prompt engineering
Techniques for writing prompts themselves.
20 tagged items
No-padding everyday default
The one to set if you set only one. Answer first, nothing before it, nothing after it, and no offer to help further.
Tested on Claude Sonnet · May 2026
- CheatsheetUniversal
Forcing an output format that holds
The phrasings that actually constrain output, and the ones people use that do not. Tested by asking for the same thing twenty times and counting the…
Tested on Claude Sonnet · May 2026
- CheatsheetChatGPT
ChatGPT commands and keyboard shortcuts
The commands and shortcuts that are not in the interface anywhere, collected in one table. Mostly keyboard, mostly undocumented.
Tested on GPT-5 · May 2026
- Before and afterUniversal
Asking for a summary
The same document, the same model. The weak version returns the article rearranged; the strong one returns something you can act on, because it says…
Tested on Claude Sonnet · May 2026
- PromptMidjourneyStable Diffusion
Image prompt skeleton
A fill-in structure for image models that keeps subject, environment, light, lens and style in the order the models weight them.
- GuideUniversal
Giving a model a role and constraints
How naming the audience, the format and the exclusions turns unpredictable answers into repeatable ones.
- PromptUniversal
Turn a vague request into a written brief
Takes a one-line request from a colleague or client and returns the questions that have to be answered before work starts.
- GuideUniversal
Choosing a model for the job
A practical comparison of what to reach for when, based on the shape of the task rather than benchmark scores.
- GuideUniversal
Working with long documents and code
Why long sessions drift, what a large context window actually buys you, and how to keep a model on task across a big input.
- PromptUniversal
Extract structured data as JSON
A strict extraction prompt that returns valid JSON only, with nulls for missing fields instead of invented values.
- GuideUniversal
Moving your rules into a config file
How to stop repeating the same instructions in every message, and what belongs in a system prompt against what belongs in the task.
- PromptUniversal
Strict code review of a diff
A review prompt that reports only what would break in production, gives the smallest fix for each finding, and is allowed to say the diff is fine.
- GuideUniversal
What a prompt actually is
The three parts every working prompt has, why their order changes the answer, and how to tell a vague prompt from a specific one.
Related terms
Chain of thought CoT
Prompting a model to write out its intermediate steps before the final answer.
Context window
The maximum amount of text, measured in tokens, that a model can take into account at once - your prompt and its answer together.
Embeddings
Numeric vectors representing text, where similar meanings land close together - the basis of semantic search.
Few-shot prompting
Showing the model two or three worked examples of the task inside the prompt, instead of only describing it.
Fine-tuning
Further training of an existing model on your own examples, to change its behaviour rather than its knowledge.
Hallucination
A confident, fluent answer that is simply wrong - an invented citation, function, statistic or fact.
Multimodal
A model that accepts or produces more than one kind of input - text plus images, audio or video.
Retrieval-augmented generation RAG
A pattern where relevant documents are fetched first and pasted into the prompt, so the model answers from your data rather than its training.
System prompt
Instructions given to the model outside the conversation, which apply to every turn rather than one message.
Temperature
A sampling setting that controls how much randomness goes into choosing each next token.
Token
The unit a model reads and writes - roughly a word fragment. Pricing, context limits and speed are all measured in tokens.