Prompt Patterns & Techniques
Move past one-off prompts and learn the named patterns pros reach for — worked examples, chain-of-thought reasoning, strict output shapes, and delimiter guardrails.
Few-shot: teaching by example
Show, do not just tell When you describe the output you want in words alone, the model has to guess at the exact style, wording, and structure you have in mind. Few-shot prompting removes the guessing by handing it a few worked examples first. Zero-shot vs few-shot A zero-shot prompt asks for the task with […]
Diagnosing a pattern that stopped working
Every pattern in this course has a failure mode Patterns are not magic words. Each one works by changing what the model attends to, and each fails in a way you can recognise once you have seen it. Few-shot drifting into copying Symptom: the output reuses details from your examples — the same company name, […]
ChatGPT: Reliable Results
The intermediate rung: give ChatGPT structure and examples, get output in the shape you need, and verify it before you use it.
Show, don’t just tell: worked examples
The fastest way to fix an inconsistent answer Describing what you want takes paragraphs. Showing what you want takes one example — and works better. Paste two or three worked examples of input → desired output, then give the real input. The model copies the pattern: length, tone, structure, level of detail. Why it works […]
Prompts that survive being handed over
The prompt works. For you Here is a pattern that repeats everywhere: someone builds a prompt that works beautifully, shares it, and their colleague gets noticeably worse results from what looks like the same thing. The reason is almost never the prompt text. It is everything the author supplied without noticing — knowing what good […]