prompt engineering
Techniques for writing prompts themselves.
42 tagged items
- GuideUniversal
Turn a messy task into a prompt in five minutes
Most weak prompts come from a task nobody fully described. A five-step routine to fix that before you type, with a worked example.
- GuideUniversal
Summaries you can trust
A summary is a claim about a document, so it can be wrong in the same ways as any claim. Four habits keep it honest.
- GuideUniversal
Briefing a coding assistant: the first message
A coding assistant works from what you tell it and what it can see. Here is what to put in the first message so you spend less time correcting it.
- GuideUniversal
How to check what an AI tells you
A few checks that catch most wrong answers: which claims to verify, how to ask for sources, and why a confident tone tells you nothing.
- CheatsheetChatGPT
ChatGPT commands and keyboard shortcuts
The commands and shortcuts the interface never shows you, in one table. Mostly keyboard, mostly undocumented.
Tested on GPT-5 · May 2026
- GuideUniversal
How to write a prompt that actually works
A short checklist to run any prompt through before you send it: who, what, shape and what to leave out. Those four things separate a specific prompt…
Researcher who separates what a source says from what it concludes
Keeps a finding, an interpretation of it and a guess labelled as three separate things, so they do not blend into one confident paragraph.
Tested on GPT-5 · Jun 2026
Comet
The Perplexity browser with an AI assistant built into the browser itself. It reads the open tab, summarises it and acts on the page, and does not…
Tested on GPT-5 · Jun 2026
- ConfigClaude
CLAUDE.md for a data pipeline repository
A Claude Code project file that names the pipeline stages, says which scripts touch production data, and lists what needs a human sign-off before it…
- GuideUniversal
Few-shot examples: showing instead of telling
Why two or three worked examples in a prompt often beat a page of written rules, and how to choose examples that teach the right pattern and not an…
- GuideUniversal
Common prompt mistakes and how to fix them
Five patterns that reliably give a worse answer than you meant, each with a one-line fix. Use it as a checklist when a prompt keeps returning…
Custom GPTs
The ChatGPT way to package instructions, uploaded files and actions into a named assistant that you or your team open directly, with no API…
Tested on GPT-5 · Jun 2026
- GuideUniversal
Add a self-critique pass before the final answer
A two-step pattern: draft, then have the model check its own draft against a specific list of failure modes. It catches a kind of mistake that a…
- GuideUniversal
Force a strict output contract
How to make a model response reliably machine-parseable: exact fields, no preamble, no trailing summary. For anything that downstream code reads and…
- GuideUniversal
Prompt templates worth keeping
Four reusable prompt shapes. They are structures with blanks and not finished prompts, for tasks that come up often enough to save once and stop…
Sysadmin who warns before anything destructive
Turns the model into infrastructure help that assumes production, flags anything irreversible before it gives the command, and never gets ahead of…
Tested on Claude Sonnet · Jun 2026
- GuideUniversal
Meta-prompting: ask the model to write the prompt
Use a model to draft or improve the prompt before you use that prompt for the real task. It pays off for a recurring job and is overkill for a…
- CheatsheetUniversal
Forcing an output format that holds
Phrasings that really constrain output, and the popular ones that do not. I asked for the same thing twenty times and counted the failures.
Tested on Claude Sonnet · May 2026
Related terms
Chain of thought CoT
Prompt the model to write out its intermediate steps before giving the final answer.
Context window
The most text, counted in tokens, that a model can consider at once. Your prompt and its answer share that space.
Embeddings
Lists of numbers that stand for text, built so that similar meanings end up close together. Semantic search runs on them.
Few-shot prompting
Put two or three worked examples of the task in the prompt, on top of the description.
Fine-tuning
More training for an existing model on your own examples. It changes how the model behaves, not what it knows.
Hallucination
A fluent, confident answer that is plain wrong: an invented citation, function, statistic or fact.
Multimodal
A model that takes in or produces more than one kind of data, such as text with images, audio or video.
Retrieval-augmented generation RAG
Fetch the relevant documents first, paste them into the prompt, and the model answers from your data instead of its training.
System prompt
Instructions given to the model outside the conversation. They apply to every turn, not to one message.
Temperature
A sampling setting that decides how much randomness goes into picking each next token.
Token
The unit a model reads and writes, roughly a word fragment. Price, context limits and speed are all counted in tokens.