ChatGPT Prompt Engineering for Developers
Reviewed by AI Agent Rank editors · Last verified 2026-05-23
Our take
The default starting point if anyone asks 'where do I learn prompting'. Free, 90 minutes, by Andrew Ng and an OpenAI engineer — there is no higher-authority entry point in the field. The course teaches structured prompting patterns (system messages, few-shot, chain-of-thought, output parsing) with hands-on Jupyter labs. The downside is age — released in 2023, the GPT-3.5-era examples are dated, but the patterns transfer cleanly to GPT-4o / Claude 3.5 / Gemini 2.
About the instructor
Andrew Ng is the most authoritative name in applied ML education. Isa Fulford built much of OpenAI's cookbook patterns.
Pros
- +Andrew Ng + OpenAI engineer — the gold-standard authorship credential
- +Free, ~90 minutes, hands-on Jupyter labs
- +Patterns are model-agnostic — they work on Claude, Gemini, open-source LLMs
Cons
- −2023 vintage — some examples use the old chat-completions style
- −Geared toward developers (Python required); marketers will struggle
Best for
- · Developers writing their first LLM-powered feature
- · Anyone who needs a vocabulary upgrade before evaluating AI tools
Not ideal for
- · Non-technical people — there's Python from minute 5 onward
- · People wanting the latest agentic-loop / tool-use patterns (covered in the LangGraph course instead)
Free on DeepLearning.AI · ~1.5 hours (9 lessons)
After this course
These are the agents and tools where the skills from this course actually pay back.
Alternatives we considered
Other courses on the same topic. The right pick depends on your level and constraints — see each card for the trade-offs.