# Promptlexity

> A free library of AI prompts for ChatGPT, Claude and Gemini, plus a plain-English glossary of AI and prompting terms. 96 prompts in 8 categories, 8 downloadable skills in the Agent Skills (SKILL.md) format, and 64 glossary terms, free to use.

Prompts use {{VARIABLE}} placeholders for the parts a user fills in. Each prompt page has the prompt, an example output, how to use it and why it works. Each glossary page has a plain-English definition, an example and a common mistake.

## Prompts

- [Cut a draft by a third without losing meaning](https://promptlexity.com/prompts/writing/tighten-draft/): Writing. Shortens any piece of writing to a word target while keeping every point, so you can hit a limit without gutting the argument.
- [Get blunt, specific feedback on a draft](https://promptlexity.com/prompts/writing/critique-my-draft/): Writing. Asks the model to grade your draft against a goal and name its weakest parts, instead of the polite praise models default to.
- [Proofread and explain every change](https://promptlexity.com/prompts/writing/proofread-with-reasons/): Writing. Fixes spelling, grammar and punctuation, then lists each change with a reason so you learn the pattern instead of just accepting edits.
- [Rewrite an email to sound more confident](https://promptlexity.com/prompts/writing/confident-email-rewrite/): Writing. Removes hedging, apologies and filler from an email so it reads as clear and assured, without turning rude.
- [Rewrite jargon in plain English](https://promptlexity.com/prompts/writing/plain-english-rewrite/): Writing. Turns technical, legal or corporate text into plain English for a specific reader, and flags anything that could not be simplified safely.
- [Rewrite text in your own writing style](https://promptlexity.com/prompts/writing/match-my-writing-style/): Writing. Studies two or three samples of your writing and rewrites new text to match your sentence length, vocabulary and tone.
- [Say no to a request without burning the bridge](https://promptlexity.com/prompts/writing/polite-decline-email/): Writing. Writes a short, kind and clear refusal that keeps the relationship intact and, where possible, offers a smaller alternative.
- [Turn an outline into a first draft, section by section](https://promptlexity.com/prompts/writing/outline-to-draft/): Writing. Writes a long document one section at a time from your outline, so quality holds up across the whole piece.
- [Turn meeting notes into a follow-up email](https://promptlexity.com/prompts/writing/meeting-follow-up-email/): Writing. Converts messy meeting notes into a clean recap email with decisions, owners and dates, using only what is in the notes.
- [Turn rough notes into a LinkedIn post](https://promptlexity.com/prompts/writing/linkedin-post-from-notes/): Writing. Shapes bullet-point notes into a readable LinkedIn post with a specific opening line and no engagement-bait clichés.
- [Write a customer apology that fixes the problem](https://promptlexity.com/prompts/writing/customer-apology-email/): Writing. Drafts an apology that owns the mistake, explains the fix and states what happens next, without corporate non-apologies.
- [Write a short cold email that gets replies](https://promptlexity.com/prompts/writing/cold-email/): Writing. Drafts a cold email under 100 words that leads with the reader’s problem, gives one proof point and asks for a small next step.
- [Brief a coding agent on a task](https://promptlexity.com/prompts/coding/coding-agent-brief/): Coding. Writes a clear task brief for an AI coding agent: scope, files, constraints and a definition of done, so it changes what you meant.
- [Build and explain a regular expression](https://promptlexity.com/prompts/coding/regex-builder/): Coding. Writes a regex from plain-English rules plus examples that should and should not match, then explains each part.
- [Choose an open model to run locally](https://promptlexity.com/prompts/coding/choose-local-model/): Coding. Narrows down which open-weights model, size and quantization level fit your hardware and task, with trade-offs explained.
- [Choose model settings for an LLM API call](https://promptlexity.com/prompts/coding/llm-api-settings/): Coding. Recommends temperature, top-p, max tokens, stop sequences and caching for a specific LLM task, with the reasoning for each.
- [Debug a problem by testing hypotheses](https://promptlexity.com/prompts/coding/debug-with-hypotheses/): Coding. Turns a confusing bug into a ranked list of hypotheses, each with a quick test, so you stop changing code at random.
- [Explain an error message and how to fix it](https://promptlexity.com/prompts/coding/explain-error-message/): Coding. Translates a stack trace into plain English, names the most likely cause in your code, and gives the smallest fix to try first.
- [Explain unfamiliar code line by line](https://promptlexity.com/prompts/coding/explain-unfamiliar-code/): Coding. Walks through code you did not write, from the big picture down to tricky lines, at the level of experience you choose.
