Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.
Getting high-quality responses from AI models starts with well-crafted questions. This guide progresses from basic principles to advanced techniques, helping you continuously improve your prompting skills.
The quality of AI responses directly correlates with the clarity and structure of your prompts. Small improvements in how you ask questions can dramatically improve results.
Basic Prompting Principles
The foundation of effective AI interaction:
Be clear and specific - Vague questions produce vague answers.
Use positive instructions - Focus on what you want, not what you don’t want.
Provide context - Give relevant background information to tailor responses.
Be clear and specific
The more specific your request, the better the response.Instead of:
Tell me about marketing.
Try:
Explain the three most effective digital marketing strategies for a B2B SaaS company with a $10,000 monthly budget.
Use positive instructions
Focus on what you want the AI to do, rather than what you don’t want.Instead of:
Don't be too technical.
Try:
Explain this in simple terms that a non-technical business owner would understand.
Provide context
Give the AI relevant background information to tailor its response.Example:
I'm a product manager at a fintech startup. We're deciding between microservices and monolithic architecture for our MVP. What factors should we consider given our 3-month launch timeline and team of 4 developers?
Think of the AI as a knowledgeable colleague who needs context to give you the best advice.
Context Setting Techniques
Proper context ensures the AI understands your goals, audience, and constraints.
Define Your Audience
Specify who will use or read the response to adjust complexity and tone.
Set the Scope
Clearly define boundaries to prevent overly broad or narrow responses.
Provide Examples
Show examples of what you’re looking for to guide the output style.
State Your Goal
Explain what you’ll do with the response to get more actionable results.
Effective Context-Setting Pattern
Use this structure to provide comprehensive context:
[Role/Perspective]: I'm a [your role] working on [project/task][Situation]: Currently, [describe your situation]🎯 [GOAL]: What I need to achieve📏 [SCOPE - Constraints]: - [Constraint 1]- [Constraint 2]- [Constraint 3]👥 [AUDIENCE]: Who will use/read this or explain the format the output needs to have💡 [EXAMPLES]: Relevant examples or current approach (if applicable)[OUTPUT]: Specify the exact format you want for the answer here. For example, request a table, summary, list of action steps, email draft, or bullet points - whatever would be most useful for your people or stakeholders.[Your specific question]
Example:
Role: I'm a data analyst at a healthcare startupSituation: We have patient satisfaction survey data from 500 respondents across 3 clinic locations over 6 months.🎯 GOAL: Identify the top 3 factors affecting patient satisfaction to present to our executive team📏 SCOPE - Constraints:- Focus on actionable insights our clinics can implement- Results must be statistically significant (p < 0.05)- 6-month timeframe across 3 clinic locations- Use Tableau for data visualization (required by our organization)👥 AUDIENCE: Non-technical executives who need clear, actionable insights- Prefer visual presentations over raw statistics- Need to understand business impact💡 EXAMPLES: Current approach includes basic satisfaction scores, but executives have requested deeper analysis linking satisfaction to specific operational factorsOutput:Please provide your answer in the following format:- [Factor Name]: [Brief explanation or insight]- [Factor Name]: [Brief explanation or insight]- [Factor Name]: [Brief explanation or insight]For example:- Waiting times: How quickly patients are attended impacts satisfaction- Staff friendliness: Positive staff interactions improve experience- Clarity of instructions: Patients value clear after-visit informationQuestion: What analysis approach would you recommend, and what visualization types should I use for the executive presentation?
This structure applies all four context-setting techniques: stating your goal 🎯, defining your audience 👥, setting the scope 📏, and providing relevant examples 💡.
See It In Action: Video Example
Watch the following video for a practical demonstration of using these best practices to instruct an AI agent and achieve high-quality results.
This video guides you step-by-step in applying clarity, positive instructions, and effective context setting when prompting an AI agent.
Structured Output Requests
Requesting specific formats helps you get responses that are immediately usable.
Lists and Bullet Points
Request organized information in scannable format.Example:
List the 5 most important considerations when choosing a database for a real-time analytics platform. For each point:- State the consideration- Explain why it matters- Provide one concrete example
Tables and Comparisons
Get side-by-side comparisons for decision-making.Example:
Create a comparison table of React, Vue, and Angular with these columns:- Framework name- Learning curve (easy/moderate/steep)- Best use case- Community size- Enterprise adoption
Step-by-Step Instructions
Request procedures in sequential format.Example:
Provide step-by-step instructions to set up CI/CD for a Node.js application using GitHub Actions. Include:1. Prerequisites needed2. Each configuration step3. How to verify each step worked4. Common troubleshooting tips
Code Examples
Request working code with explanations.Example:
Write a Python function to validate email addresses using regex.Include:- Complete, runnable code with type hints- Inline comments explaining the regex pattern- Example usage- Edge cases it handles
Output Length and Format
Specify desired length and structure to get appropriately detailed responses.Examples:
Summarize this in exactly 3 bullet points.Provide a comprehensive analysis (approximately 500 words).Give me a brief one-sentence answer first, then expand with details.
