AI Agents Course review
Hugging Face · hugging-face
Build LLM agents that use tools and plan steps, using open-source frameworks and open models.
What does it take?
| Difficulty | 3 out of 5 |
|---|---|
| Hours | Not checked yet |
| Format | Reading, Code notebooks, Projects |
| Maths needed | No maths |
| Coding needed | Yes, you will write code |
| Hardware needed | Not checked yet |
| Certificate | Free 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 who already use LLM APIs
- Anyone who wants to build tool-using assistants
Skip it if you are
- Beginners to Python
- People who want the theory behind transformers
What will you be able to do after it?
- Explain how an agent loop works
- Build an agent that calls tools
- Compare popular agent frameworks
What's in each module?
| Module | What it covers |
|---|---|
| What agents are | Thought, action and observation, explained clearly. |
| Frameworks | Building the same kind of agent with different open-source libraries. |
| Final project | Build and submit an agent of your own. |
What we liked, and what we didn't
What we liked
- Current material
- Uses open models
- Hands-on final project
What we didn't
- Content changes quickly
- Assumes you're comfortable with Python and APIs
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.
How we rated it: 8 out of 10
| Criterion | Score out of 10 |
|---|---|
| Clarity | 7 |
| Hands-on practice | 9 |
| Up to date | 9 |
| Depth | 7 |
| Truly free | 9 |
So should you take it?
The best free course on agents if you already code comfortably. It moves fast and changes often, but it teaches what agents actually do rather than selling a framework.
Where to go next
- Hugging Face 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.