- [Extract structured data as valid JSON](https://promptlexity.com/prompts/coding/structured-json-extractor/): Coding. Pulls fields out of messy text into JSON that matches your schema exactly, with null for anything that is not there.
- [Refactor code for readability, same behaviour](https://promptlexity.com/prompts/coding/refactor-for-readability/): Coding. Cleans up messy code in small, safe steps and explains each change, while keeping inputs, outputs and side effects identical.
- [Review code like a senior engineer](https://promptlexity.com/prompts/coding/code-review-checklist/): Coding. Reviews a diff or file for bugs, security issues and readability, ranked by severity, with concrete line-level fixes.
- [Turn a business question into a SQL query](https://promptlexity.com/prompts/coding/sql-query-from-question/): Coding. Writes a correct SQL query from a plain-English question and your table schema, and explains the assumptions it made.
- [Write unit tests for a function](https://promptlexity.com/prompts/coding/write-unit-tests/): Coding. Generates focused unit tests covering normal cases, edge cases and errors, using your test framework’s conventions.
- [Answer "People also ask" questions in one pass](https://promptlexity.com/prompts/seo/people-also-ask-answers/): SEO. Writes short, snippet-ready answers to a list of search questions, each one direct enough to be quoted on its own.
- [Check whether a page matches search intent](https://promptlexity.com/prompts/seo/search-intent-check/): SEO. Judges whether your page gives searchers what they want for a keyword, and lists the specific changes that would close the gap.
- [Create a content brief for a target keyword](https://promptlexity.com/prompts/seo/content-brief/): SEO. Builds a writer-ready brief with search intent, outline, questions to answer and the angle that beats current results.
- [Find what to update in an old article](https://promptlexity.com/prompts/seo/content-refresh-audit/): SEO. Audits an older article for outdated facts, missing subtopics and weak sections, and gives a prioritised update plan.
- [Group keywords into topic clusters](https://promptlexity.com/prompts/seo/keyword-clustering/): SEO. Sorts a raw keyword list into clusters by search intent, so you know which keywords one page can target together.
- [Make a page easier for AI assistants to cite](https://promptlexity.com/prompts/seo/ai-search-visibility/): SEO. Reviews a page for the things that make AI answer engines quote it: direct answers, clear facts, named sources and clean structure.
- [Plan internal links between your pages](https://promptlexity.com/prompts/seo/internal-link-plan/): SEO. Suggests which pages should link to which, with natural anchor text, to send authority to the pages that matter most.
- [Write an llms.txt file for your website](https://promptlexity.com/prompts/seo/llms-txt-writer/): SEO. Drafts an llms.txt file in the standard format, so AI tools can understand what your site offers and which pages matter.
- [Write FAQ answers with matching schema markup](https://promptlexity.com/prompts/seo/faq-schema/): SEO. Writes short, factual FAQ answers based on your own content and outputs valid FAQPage JSON-LD to paste into the page.
- [Write meta descriptions for many pages at once](https://promptlexity.com/prompts/seo/meta-descriptions-batch/): SEO. Writes a unique meta description under 155 characters for each page in a list, returned as a table you can paste into a spreadsheet.
- [Write title tags that earn the click](https://promptlexity.com/prompts/seo/title-tag-variants/): SEO. Generates title tag options under 60 characters that include the keyword early and give searchers a clear reason to click.
- [Write useful alt text for images](https://promptlexity.com/prompts/seo/image-alt-text/): SEO. Writes alt text for uploaded images that describes what matters on that page, for screen reader users first and search second.
- [Compare competitor messaging side by side](https://promptlexity.com/prompts/marketing/competitor-messaging-teardown/): Marketing. Breaks down how competitors describe themselves and finds the claims nobody is making, so you can stand apart.
- [Draft a positioning statement](https://promptlexity.com/prompts/marketing/positioning-statement/): Marketing. Turns what you know about your product, customers and competitors into a clear positioning statement and the messaging that follows from it.
- [Find patterns across customer interviews](https://promptlexity.com/prompts/marketing/customer-interview-synthesis/): Marketing. Pulls themes, quotes and surprises out of interview transcripts, with every claim traced to who said it.
- [Generate a clean product photo with AI](https://promptlexity.com/prompts/marketing/product-photo-prompt/): Marketing. Writes an image prompt for a studio-style product shot on a clean background, ready for a shop listing or social post.
- [Mine customer reviews for your value proposition](https://promptlexity.com/prompts/marketing/value-prop-from-reviews/): Marketing. Finds the benefits, phrases and objections customers actually use in reviews, so your copy sounds like them.