Prompt Engineering
Use tailored prompt engineering strategies to get high-quality, targeted responses from AI. Choose the approach that matches your needs and your current experience level.
Basic Strategies
Advanced Techniques
Master these foundational techniques to consistently get better results:
Iterative refinement
Don’t expect the perfect answer on your first try. Adjust your prompt each time based on the previous AI response.
1
Start with a basic prompt
Begin with a clear but simple question.
Explain how context windows work in AI models.
2
Evaluate the response
Check if the answer meets your needs. Was it too technical, too vague, or off-topic?
3
Refine and add specificity
Adjust your question to clarify what you want.
Explain how context windows work in AI models in simple terms. Use an analogy to help a non-technical person understand, and explain why this matters for everyday AI users.
4
Iterate until satisfied
Repeat this process until the answer matches your needs.
You’ll learn what works best for your goals by refining each time.
Building on responses
Use the AI’s previous answers as a springboard for further exploration or greater depth.Pattern:
First prompt: "Explain the benefits of microservices architecture."Follow-up: "You mentioned scalability as a key benefit. Can you provide a concrete example of how microservices enabled scalability for a company handling rapid growth?"Further follow-up: "Given those scalability benefits, what are the main challenges small teams face when adopting microservices?"
This approach leads to more natural, conversational, and productive exploration of complex topics.
Assign roles for perspective
Ask the AI to take on a specific professional or subject matter expert role.Example:
You are an experienced DevOps engineer with expertise in Kubernetes. Review this deployment configuration and identify potential security vulnerabilities and performance bottlenecks.[Your configuration here]
Use constraints effectively
Clearly specify response rules to limit scope, structure, or style.Example:
Analyze this dataset with the following constraints:- Focus only on Q4 2024 data- Exclude outliers beyond 2 standard deviations- Present findings in order of business impact- Include statistical confidence levels
Level up your prompting with these more sophisticated approaches:
Chain-of-thought prompting
Ask for step-by-step reasoning to see how the AI arrives at a solution.Example:
Solve this problem step-by-step, explaining your reasoning at each stage:Our e-commerce site has a 68% cart abandonment rate. Average cart value is $120. We have 50,000 monthly visitors with a 12% add-to-cart rate. Calculate the potential monthly revenue increase if we reduce abandonment to 55%, and explain what interventions might achieve this.Show your calculations and reasoning for each step.
Why it works: Step-by-step requests generate more transparent, verifiable answers and reduce mistakes.
Few-shot learning
Show a few example inputs and the type of answers you expect. The AI will mimic your structure and approach.Example:
I'll show you examples of customer feedback and how I want them categorized, then you categorize new feedback the same way:Example 1:Feedback: "The app crashes every time I try to upload photos"Category: Bug - CriticalSentiment: FrustratedAction: Escalate to engineeringExample 2:Feedback: "Love the new dark mode! Makes it easier to use at night"Category: Feature feedback - PositiveSentiment: SatisfiedAction: Share with product teamExample 3:Feedback: "It would be great if we could export data to CSV"Category: Feature requestSentiment: NeutralAction: Add to feature backlogNow categorize this feedback:"The search function doesn't find exact matches sometimes"
Zero-shot prompting
Use this when your task is simple and expectations are obvious - no examples needed.Best for:
Clear tasks like summarization, translation, or classification
When you want unbiased answers
Example:
Translate the following English text to French, maintaining the professional tone:[Your text here]
Prompt chaining
Break bigger challenges into smaller, sequential prompts. Use the output from one step as the input to the next.Example sequence:
Prompt 1: "Extract all customer pain points mentioned in these support tickets: [tickets]"Prompt 2: "Take these pain points: [output from prompt 1] and group them into themes."Prompt 3: "For each theme: [output from prompt 2], suggest one product improvement that addresses multiple pain points."
