![]()
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 am for your computer?
Dis repository get over 50 language translations wey go make the download size big well-well. If you wan clone without the 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 wey you need to complete the course quick-fast.
If you want make we add more translation languages, dem list dey here
Dis course get lessons wey dey cover the basics of building AI Agents. Each lesson dey cover im own topic so you fit start anywhere wey you like!
We get multi-language support for dis course. Check our available languages here.
If na your first time to dey 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 fit run the code.
If you jam wahala or get any question about building AI Agents, join our special Discord Channel for Microsoft Foundry Discord.
Each lesson for dis course get code examples inside, wey you go find for the 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 Azure AI Foundry Agent Service V2:
Dis course dey use the following AI Agent frameworks and services from Microsoft:
Some code samples also fit use other OpenAI-compatible providers like MiniMax, wey get large-context models (reach 204K tokens). Check the Course Setup to see the details of how to configure am.
For more info on how to run the code for dis course, visit the Course Setup.
You get suggestions or you see spelling or code mistakes? 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 | Coming Soon | ||
| Creating Local AI Agents | Coming Soon | ||
| Securing AI Agents | Coming Soon |
Our tɛm de produce oda kɔs! Make una check am:
Tanks to Shivam Goyal for di beta contribution wey show how Agentic RAG dey work.
Dis projek dey welcome contributions and suggestions. Most contributions require say you gɛt to agree to Contributor License Agreement (CLA) wey talk say you get di right, and you really grant us di rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit pull request, CLA bot go automatically check if you need to provide CLA and go add di correct tags for di PR (for example, status check, comment). Just follow di instructions wey di bot give. You need to do dis only once for all repos wey dey use our CLA.
Dis projek don adopt di Microsoft Open Source Code of Conduct. For more information see di Code of Conduct FAQ or contact opencode@microsoft.com if you get any oda questions or comments.
Dis projek fit get trademarks or logos for projects, products, or services. Make sure you use Microsoft trademarks or logos according to Microsoft’s Trademark & Brand Guidelines. If you use Microsoft trademarks or logos for modified versions of dis projek, e no suppose cause confusion or make people think say Microsoft sponsor am. If you use third-party trademarks or logos, you gɛt follow those third parties’ rules.
If you jam problem or get questions about how to build AI apps, make you join:
If you get product feedback or errors for while you dey build, visit:
Disclaimer:
Dis document don translate with AI translation service Co-op Translator. Even tho we dey try make am correct, abeg make you sabi say automated translations fit get error or no too correct. The original document for e own language na the correct source. For any important information, make person wey sabi translate human translation. We no go responsible if person no understand well or take am anyhow because of this translation.