- [Plan a month of social posts](https://promptlexity.com/prompts/marketing/social-content-calendar/): Marketing. Builds a 4-week posting plan with themes, formats and post ideas grounded in what your audience cares about.
- [Plan a product launch email sequence](https://promptlexity.com/prompts/marketing/launch-email-sequence/): Marketing. Plans a 4 to 5 email launch sequence with the goal, timing and draft of each email, so the series builds rather than repeats.
- [Prepare answers to common sales objections](https://promptlexity.com/prompts/marketing/objection-handling/): Marketing. Writes honest, specific responses to the objections you hear most, including when to agree that the product is not a fit.
- [Write a product description that sells](https://promptlexity.com/prompts/marketing/product-description/): Marketing. Turns a list of product specs into a short description that leads with what the buyer gets, then backs it up with details.
- [Write ad copy variations for paid social](https://promptlexity.com/prompts/marketing/ad-copy-variants/): Marketing. Writes short ad variants for one platform, each testing a different hook, within that platform’s character limits.
- [Write an image prompt for an ad visual](https://promptlexity.com/prompts/marketing/image-ad-prompt/): Marketing. Turns an ad idea into a detailed image-generation prompt with composition, lighting, style and what to avoid.
- [Write landing page headlines to test](https://promptlexity.com/prompts/marketing/landing-page-headline-variants/): Marketing. Generates headline and subhead pairs built on different angles, so your A/B test compares ideas rather than synonyms.
- [Build a meeting agenda with a clear outcome](https://promptlexity.com/prompts/business/meeting-agenda-builder/): Business. Turns a vague meeting idea into a timed agenda with a decision to reach, pre-reading and an owner for each item.
- [Draft a one-page business plan](https://promptlexity.com/prompts/business/one-page-business-plan/): Business. Turns a business idea into a one-page plan covering customer, offer, pricing, channels, costs and the riskiest assumption to test first.
- [Draft an AI use policy for a small team](https://promptlexity.com/prompts/business/ai-use-policy/): Business. Writes a short, practical policy on which AI tools staff can use, what data they can share, and how to check AI output.
- [Estimate the cost of an AI feature](https://promptlexity.com/prompts/business/ai-cost-estimate/): Business. Estimates monthly API costs for an AI feature from expected usage and token prices, and shows which levers reduce cost most.
- [Review your pricing page like a buyer](https://promptlexity.com/prompts/business/pricing-page-review/): Business. Reads your pricing page as a sceptical buyer would, and lists what is confusing, missing or likely to stall a purchase.
- [Summarise a contract in plain English](https://promptlexity.com/prompts/business/contract-summary/): Business. Summarises key terms, obligations, dates and risks in a contract, with clause references so you can check each point.
- [Turn goals into measurable OKRs](https://promptlexity.com/prompts/business/okr-draft/): Business. Converts rough quarterly goals into objectives and key results that are measurable, ambitious and not just a task list.
- [Write a job description people want to read](https://promptlexity.com/prompts/business/job-description/): Business. Writes a clear job post that describes the actual work, the first-year goals and real requirements, without inflated wish lists.
- [Write a monthly investor update](https://promptlexity.com/prompts/business/investor-update/): Business. Turns your monthly numbers and notes into a short, honest investor update with clear asks at the end.
- [Write a one-page decision memo](https://promptlexity.com/prompts/business/decision-memo/): Business. Structures a decision into options, trade-offs, a recommendation and the risks of being wrong, on a single page.
- [Write a standard operating procedure](https://promptlexity.com/prompts/business/sop-writer/): Business. Turns rough notes about how you do a task into a clear, numbered SOP that someone new could follow without asking you.
- [Write support reply templates for common questions](https://promptlexity.com/prompts/business/support-reply-macros/): Business. Creates reusable support replies for your most common tickets, based only on your real policies, with blanks for personal details.
- [Answer a question from your own documents only](https://promptlexity.com/prompts/research/answer-from-documents/): Research. Makes the model answer strictly from documents you provide, cite which one each fact came from, and admit when the answer is not there.
- [Compare sources on a question in one table](https://promptlexity.com/prompts/research/source-comparison-table/): Research. Lines up what several sources say about one question, how strong each one’s evidence is, and where they disagree.
- [Design a short survey that gives usable answers](https://promptlexity.com/prompts/research/survey-design/): Research. Writes a focused survey with clear, unbiased questions and answer options, plus how you will use each answer.
- [Estimate a market size from first principles](https://promptlexity.com/prompts/research/market-sizing/): Research. Builds a bottom-up market size estimate with stated assumptions, then checks it against a second method to see if the answers agree.