Why chain prompts:
Breaks up complex tasks
Lets you check (and fix) partial steps
Increases accuracy on multi-stage workflows
Template creation
Save time by building your own prompt templates for tasks you repeat often. Store them in the Prompt Library.Template Example:
Analyze this {{document_type}} for a {{target_audience}} audience.Document:{{content}}Provide:1. Executive summary (2-3 sentences)2. Key insights (3-5 bullet points)3. Recommended actions4. Potential risks or considerationsFormat: {{output_format:bullets|paragraphs|table}}
For details on managing and sharing prompts, see the Prompt Library.
Using tools in prompts
Direct the AI to use plugins or integrations when available, like business data connectors.Example:
Use the database connection tool to query our customer table and find all customers who signed up in the last 30 days but haven't made a purchase. Then analyze the data and suggest targeted retention strategies.
For further learning on prompt engineering, see guides from OpenAI, Anthropic, and Google.
Common Mistakes to Avoid
Being Too Vague
Problem: “Tell me about AI.”Better: “Explain the key differences between supervised and unsupervised machine learning for a business analyst evaluating which approach to use for customer segmentation.”
Asking Multiple Questions at Once
Problem: “How do I improve our SEO, should we use social media ads, and what content strategy works best for B2B?”Better: Break into separate, focused prompts or explicitly request separate treatment of each question.
Providing No Context
Problem: “Is this a good approach?” [without explaining what ‘this’ is or what your goals are]Better: Provide the approach, your context, your goals, and criteria for “good.”
Assuming Prior Knowledge
Problem: Starting a new conversation with “Continue from where we left off” without re-establishing context.Why this fails: Each new conversation starts with its own context window, so the AI can’t automatically read what was discussed in a different, unrelated conversation.
If your organization has enabled Memories or Projects, the AI can carry some context across conversations automatically. Otherwise, learn more about context windows in Conversation Management.
Better: Briefly summarize relevant context from previous conversations when starting a new chat, or group related work in a Project so context is shared automatically.
Best Practices Summary
Start Simple
Begin with a clear basic prompt, then add complexity as needed.
Be Specific
Vague questions get vague answers. Provide details and context.
Iterate
Refine your prompts based on the responses you receive.
Save What Works
Build a library of effective prompts for recurring tasks.
The best prompt is one that gets you the result you need. Experiment with different approaches and learn what works for your use cases.
Next Steps
Conversation Management
Learn how to manage long conversations and understand context windows.
Prompt Library
Save and reuse your best prompts with variables for efficiency.
Choosing a Model
Pick the right model size, or let the Router choose for you.
Was this page helpful?
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"WonkaChat Wiki","colors":{"primary":"#2f6de0","light":"#75a3fd","dark":"#2f6de0"},"logo":{"light":"https://mintcdn.com/wonkaai/sJA7XYqvmb80Vuja/logo/wonka-logo-black.svg?fit=max\u0026auto=format\u0026n=sJA7XYqvmb80Vuja\u0026q=85\u0026s=dea1abfec97032f9ea8a961f35923e31","dark":"https://mintcdn.com/wonkaai/sJA7XYqvmb80Vuja/logo/wonka-logo-white.svg?fit=max\u0026auto=format\u0026n=sJA7XYqvmb80Vuja\u0026q=85\u0026s=49741e373dbbcf97407c5dd3cbcb63e2","href":"https://www.wonka-ai.com"},"favicon":"https://mintcdn.com/wonkaai/sJA7XYqvmb80Vuja/favicon.png?fit=max\u0026auto=format\u0026n=sJA7XYqvmb80Vuja\u0026q=85\u0026s=b30e81d48064a0b4cf0bc9c0d51689c3","background":{"color":{"light":"#ffffff","dark":"#0e1a16"}},"footer":{"socials":{"linkedin":"https://www.linkedin.com/company/wonka-ai","instagram":"https://www.instagram.com/meetwonka"}},"fonts":{"heading":{"family":"GT Sectra","weight":400,"source":"fonts/GT-Sectra-Regular.woff2","format":"woff2"},"body":{"family":"Inter Display","weight":400,"source":"fonts/InterDisplay-Regular.woff2","format":"woff2"}},"banner":{"content":"🚧 Beta Version some errors might be present | Version Bêta des erreurs peuvent être présentes | Bètaversie er kunnen fouten aanwezig zijn 🚧","dismissible":false},"errors":{"404":{"redirect":false,"title":"Your page can't be found | Votre page est introuvable | Je pagina kan niet worden gevonden","description":"Please, go ask **WonkaChat** to help you find what you're looking for, I am sure it can help you! | Veuillez demander à **WonkaChat** de vous aider à trouver ce que vous cherchez, je suis sûr qu'il peut vous aider ! | Vraag **WonkaChat** om je te helpen vinden wat je zoekt, ik weet zeker dat het je kan helpen!"