Prompt Engineering Essentials

4 Interactive Sessions

Short, interactive sessions: watch it work, try it, then build it yourself. You can go deeper at any time in the written chapters.

1. 1

   The model sees only what you give it

   The model sees only one thing, the context window. Your instructions are one part of it, and naming a role, task, context and format makes them clear.

2. 2

   Make it think before it answers

   Ask a model to reason step by step before answering, and it gets hard problems right. Skip it for simple lookups.

3. 3

   Make it behave the same every time

   A system prompt is set once, behind the scenes. It gives the model a role, rules and a format that apply to every reply.

4. 4

   Output your code can use, and a library to reuse

   Get clean, structured output that you can pass straight into code, and save your best prompts in a tested library.

How this certificate is scored

Your certificate shows how many of your written answers met the rubric below, checked by an AI grader. Anyone who checks your certificate sees it.

• You answer 6 short questions, one for each module, in your own words (at least 40 words each).
• An AI grader checks each answer against what its module asks for: it must answer the question, use the course's practice case specifically, and be correct.
• To pass, at least 5 of the 6 answers must meet that bar. The certificate says the answers were graded by AI.

The rubric

1. Module 1, How LLMs Think: Mental model of tokens, context, and probability.
2. Module 2, Zero-Shot & Few-Shot: Prompts that work without training data.
3. Module 3, Chain-of-Thought: Multi-step reasoning prompts.
4. Module 4, System Prompts: Role + rules + format instructions.
5. Module 5, Structured Output: JSON, tables, and validated formats.
6. Module 6, Prompt Library: Reusable prompt collection with tests.

What you walk away with