- [Fact-check the claims in a piece of text](https://promptlexity.com/prompts/research/fact-check-claims/): Research. Pulls out every checkable claim from a text, rates how likely each is to be true, and says how to verify it.
- [Interpret a table of data without overclaiming](https://promptlexity.com/prompts/research/data-interpretation/): Research. Reads a table or CSV, answers your question with the numbers, and flags what the data can and can not tell you.
- [Plan a deep research task before you run it](https://promptlexity.com/prompts/research/deep-research-plan/): Research. Writes a research brief with sub-questions, source types and a report format, ready to paste into a deep research tool.
- [Sharpen a vague research question](https://promptlexity.com/prompts/research/research-question-sharpener/): Research. Turns a fuzzy question into a specific, answerable one with defined terms, scope and what a good answer would look like.
- [Steelman both sides of an argument](https://promptlexity.com/prompts/research/steelman-both-sides/): Research. Builds the strongest honest case for each side of a question, including the one you disagree with, then shows where the real disagreement lies.
- [Summarise a long document with supporting quotes](https://promptlexity.com/prompts/research/summarize-with-quotes/): Research. Summarises a long document around the questions you care about, backing every point with a short exact quote.
- [Summarise a research paper for a busy reader](https://promptlexity.com/prompts/research/literature-summary/): Research. Explains a paper’s question, method, findings and limits in plain language, and separates what it shows from what it suggests.
- [Write questions for a user research interview](https://promptlexity.com/prompts/research/interview-questions-generator/): Research. Writes an interview guide with open, non-leading questions that uncover what people actually do, not what they say they would do.
- [Explain a concept at three levels of depth](https://promptlexity.com/prompts/learning/concept-at-three-levels/): Learning. Explains one concept for a child, a curious adult and a practitioner, so you can climb from intuition to detail.
- [Explain a topic to a complete beginner](https://promptlexity.com/prompts/learning/explain-like-im-new/): Learning. Explains any topic from zero, using one everyday analogy, then checks your understanding with a quick question.
- [Explain how AI chatbots work, without the hype](https://promptlexity.com/prompts/learning/explain-how-ai-works/): Learning. Gives an accurate, plain-English explanation of how chatbots like ChatGPT and Claude work, what they are good at, and where they fail.
- [Get coached on writing better prompts](https://promptlexity.com/prompts/learning/prompting-coach/): Learning. Reviews a prompt you wrote, explains what is missing, and teaches you the habit so your next prompt is better on its own.
- [Learn a method from a worked example](https://promptlexity.com/prompts/learning/worked-example/): Learning. Solves one problem slowly with every step explained, then gives you a similar problem to solve on your own.
- [Learn through questions with a Socratic tutor](https://promptlexity.com/prompts/learning/socratic-tutor/): Learning. Sets the model up as a tutor that guides you with questions and hints instead of giving the answer away.
- [Make a realistic study plan for a goal](https://promptlexity.com/prompts/learning/study-plan/): Learning. Builds a week-by-week plan that fits your actual hours, with practice and review built in, not just a reading list.
- [Practise a language in real conversation](https://promptlexity.com/prompts/learning/language-practice-partner/): Learning. Sets up a role-play conversation in the language you are learning, with gentle corrections after each of your replies.
- [Quiz me on a topic, one question at a time](https://promptlexity.com/prompts/learning/practice-quiz/): Learning. Runs an interactive quiz that adapts to your answers, explains mistakes and finishes with a list of topics to review.
- [Read a hard book or article with a guide](https://promptlexity.com/prompts/learning/reading-companion/): Learning. Helps you read difficult texts section by section: context first, then the argument, key terms and questions to think about.
- [Test your understanding with the Feynman technique](https://promptlexity.com/prompts/learning/feynman-check/): Learning. You explain a topic in simple words; the model finds the gaps, errors and jargon you used to hide what you do not understand.
- [Turn notes into flashcards for spaced repetition](https://promptlexity.com/prompts/learning/flashcards-from-notes/): Learning. Converts your notes into clear question and answer flashcards, formatted to import straight into Anki or Quizlet.
- [Break a big task into first steps](https://promptlexity.com/prompts/productivity/break-down-big-task/): Productivity. Splits an overwhelming task into small, concrete steps, and gives you one step you can start in the next five minutes.
- [Catch up on a long chat or email thread](https://promptlexity.com/prompts/productivity/summarize-long-thread/): Productivity. Summarises a long Slack, Teams or email thread into what was decided, what is still open, and what anyone needs from you.
