FindPrompts
Sign InGet Started

Get the best new prompts every week

Join the FindPrompts newsletter — top prompts, fresh mastery guides, and AI workflow tips. Free, no spam.

FindPrompts

The largest AI prompts database. 30,000+ prompts for ChatGPT, Claude, Midjourney, and more.

Categories

  • Marketing
  • Business
  • Writing
  • Coding
  • Education

Platforms

  • ChatGPT
  • Claude
  • Gemini
  • Grok
  • Midjourney

Resources

  • Best AI Prompts
  • Free Tools
  • Prompt Grader
  • Prompt Templatizer
  • AI Token Counter
  • Image Prompt Generator
  • System Prompt Generator
  • Prompt A/B Tester
  • Prompt-to-JSON
  • Headline Generator
  • AI Cost Calculator
  • AI Prompt Improver
  • Prompt Generators
  • Mastery Guides
  • Cheatsheets
  • Automations
  • AI Tools
  • Custom GPTs
  • Blog
  • Affiliate Program

Company

  • Pricing
  • Contact
  • Terms of Service
  • Privacy Policy

© 2026 FindPrompts. All rights reserved.

TwitterGitHub
FindPrompts
FindPrompts

Main

Dashboard
Prompt Library30k+
DiscoverHot
LeaderboardNew
BundlesNew
Prompt Maker
PlaygroundBeta
GeneratorsNew
WorkflowsPro

Personal

Compare
Prompt Improver
Prompt Grader
Templatizer
Token Counter
Image Prompts
System Prompts
A/B Tester
All Free Tools
My Vault
Analytics
Submit Prompt
AI Tools
Guides
Cheatsheets
Automations
Settings
Go Pro

Unlock workflows, API access, and premium features.

Upgrade Now

User

Command Palette

Search for a command to run...

HomeCheatsheetsPrompt Engineering Cheatsheet
Prompt Engineering6 min

Prompt Engineering Cheatsheet

A model-agnostic reference for the prompting techniques that actually move the needle. Use it to structure prompts, control output, and reason through hard tasks.

Core Techniques

Zero-shotAsk directly with no examples. Best for simple, well-known tasks.
Few-shotInclude 2-5 input/output examples to show the desired pattern and format.
Chain-of-thoughtAdd "Think step by step" to force intermediate reasoning before the answer.
Role promptingAssign a persona: "You are a senior tax accountant." Sets tone and expertise.
DecompositionBreak a complex task into ordered sub-tasks the model solves one at a time.
Self-consistencyGenerate multiple reasoning paths, then take the majority answer.
ReActInterleave Reasoning and Acting (tool calls) for agentic, multi-step tasks.

Structure & Clarity

DelimitersWrap inputs in triple quotes, ###, or XML tags so the model knows what is data.
Instructions firstPut the task at the top, supporting context below. Models weight the start heavily.
Be specificReplace "make it good" with measurable criteria (length, tone, audience).
Positive framingSay what to do, not just what to avoid. "Use plain English" beats "Don't be technical."
One ask per promptBundling unrelated requests degrades quality. Split into separate turns.

Controlling Output

Output formatSpecify exactly: "Return JSON with keys title, body, tags."
Length controlSet hard limits: "Max 3 sentences" or "Exactly 5 bullet points."
Tone & styleName the register: formal, casual, witty, academic, or "like Hemingway."
Schema / templateProvide a fill-in-the-blank template the model must complete verbatim.
Refusal handlingAdd "If you are unsure, say so" to reduce confident hallucinations.

Advanced Reasoning

Step-back promptingAsk for the general principle first, then apply it to the specific case.
Tree-of-thoughtExplore several branches, evaluate each, then expand the most promising.
Plan then executeHave the model draft a plan, confirm it, then carry it out.
Critique & reviseAsk the model to find flaws in its own answer, then produce a v2.
Rubric scoringGive a scoring rubric so the model self-evaluates against your criteria.

Reducing Hallucination

GroundingProvide source text and instruct: "Answer only from the context above."
Cite sourcesRequire quotes or references for every factual claim.
"I don't know" licenseExplicitly allow the model to admit uncertainty instead of guessing.
TemperatureLower it (0-0.3) for factual tasks, raise it (0.7-1.0) for creative ones.
Verify with a second passRun a separate prompt that fact-checks the first output.

Common Pitfalls

Vague verbs"Analyze" and "optimize" mean nothing without criteria. Define them.
Buried instructionsKey rules lost in long context get ignored. Repeat them at the end.
Overloading contextMore text is not better. Irrelevant info dilutes attention.
Leading examplesBiased few-shot examples make the model copy your mistakes.
No success criteriaIf you can't tell good from bad output, neither can the model.

Want ready-to-use prompts to go with this cheatsheet?

Browse 30,000+ Prompts