or get any questions about building AI Agents, join our own Discord Channel for the Microsoft Foundry Discord.
Each lesson for dis course get code examples, wey you go find for code_samples folder. You fit fork dis repo to create your own copy.
The code examples for these exercises dey use Microsoft Agent Framework with Microsoft Foundry Agent Service V2:
Dis course dey use the following AI Agent frameworks and services from Microsoft:
Some code samples still support other OpenAI-compatible providers like MiniMax, wey get large-context models (up to 204K tokens). Check the Course Setup for configuration details.
For more info on how to run the code for dis course, go to the Course Setup.
You get suggestions or you find mistake for spelling or code? Raise an issue or Create a pull request
| Lesson | Text & Code | Video | Extra Learning |
|---|---|---|---|
| Intro to AI Agents and Agent Use Cases | Link | Video | Link |
| Exploring AI Agentic Frameworks | Link | Video | Link |
| Understanding AI Agentic Design Patterns | Link | Video | Link |
| Tool Use Design Pattern | Link | Video | Link |
| Agentic RAG | Link | Video | Link |
| Building Trustworthy AI Agents | Link | Video | Link |
| Planning Design Pattern | Link | Video | Link |
| Multi-Agent Design Pattern | Link | Video | Link |
| Metacognition Design Pattern | Link | Video | Link |
| AI Agents in Production | Link | Video | Link |
| Using Agentic Protocols (MCP, A2A and NLWeb) | Link | Video | Link |
| Context Engineering for AI Agents | Link | Video | Link |
| Managing Agentic Memory | Link | Video | |
| Exploring Microsoft Agent Framework | Link | ||
| Building Computer Use Agents (CUA) | Link | Link | |
| Deploying Scalable Agents | Link | Link | |
| Creating Local AI Agents | Link | Link | |
| Securing AI Agents | Link | Link |
Our team de produce oda kɔs! Check am out:
Tanks to Shivam Goyal for putting important code samples wey show Agentic RAG.
Dis project dey welcome contributions and suggestions. Most contributions need say you gɛ agree for Contributor License Agreement (CLA) wey talk say you get right to, and you really do, give us di rights to use your contribution. For full details, visit https://cla.opensource.microsoft.com.
When you send pull request, CLA bot go automatically check if you need provide CLA and put correct decoration for the PR (for example, status check, comment). Just follow di instructions wey the bot go give. You go only need to do am once across all repos wey dey use our CLA.
Dis project don adopt Microsoft Open Source Code of Conduct. For more info, check Code of Conduct FAQ or contact opencode@microsoft.com if you get any other questions or comments.
Dis project fit get trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos dey based on and you must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos for modified versions of dis project no suppose cause confusion or make person think Microsoft dey support am. Any use of third-party trademarks or logos dey based on those third-parties’ policies.
If you get stuck or get any questions about how to build AI apps, join:
If you get product feedback or errors when you dey build, visit:
Disclaimer: Dis document don translate wit AI translation service Co-op Translator. Even tho we dey try make am correct, abeg make you know say automated translation fit get errors or mistakes. Di original document for dia own language na im be di correct source. For important info, make person wey sabi human translation do am. We no go responsible for any misunderstanding or wrong understanding wey fit happen because of dis translation.