- [Compare options with a weighted decision matrix](https://promptlexity.com/prompts/productivity/decision-matrix/): Productivity. Scores options against criteria you weight yourself, shows the totals, and tests whether the winner holds up when weights change.
- [Create a project kickoff checklist](https://promptlexity.com/prompts/productivity/project-kickoff-checklist/): Productivity. Builds a kickoff document covering goals, scope, roles, risks and the first two weeks of work, so the project starts with no loose ends.
- [Design an AI agent workflow for a repetitive task](https://promptlexity.com/prompts/productivity/automation-workflow-design/): Productivity. Maps a repetitive task into steps an AI agent can do, which tools it needs, and where a human must approve before anything is sent.
- [Improve any prompt before you use it](https://promptlexity.com/prompts/productivity/prompt-improver/): Productivity. Asks the model to rewrite your prompt with clearer context, constraints and output format, and to list what it still needs from you.
- [Plan your day around your energy](https://promptlexity.com/prompts/productivity/daily-plan/): Productivity. Turns a messy to-do list and fixed meetings into a realistic time-blocked day, with hard work matched to your best hours.
- [Pull action items out of a meeting transcript](https://promptlexity.com/prompts/productivity/meeting-notes-to-actions/): Productivity. Extracts decisions, action items with owners and deadlines, and open questions from a transcript, quoting where each came from.
- [Run a 20-minute weekly review](https://promptlexity.com/prompts/productivity/weekly-review/): Productivity. Reflects on what happened last week, what slipped and why, then picks the three things that matter most next week.
- [Triage a backlog of emails fast](https://promptlexity.com/prompts/productivity/inbox-triage/): Productivity. Sorts a pile of emails into reply now, schedule, delegate and archive, with one-line draft replies for the urgent ones.
- [Turn a good chat into a reusable prompt template](https://promptlexity.com/prompts/productivity/reusable-prompt-template/): Productivity. Looks back at a conversation that went well and condenses it into one reusable prompt with blanks, so you get that result first time next time.
- [Write custom instructions for your AI assistant](https://promptlexity.com/prompts/productivity/custom-instructions-writer/): Productivity. Drafts the "custom instructions" or project instructions for ChatGPT, Claude or Gemini, so every chat starts already knowing how you like to work.

## Skills

- [Plain English editor](https://promptlexity.com/skills/plain-english-editor/): Rewrites technical, legal or corporate text into plain English for a named reader, keeping every fact, obligation and number. Use when someone asks to simplify, de-jargon, make text clearer, or write for a non-expert audience. Download: https://promptlexity.com/skills/plain-english-editor.zip
- [Code review](https://promptlexity.com/skills/code-review/): Reviews code or a diff for bugs, security problems, performance issues and readability, ranked by severity with concrete fixes. Use when someone asks for a code review, to check a pull request, to find bugs in a function, or whether code is safe to merge. Download: https://promptlexity.com/skills/code-review.zip
- [SEO content brief](https://promptlexity.com/skills/seo-content-brief/): Creates a writer-ready SEO content brief for a target keyword, covering search intent, angle, outline, questions to answer and facts to source, written to work for both search engines and AI answer engines. Use when someone asks for a content brief, an article outline for SEO, or how to beat current search results. Download: https://promptlexity.com/skills/seo-content-brief.zip
- [Brand voice](https://promptlexity.com/skills/brand-voice/): Learns a brand or personal writing voice from samples, writes a reusable voice guide, and applies it to new drafts. Use when someone asks to write in their voice, match their brand tone, make copy sound like them, or create a style guide from examples. Download: https://promptlexity.com/skills/brand-voice.zip
- [Meeting notes to actions](https://promptlexity.com/skills/meeting-notes/): Turns meeting transcripts or rough notes into a short recap with decisions, action items with owners and dates, and open questions, using only what was said. Use when someone shares a meeting transcript or notes and wants a summary, action items, minutes or a follow-up email. Download: https://promptlexity.com/skills/meeting-notes.zip
- [Source checker](https://promptlexity.com/skills/source-checker/): Fact-checks claims in a text by listing each checkable claim, rating how likely it is to be true, and saying how to verify it, with citations when web search is available. Use when someone asks to fact-check, verify claims, check sources, or find out if something is true. Download: https://promptlexity.com/skills/source-checker.zip
- [Socratic tutor](https://promptlexity.com/skills/socratic-tutor/): Tutors a learner through a problem with guiding questions and small hints instead of giving the answer, then checks understanding. Use when a student asks for help with homework, wants to learn a topic, or asks to be taught rather than told. Download: https://promptlexity.com/skills/socratic-tutor.zip
- [Weekly review](https://promptlexity.com/skills/weekly-review/): Runs a structured 20-minute weekly review from the user's tasks, calendar and notes, finding what slipped and why, and choosing the top three priorities for next week. Use when someone asks to plan their week, do a weekly review, reflect on last week, or prioritise. Download: https://promptlexity.com/skills/weekly-review.zip

## Guides

- [How to write a prompt that gets a useful answer](https://promptlexity.com/guides/how-to-write-a-prompt/): A five-part pattern for writing AI prompts: role, task, context, format and a check. With a before and after example you can copy.