}},"contextual":{"options":["copy","view","chatgpt","claude","perplexity","mcp","cursor","vscode"],"display":"header"},"styling":{"latex":false},"navigation":{"languages":[{"language":"en","href":"en/welcome/introduction"},{"language":"fr-CA","href":"fr/welcome/introduction"},{"language":"nl","href":"nl/welcome/introduction"},{"language":"fr","href":"fr/welcome/introduction"}]}},"deployment":{"deploymentMetadataValue":{"subdomain":"wonkaai","hasAudioNarration":false,"actualSubdomain":"wonkaai","customDomains":["help.wonka.chat"],"gitSource":{"type":"github","owner":"meetwonka","repo":"starter","deployBranch":"main","contentDirectory":"","isPrivate":false,"mountPath":"","label":""},"feedback":{"edits":false,"thumbs":true,"issues":false},"entitlements":{},"buildId":"6ad144d7ca6e4f21c0f19188","clientVersion":"0.0.4263","searchFilterCounts":[{"language":"en","tag":"WonkaChat","count":51},{"language":"fr","tag":"WonkaChat","count":51},{"language":"nl","tag":"WonkaChat","count":51},{"language":"en","tag":"Improved Usage","count":12},{"language":"fr","tag":"Utilisation améliorée","count":12},{"language":"nl","tag":"Verbeterd gebruik","count":12},{"language":"en","tag":"AI Agents","count":8},{"language":"fr","tag":"Agents IA","count":8},{"language":"nl","tag":"AI-Agents","count":8},{"language":"en","tag":"Administration","count":6},{"language":"en","tag":"Tools \u0026 Connection","count":6},{"language":"fr","tag":"Administration","count":6},{"language":"fr","tag":"Outils et connexion","count":6},{"language":"nl","tag":"Beheer","count":6},{"language":"nl","tag":"Tools en verbinding","count":6},{"language":"en","tag":"Legal","count":5},{"language":"en","tag":"Security \u0026 Governance","count":5},{"language":"fr","tag":"Légal","count":5},{"language":"fr","tag":"Sécurité et gouvernance","count":5},{"language":"nl","tag":"Juridisch","count":5},{"language":"nl","tag":"Beveiliging en governance","count":5},{"language":"en","tag":"Support \u0026 Resources","count":3},{"language":"en","tag":"Welcome to WonkaChat","count":3},{"language":"fr","tag":"Support et ressources","count":3},{"language":"fr","tag":"Bienvenue dans WonkaChat","count":3},{"language":"nl","tag":"Support en bronnen","count":3},{"language":"nl","tag":"Welkom bij WonkaChat","count":3},{"language":"en","tag":"Pricing \u0026 Plans","count":2},{"language":"fr","tag":"Tarifs et forfaits","count":2},{"language":"nl","tag":"Prijzen en pakketten","count":2}]},"assistantConfig":{},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[{"name":"kill-isr","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-rbac-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-mintlify-slack","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-integrations-settings","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"rbac-expansion","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-pr-grouping","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-prefix","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"analytics-v7","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"user-flows-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"no-publish-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-onboarding","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving-live","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"stripTemperatureMiddleware","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"support-platform-pylon-zendesk","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"instant-rollback","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications-server","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-fable","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fixed-ai-action-pricing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"site-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automation-resolve-merge-conflict","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"scoped-publishing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"mintql","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"page-level-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-version-history-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"billing-page-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"full-page-search","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workspace-projects","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"assistant-v5","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fork-pr-previews","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"revalidation-jwt","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-sso-scim","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"hobby-abuse-scan","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"dashboard-inbox","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-signup","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-dual-write","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-enabled","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"approve-review-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-metadata","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-serve","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"live-agents","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"starter-pricing","enabled":true,"variant":{"name":"control","enabled":true,"payload":{"type":"string","value":"control"},"feature_enabled":true},"impressionData":false},{"name":"llms-txt-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"wildcard-email-auth","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":false},"customCss":[{"filePath":"style.css","content":"@font-face{font-family:\"Inter