20 KiB
AI Agents for Beginners - One Kɔs
One kɔs we go teach you everything wey you need sabi to start build AI Agents
🌐 Support for Many Languages
Support dey from GitHub Action (E dey automatic & e dey always update)
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 Dey Prefer Make You Clone For Your Machine?
This repository get over 50 language translations wey go make the download big well well. If you wan clone without di 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 quick quick to finish di kɔs.
If you want make dem put more translation languages, dem dey listed here.
🌱 How to Start
Dis kɔs get lessons wey cover the fundamentals of how to build AI Agents. Each lesson get him own topic so you fit start from anywhere wey you like!
This kɔs get multi-language support. Go our available languages here.
If na your first time to build with Generative AI models, check our Generative AI For Beginners kɔs, 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.
Meet Other Learners, Get Your Questions Answered
If you jam any wahala or you get questions about how to build AI Agents, join our special Discord Channel for inside the Microsoft Foundry Discord.
Wetin You Need
Each lesson for this kɔs get code examples, wey dey for inside the code_samples folder. You fit fork dis repo to make your own copy.
The code examples for these exercises dey use Microsoft Agent Framework with Azure AI Foundry Agent Service V2:
- Microsoft Foundry - You need Azure Account
This kɔs dey use these AI Agent frameworks and services from Microsoft:
Some code samples still fit use other OpenAI-compatible providers like MiniMax, wey get large-context models (up to 204K tokens). Make you check the Course Setup for how to set am up.
For more information about how to run the code for dis kɔs, waka go the Course Setup.
🙏 You Want Help?
You get any suggestions or you see any spelling or code mistakes? Raise an issue or Create a pull request
📂 Wetin dey inside each lesson
- One written lesson wey dey for the README plus one short video
- Python code samples wey dey use Microsoft Agent Framework with Azure AI Foundry
- Links to extra resources to help you continue to learn
🗃️ Lessons
| 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 for 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 | Link | Link |
🎒 Ada oda Courses
Our team dey produce oda courses! Check am out:
LangChain
Azure / Edge / MCP / Agents
Generative AI Series
Core Learning
Copilot Series
🌟 Community Thanks
Tenk yu to Shivam Goyal for to help wit important code samples wey show Agentic RAG.
Contributing
Dis project dey welcome contributions and suggestions. Most contributions dem require say you gree wit Contributor License Agreement (CLA) wey talk say you get di right, and truly, you dey give us di rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit pull request, CLA bot go automatically sabi if you need provide CLA and mark di PR (like status check or comment). Just follow wetin di bot talk. You go do dis one time for all repos wey use our CLA.
Dis project don adopt Microsoft Open Source Code of Conduct. For more info, see Code of Conduct FAQ or contact opencode@microsoft.com if you get more questions or comments.
Trademarks
Dis project fit get trademarks or logos for projects, products, or services. To use Microsoft trademarks or logos, you need follow Microsoft's Trademark & Brand Guidelines. If you change dem small and use dem, e no suppose cause wahala or make people think Microsoft dey sponsor am. Any use of third-party trademarks or logos get to follow di third-parties policies.
Getting Help
If you jam problem or get any question about building AI apps, join:
If you get product feedback or errors while 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.