- [How to find, fill in and use a prompt from the library](https://promptlexity.com/guides/how-to-use-promptlexity/): Search for a task, fill in the blanks, then copy the prompt or open it in ChatGPT, Claude or Perplexity. A two-minute walkthrough.
- [How to add a skill to Claude and Claude Code](https://promptlexity.com/guides/how-to-install-a-skill-in-claude/): Download a skill zip, upload it in the Claude apps, or drop the folder into Claude Code. Plus how to check it is working.
- [How to use AI skills in ChatGPT, Gemini and other chatbots](https://promptlexity.com/guides/how-to-use-skills-in-chatgpt-and-gemini/): Turn any SKILL.md skill into reusable instructions for a custom GPT, a ChatGPT project, a Gemini Gem or a single chat.
- [How to check an AI answer before you rely on it](https://promptlexity.com/guides/how-to-check-ai-answers/): A practical routine for catching made-up facts, wrong numbers and broken code in AI answers, with prompts that make checking faster.
- [How to build your own prompt library](https://promptlexity.com/guides/how-to-build-a-prompt-library/): Save the prompts that work, turn them into templates with blanks, and keep them one click away. A simple system that takes ten minutes.

## Glossary

- [AI agent](https://promptlexity.com/glossary/ai-agent/): An AI system that can take actions toward a goal, such as searching, editing files or sending messages, not just answer questions.
- [Alignment](https://promptlexity.com/glossary/alignment/): The work of making AI systems pursue the goals and values their makers and users actually intend.
- [Attention (in AI models)](https://promptlexity.com/glossary/attention/): The part of a transformer model that decides which other words matter most when processing each word.
- [Chain-of-thought prompting](https://promptlexity.com/glossary/chain-of-thought/): Asking the model to work through a problem step by step before giving its final answer.
- [Context engineering](https://promptlexity.com/glossary/context-engineering/): Deciding everything an AI model sees for a task: instructions, examples, documents, memory and tool results, not just the prompt wording.
- [Context window](https://promptlexity.com/glossary/context-window/): The maximum amount of text, measured in tokens, that an AI model can read and write in one go.
- [Deep research](https://promptlexity.com/glossary/deep-research/): An AI mode that spends several minutes searching and reading many sources, then writes a detailed report with citations.
- [Delimiters](https://promptlexity.com/glossary/delimiters/): Markers like triple quotes or XML tags that separate your instructions from the text you want the AI to work on.
- [Diffusion model](https://promptlexity.com/glossary/diffusion-model/): A type of AI that generates images or video by starting from random noise and gradually refining it into a picture.
- [Distillation](https://promptlexity.com/glossary/distillation/): Training a smaller AI model to imitate a larger one, so you get similar results for less cost.
- [Embeddings](https://promptlexity.com/glossary/embeddings/): Lists of numbers that represent the meaning of text, so a computer can find texts that mean similar things.
- [Evals (AI evaluations)](https://promptlexity.com/glossary/evals/): Tests that measure how well an AI model or prompt performs on a set of example tasks.
- [Few-shot prompting](https://promptlexity.com/glossary/few-shot/): Showing the model two or three examples of the task done well before asking it to do a new one.
- [Fine-tuning](https://promptlexity.com/glossary/fine-tuning/): Training an existing AI model further on your own examples to change how it behaves.
- [Foundation model](https://promptlexity.com/glossary/foundation-model/): A large, general-purpose AI model trained on broad data that many different apps and tasks are built on top of.
- [Generative AI](https://promptlexity.com/glossary/generative-ai/): AI that creates new content, such as text, images, audio, code or video, rather than only sorting or predicting labels.
- [Generative engine optimization (GEO)](https://promptlexity.com/glossary/generative-engine-optimization/): Making your content easy for AI answer engines like ChatGPT search, Perplexity and Google AI Overviews to find, understand and cite.
- [Grounding](https://promptlexity.com/glossary/grounding/): Making an AI base its answer on specific sources you provide or it retrieves, instead of only its memory.
