Generative AI for Beginners review
Microsoft · microsoft
Microsoft's open-source course on building apps with large language models, from prompting to retrieval.
What does it take?
| Difficulty | 2 out of 5 |
|---|---|
| Hours | Not checked yet |
| Format | Reading, Video, Code notebooks |
| Maths needed | No maths |
| Coding needed | Yes, you will write code |
| Hardware needed | Not checked yet |
| Certificate | No certificate |
| Free to audit | Yes |
| Pace | Self-paced |
| Last updated by the provider | Not checked yet |
Who should take it, and who should skip it?
Take it if you are
- Developers new to LLMs
- People who want to build a chatbot or search tool
Skip it if you are
- People who never want to write code
- Anyone who wants to train models from scratch
What will you be able to do after it?
- Write effective prompts in code
- Build a simple chat or search app on top of an LLM
- Understand retrieval-augmented generation
What's in each module?
| Module | What it covers |
|---|---|
| LLM fundamentals | What LLMs are and how to choose one. |
| Prompting | From basic prompts to more advanced techniques. |
| Building applications | Chat, search, image generation and retrieval-augmented generation. |
What we liked, and what we didn't
What we liked
- Covers the whole app-building workflow
- Code samples in more than one language
- Regularly updated
What we didn't
- Some lessons assume Azure access
- Quality varies between lessons
What's the catch?
Some examples use Azure OpenAI. You can often swap in another provider, but not always easily.
What should you take after it?
- Hugging Face LLM Course
Hugging Face LLM Course has 12 chapters of 6 to 8 hours each, costs nothing and has no certificate. You learn LLMs with the Transformers library.
- AI Agents Course
Build LLM agents that use tools and plan steps, using open-source frameworks and open models.
How we rated it: 8.2 out of 10
| Criterion | Score out of 10 |
|---|---|
| Clarity | 8 |
| Hands-on practice | 8 |
| Up to date | 8 |
| Depth | 7 |
| Truly free | 9 |
So should you take it?
If you can code a little and want to build with LLMs rather than only use them, this is the most complete free starting point. Skim the lessons you know and build the ones you don't.
Where to go next
- Microsoft Learn: our platform review
What else it offers, and what costs money.
- Generative AI for Everyone
What large language models can actually do for you and your team, without writing a line of code. Andrew Ng teaches it in 6 hours on Coursera, certificate paid.
- Machine Learning Crash Course
Google's Machine Learning Crash Course has 12 modules and takes about 13.5 hours by Google's own timings. It is free, with quiz badges and no certificate.
- CS50's Introduction to AI with Python
CS50's Introduction to AI with Python runs 7 weeks with 12 projects, costs nothing and gives a free CS50 Certificate if you score 70% on every project.
Last checked .
Not sure this is the one?
Answer two questions and we'll point you to the course that fits where you are today.