ChatGPT Prompt Engineering for Developers review
DeepLearning.AI and OpenAI · deeplearning-ai
A short course on getting reliable output from an LLM API, with runnable notebooks.
What does it take?
| Difficulty | 2 out of 5 |
|---|---|
| Hours | Not checked yet |
| Format | 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 who want to call an LLM API
- Anyone who wants structured prompting habits
Skip it if you are
- Non-coders
- Anyone already building LLM apps
What will you be able to do after it?
- Write clear, structured prompts
- Summarise, classify and transform text with an API
- Build a basic chatbot
What's in each module?
| Module | What it covers |
|---|---|
| Guidelines and iteration | Two principles for prompts that work. |
| Summarising, inferring and transforming | Common text tasks done with an API. |
| Building a chatbot | Putting it together into a simple conversational app. |
What we liked, and what we didn't
What we liked
- Short and focused
- Notebooks run in the browser
- Practical habits you'll keep using
What we didn't
- Examples use an older model generation
- Narrow scope
What should you take after it?
- Generative AI for Beginners
Microsoft's open-source course on building apps with large language models, from prompting to retrieval.
- 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: 7.8 out of 10
| Criterion | Score out of 10 |
|---|---|
| Clarity | 9 |
| Hands-on practice | 8 |
| Up to date | 6 |
| Depth | 5 |
| Truly free | 9 |
So should you take it?
The quickest way to go from chatting with ChatGPT to calling a model from code. It's short, so treat it as a sharp introduction rather than a complete course.
Where to go next
- DeepLearning.AI: 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.