- [Guardrails](https://promptlexity.com/glossary/guardrails/): Rules, checks and limits placed around an AI system to keep its behaviour safe and on task.
- [Hallucination](https://promptlexity.com/glossary/hallucination/): When an AI model states something false or made up as if it were true.
- [Inference](https://promptlexity.com/glossary/inference/): Running a trained AI model to get an answer. Every chat message you send triggers inference.
- [Instruction tuning](https://promptlexity.com/glossary/instruction-tuning/): Training that teaches a raw language model to follow instructions and answer like an assistant.
- [Iterative prompting](https://promptlexity.com/glossary/iterative-prompting/): Improving an AI result through a series of follow-up instructions, rather than expecting a perfect answer first time.
- [Jailbreak](https://promptlexity.com/glossary/jailbreak/): A prompt designed to trick an AI into ignoring its safety rules or usage policies.
- [Knowledge cutoff](https://promptlexity.com/glossary/knowledge-cutoff/): The date after which an AI model has no built-in knowledge, because its training data stops there.
- [Large language model (LLM)](https://promptlexity.com/glossary/llm/): An AI model trained on huge amounts of text to predict and generate language, like the models behind ChatGPT and Claude.
- [LLM-as-a-judge](https://promptlexity.com/glossary/llm-as-a-judge/): Using an AI model to grade or compare AI outputs against criteria, instead of having people review every one.
- [llms.txt](https://promptlexity.com/glossary/llms-txt/): A plain-text file at a website’s root that tells AI tools what the site is about and which pages matter most.
- [Max tokens](https://promptlexity.com/glossary/max-tokens/): A setting that caps how long the AI’s reply can be, measured in tokens.
- [MCP (Model Context Protocol)](https://promptlexity.com/glossary/mcp/): An open standard that lets AI apps connect to tools and data sources, like a universal plug for AI integrations.
- [Meta-prompting](https://promptlexity.com/glossary/meta-prompting/): Using an AI model to write, improve or critique prompts, rather than doing the task directly.
- [Multimodal AI](https://promptlexity.com/glossary/multimodal/): AI that can work with more than one type of input or output, such as text, images, audio and video.
- [Negative prompt](https://promptlexity.com/glossary/negative-prompt/): A list of things you do not want in an AI-generated image, such as blur, extra fingers or text.
- [Open-weights model](https://promptlexity.com/glossary/open-weights/): An AI model whose trained parameters are published, so anyone can download and run it on their own hardware.
- [Parameters](https://promptlexity.com/glossary/parameters/): The internal numbers a model learns during training. Model size, like "70B", counts them in billions.
- [Prefilling](https://promptlexity.com/glossary/prefilling/): Writing the first few words of the AI’s reply yourself, so it continues in the format you want.
- [Prompt](https://promptlexity.com/glossary/prompt/): The text you give an AI model to tell it what to do.
- [Prompt caching](https://promptlexity.com/glossary/prompt-caching/): A feature that reuses the processed start of a prompt across requests, making repeated calls cheaper and faster.
- [Prompt chaining](https://promptlexity.com/glossary/prompt-chaining/): Splitting a big task into a sequence of smaller prompts, where each step uses the output of the last.
- [Prompt engineering](https://promptlexity.com/glossary/prompt-engineering/): Writing and testing instructions for an AI model so it reliably gives you the result you want.
- [Prompt injection](https://promptlexity.com/glossary/prompt-injection/): An attack where hidden instructions in a document, email or web page trick an AI into doing something it should not.
- [Prompt template](https://promptlexity.com/glossary/prompt-template/): A reusable prompt with blanks, like {{AUDIENCE}}, that you fill in each time you use it.
- [Quantization](https://promptlexity.com/glossary/quantization/): Storing an AI model’s numbers with less precision so it uses less memory and runs faster, with a small loss in quality.
- [RAG (retrieval-augmented generation)](https://promptlexity.com/glossary/rag/): A setup where the AI first searches your documents for relevant passages, then answers using them.
- [ReAct (reason and act)](https://promptlexity.com/glossary/react-prompting/): A pattern where an AI alternates between thinking about what to do, taking an action with a tool, and checking the result.
- [Reasoning model](https://promptlexity.com/glossary/reasoning-model/): An AI model trained to think through a problem at length before answering, which helps on hard maths, code and analysis.
- [RLHF (reinforcement learning from human feedback)](https://promptlexity.com/glossary/rlhf/): A training method where people rate AI answers and the model learns to give answers that get better ratings.
- [Role prompting](https://promptlexity.com/glossary/role-prompting/): Telling the AI to act as a particular expert or character, such as an editor or a teacher.
