01

Log in Start free

18 prompts

Fundamentals AI Prompts

Every fundamentals prompt in the library — tested, copy-ready, and tagged with the model it works best on. Free to use in personal or commercial work.

ChatGPTFundamentals

The 5-Part Prompt Framework — ChatGPT

Every strong prompt combines five parts: Role (who the AI should act as), Context (background info it needs), Task (the specific ask), Format (how you want the output structured), and Constraints (length, tone, things to avoid).

You are a senior email marketer. Context: I run a 3-person SaaS startup selling project management software to freelancers. Task: …

ClaudeFundamentals

The 5-Part Prompt Framework — Claude

Every strong prompt combines five parts: Role (who the AI should act as), Context (background info it needs), Task (the specific ask), Format (how you want the output structured), and Constraints (length, tone, things to avoid).

Role: You are a meticulous technical editor. Context: The attached text is a beginner tutorial on Python loops. Task: Rewrite it f…

ChatGPTFundamentals

Zero-Shot vs Few-Shot Prompting — ChatGPT

Zero-shot means asking directly with no examples.

Classify each review as Positive, Negative, or Neutral. Review: "Delivery was fast but the box arrived damaged." -> Neutral Revie…

GrokFundamentals

Zero-Shot vs Few-Shot Prompting — Grok

Zero-shot means asking directly with no examples.

Here are 3 examples of turning a boring headline into a punchy one: "5 Tips for Productivity" -> "Stop Wasting Your Mornings: 5 Pr…

ChatGPTFundamentals

Chain-of-Thought Prompting — ChatGPT

Asking a model to "think step by step" before answering measurably improves accuracy on reasoning, math, and multi-step logic tasks because it forces the model to externalize intermediate steps instead of jumping to a guess..

A customer has a $1,200 budget. Product A costs $340 and lasts 2 years. Product B costs $610 and lasts 4 years. Which has the bett…

ClaudeFundamentals

Chain-of-Thought Prompting — Claude

Asking a model to "think step by step" before answering measurably improves accuracy on reasoning, math, and multi-step logic tasks because it forces the model to externalize intermediate steps instead of jumping to a guess..

Before answering, list the 3 possible root causes of this bug, evaluate each against the stack trace below, then state which is mo…

ChatGPTFundamentals

Structured Output (JSON & Tables) — ChatGPT

When you need output your app or spreadsheet can actually use, explicitly request a schema.

Extract the following fields from this job listing as JSON only, no extra text: { "title": string, "company": string, "location": …

Hugging Face (open-source)Fundamentals

Structured Output (JSON & Tables) — Hugging Face (open-source)

When you need output your app or spreadsheet can actually use, explicitly request a schema.

System: Respond only with valid JSON matching this schema: {"summary": string, "sentiment": "positive"|"neutral"|"negative", "keyw…

PerplexityFundamentals

ChatGPT vs Claude vs Perplexity vs Grok — Perplexity

The same task often needs a slightly different prompt style per model.

What are the three most significant changes to [topic] in the last 6 months? Cite sources for each claim and note the publish date…

GrokFundamentals

ChatGPT vs Claude vs Perplexity vs Grok — Grok

The same task often needs a slightly different prompt style per model.

Give me a quick, no-fluff rundown of what people are currently saying about [topic] — what's the general sentiment right now?…

ChatGPTFundamentals

Role + Constraints to Kill Vagueness — ChatGPT

When answers are generic, the fix is almost always more specificity, not a longer prompt.

You are a conversion copywriter for B2B SaaS. Rewrite this headline for a CFO audience. Constraints: under 12 words, lead with a q…

ClaudeFundamentals

Role + Constraints to Kill Vagueness — Claude

When answers are generic, the fix is almost always more specificity, not a longer prompt.

Act as a plain-language editor for a 10-year-old reader. Rewrite the paragraph below at a 5th-grade reading level, keep it under 8…

ChatGPTFundamentals

Ask-Before-Answer for Ambiguous Tasks

For open-ended requests, instruct the model to ask clarifying questions first.

I want help planning a product launch. Before you give any plan, ask me up to 5 clarifying questions about my product, audience, t…

ClaudeFundamentals

Self-Grading With a Rubric

Have the model score its own draft against an explicit rubric, then revise to hit the top score.

Write a 100-word product pitch for [PRODUCT]. Then score it 1-5 on: clarity, specificity, and persuasiveness. If any score is belo…

Any modelFundamentals

Prompt Chaining Architectures

Experts rarely use one mega-prompt.

STEP 1 (extract): From the customer interview below, extract pains, desired outcomes, and objections as JSON: {"pains":[],"outcome…

ClaudeFundamentals

Meta-Prompting: Prompts That Write Prompts

The fastest way to a great prompt is asking the model to write and critique one.

You are a prompt engineer. Task: I need a reusable prompt that turns raw meeting notes into a client-ready status email. Draft the…

Any modelFundamentals

Evaluating Prompts Like an Engineer

A prompt is good when it performs consistently, not when one output impressed you.

Here are 2 versions of a prompt and 5 test inputs. Run each version mentally against each input. Build a table: input × version → …

Any modelFundamentals

Project: A 3-Step Prompt Chain for Your Real Work

Deliverable: a documented, tested 3-step prompt chain that automates one recurring task from your actual work or studies. Steps: 1.

Act as my project reviewer. Here is my 3-step prompt chain and one test input with its output. Grade against: single-responsibilit…

Browse other categories

Automation (15)Coding (6)Image Generation (2)Marketing (16)Productivity (2)Research (8)Writing (18)