Prompt Engineering
The quality of an LLM app is often decided by prompt design more than by model choice.
Learn it
Work through DeepLearning.AI's short course, which teaches the two guiding principles (write clear, specific instructions; give the model time to reason) with runnable notebooks. Cross-reference Anthropic's prompt engineering overview for a structured checklist, and try the interactive tutorial hands-on.
By the end you’ll be able to
- Apply clear instructions, few-shot examples, and structured output
- Use chain-of-thought and role/system prompts to improve reliability
Free resources
- DeepLearning.AI — ChatGPT Prompt Engineering for Developers(opens in a new tab)Start here
Taught by Isa Fulford and Andrew Ng; hands-on notebooks.
Free1.5 hr - Anthropic — Prompt Engineering Overview(opens in a new tab)
Well-organized techniques: clarity, examples, chain-of-thought.
Free45 min - Anthropic — Interactive Prompt Engineering Tutorial(opens in a new tab)
9-chapter hands-on tutorial with exercises.
Free2 hr
Practice
Take one weak prompt and iterate through five versions, adding clarity, examples, and a required JSON output format; log what changed each time.
Build it — your output
A before/after prompt casebook showing measurable improvement on a real task.
Prove it — check yourself
You’re ready to move on when you can honestly say yes to each:
- Can you turn a vague request into a specific, structured prompt?
- Can you get reliable JSON output from a model?
- Can you explain when few-shot examples help versus hurt?
Do it with AI
Use a free AI tool as your tutor and pair-programmer. Copy a prompt below into Claude, ChatGPT, or Gemini (for building, try Cursor or Copilot).
The habit: Try it yourself first — a little struggle is where the learning actually happens. Then ask for a hint before the answer — never copy blindly.
- Understand itClaude / ChatGPT / Gemini
I'm a beginner learning "Prompt Engineering". Explain it in simple terms with a real-world analogy, then ask me ONE question to check my understanding — don't reveal the answer.
- PracticeClaude / ChatGPT / Gemini
Give me 3 short practice problems on "Prompt Engineering" (my goal: apply clear instructions, few-shot examples, and structured output), from easy to hard. Don't include the solutions yet — I'll try them first, then ask you to check.
- Get unstuckClaude / ChatGPT / Gemini
I'm stuck on this exercise about "Prompt Engineering": [paste your attempt here]. Give me ONE small hint to move forward — do NOT give me the full solution.
- Build & reviewCursor / Copilot
Here is my work for a "Prompt Engineering" task: [paste your code or answer]. Review it: point out what's wrong and WHY, and suggest improvements — but let me make the fixes myself.
- Prove itClaude / ChatGPT / Gemini
Quiz me on "Prompt Engineering". Ask me 5 questions one at a time, wait for my answer each time, then tell me if I'm right and briefly why.