- [Self-consistency](https://promptlexity.com/glossary/self-consistency/): Asking the same question several times, or several ways, and trusting the answer that comes up most often.
- [Semantic search](https://promptlexity.com/glossary/semantic-search/): Search that finds results by meaning, not just by matching the exact words you typed.
- [Stop sequence](https://promptlexity.com/glossary/stop-sequence/): A piece of text that tells the AI to stop writing as soon as it produces it.
- [Structured output](https://promptlexity.com/glossary/structured-output/): Getting an AI to answer in a fixed format, like JSON or a table, that software or people can use directly.
- [Sycophancy](https://promptlexity.com/glossary/sycophancy/): When an AI model tells you what you want to hear, agreeing or praising instead of being accurate or honest.
- [System prompt](https://promptlexity.com/glossary/system-prompt/): Standing instructions given to an AI model before the conversation starts, which shape every reply.
- [Temperature](https://promptlexity.com/glossary/temperature/): A setting that controls how random or predictable an AI model’s word choices are.
- [Token](https://promptlexity.com/glossary/token/): A small chunk of text, often part of a word, that AI models read and write. Usage and prices are counted in tokens.
- [Tool use (function calling)](https://promptlexity.com/glossary/tool-use/): When an AI model asks to run a tool, like a search or a calculator, and uses the result in its answer.
- [Top-p](https://promptlexity.com/glossary/top-p/): A setting that limits the AI’s word choices to the most likely options that together add up to a set probability.
- [Training data](https://promptlexity.com/glossary/training-data/): The huge collection of text, code and other material an AI model learned from.
- [Transformer](https://promptlexity.com/glossary/transformer/): The neural network design behind almost all modern language models, built around a mechanism called attention.
- [Tree of thoughts](https://promptlexity.com/glossary/tree-of-thoughts/): A prompting approach where the model explores several possible paths, judges them, and continues with the most promising.
- [Vector database](https://promptlexity.com/glossary/vector-database/): A database built to store embeddings and quickly find the ones most similar to a query.
- [Vibe coding](https://promptlexity.com/glossary/vibe-coding/): Building software by describing what you want to an AI and accepting the code it writes, often without reading it closely.
- [Zero-shot prompting](https://promptlexity.com/glossary/zero-shot/): Asking an AI model to do a task with instructions only, without showing it any examples.

## Optional

- [A 20-minute weekly review with AI](https://promptlexity.com/blog/weekly-review-with-ai/): Use AI to look back at your week, spot what slipped and plan the next one, without it taking over your judgement. Step by step.
- [AI skills are not just for developers](https://promptlexity.com/blog/skills-for-non-developers/): Skills sound technical, but most are plain-English instructions. Five everyday jobs where a skill saves time for people who never write code.
- [Do role prompts like 'You are an expert' still work?](https://promptlexity.com/blog/do-role-prompts-work/): Telling a model it is a world-class expert does less than people think. Telling it who the answer is for does more. Here is the difference.
- [Five prompt mistakes that make AI answers worse](https://promptlexity.com/blog/five-prompt-mistakes/): Vague tasks, missing context, no format, stacked requests and starting over too soon. How to spot each mistake and the one-line fix.
- [From messy meeting notes to clear actions in two minutes](https://promptlexity.com/blog/meeting-notes-workflow/): A simple AI workflow for turning a transcript or rough notes into decisions, owners and a follow-up email, without losing what was said.
- [Prompts vs skills: which one do you need?](https://promptlexity.com/blog/prompts-vs-skills/): A prompt is a request you send once. A skill is a standing set of instructions your assistant reuses. Here is when to use each.
- [The context window, explained without the jargon](https://promptlexity.com/blog/context-window-explained/): Why AI chats forget things, why long documents get skimmed, and what you can do about it. The context window in plain English.
- [Why AI makes things up, and how to make it stop](https://promptlexity.com/blog/why-ai-makes-things-up/): AI hallucinations explained in plain English: why models invent facts and sources, and five prompt habits that make it much less likely.
- [Why one example beats five adjectives in a prompt](https://promptlexity.com/blog/examples-beat-adjectives/): Words like punchy, friendly and professional mean different things to everyone. A short example tells the model exactly what you mean.
- [Write your first AI skill in 15 minutes](https://promptlexity.com/blog/write-your-first-skill/): A skill is a folder with one text file. Here is how to write the name, the description and the instructions so your assistant uses it well.
- [Full library in markdown](https://promptlexity.com/llms-full.txt): every prompt and glossary term in one file
- [Library as JSON](https://promptlexity.com/prompts.json): structured data for every prompt and term