Display\";src:url(\"/fonts/InterDisplay-Medium.woff2\") format(\"woff2\");font-weight:500;font-style:normal;font-display:swap}:root{--wonka-black: #0e1a16;--wonka-light-brown: #76766b;--wonka-dark-gray: #d9d9d5;--wonka-gray: #f6f6f4;--wonka-blue-600: #2f6de0;--wonka-blue-400: #75a3fd;--wonka-radius-sm: 0.5rem;--wonka-font-mono: \"Cascadia Mono\", \"Segoe UI Mono\", ui-monospace, monospace}h1,h2,h3,h4{font-weight:400!important;letter-spacing:-0.01em}html:not(.dark) h1,html:not(.dark) h2,html:not(.dark) h3,html:not(.dark) h4{color:var(--wonka-black)}html:not(.dark) body{color:var(--wonka-black)}strong,b{font-weight:500}code,pre,kbd{font-family:var(--wonka-font-mono)}#content-area a:not([class*=\"card\"]){text-decoration-color:var(--wonka-blue-600)}html:not(.dark) #content-area .card,html:not(.dark) #content-area [class*=\"callout\"]{border-color:var(--wonka-dark-gray)}#content-area .card,#content-area [class*=\"callout\"],#content-area pre,#content-area img{border-radius:var(--wonka-radius-sm)}#sidebar-content .sidebar-group-header,#sidebar-content h5{font-family:\"Inter Display\", ui-sans-serif, system-ui, sans-serif;font-weight:500;letter-spacing:0.02em}html.dark #content-area{color:#ffffff}"}]}
{"page":{"pagePath":"en/improved-usage/asking-great-questions","slug":"/en/improved-usage/asking-great-questions","pageMetadata":{"title":"Asking Great Questions","description":"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.","href":"/en/improved-usage/asking-great-questions"},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n p: \"p\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsx(_components.p, {\n children: \"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.\"\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx,jsxs:_jsxs}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){const _components={a:`a`,code:`code`,hr:`hr`,li:`li`,p:`p`,pre:`pre`,span:`span`,strong:`strong`,ul:`ul`,..._provideComponents(),...props.components},{Accordion,AccordionGroup,Card,CardGroup,Check,CodeBlock,Heading,Info,OptimizedFrame,Step,Steps,Tab,Tabs,Tip}=_components;if(!Accordion)_missingMdxReference(`Accordion`,true);if(!AccordionGroup)_missingMdxReference(`AccordionGroup`,true);if(!Card)_missingMdxReference(`Card`,true);if(!CardGroup)_missingMdxReference(`CardGroup`,true);if(!Check)_missingMdxReference(`Check`,true);if(!CodeBlock)_missingMdxReference(`CodeBlock`,true);if(!Heading)_missingMdxReference(`Heading`,true);if(!Info)_missingMdxReference(`Info`,true);if(!OptimizedFrame)_missingMdxReference(`OptimizedFrame`,true);if(!Step)_missingMdxReference(`Step`,true);if(!Steps)_missingMdxReference(`Steps`,true);if(!Tab)_missingMdxReference(`Tab`,true);if(!Tabs)_missingMdxReference(`Tabs`,true);if(!Tip)_missingMdxReference(`Tip`,true);return _jsxs(_Fragment,{children:[_jsx(_components.p,{children:`Getting high-quality responses from AI models starts with well-crafted questions. This guide progresses from basic principles to advanced techniques, helping you continuously improve your prompting skills.`}),`\n`,_jsx(Info,{children:_jsx(_components.p,{children:`The quality of AI responses directly correlates with the clarity and structure of your prompts. Small improvements in how you ask questions can dramatically improve results.`})}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`basic-prompting-principles`,children:`Basic Prompting Principles`}),`\n`,_jsx(_components.p,{children:`The foundation of effective AI interaction:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Be clear and specific`}),` - Vague questions produce vague answers.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Use positive instructions`}),` - Focus on what you want, not what you don’t want.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Provide context`}),` - Give relevant background information to tailor responses.`]}),`\n`]}),`\n`,_jsxs(AccordionGroup,{children:[_jsxs(Accordion,{title:`Be clear and specific`,icon:`bullseye`,id:`be-clear-and-specific`,children:[_jsx(_components.p,{children:`The more specific your request, the better the response.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Instead of:`})}),_jsx(CodeBlock,{numberOfLines:`2`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`2`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Tell me about marketing.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Try:`})}),_jsx(CodeBlock,{numberOfLines:`3`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`3`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Explain the three most effective digital marketing strategies for `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`a B2B SaaS company with a $10,000 monthly budget.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Use positive instructions`,icon:`check`,id:`use-positive-instructions`,children:[_jsx(_components.p,{children:`Focus on what you want the AI to do, rather than what you don’t want.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Instead of:`})}),_jsx(CodeBlock,{numberOfLines:`2`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`2`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Don't be too technical.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Try:`})}),_jsx(CodeBlock,{numberOfLines:`3`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`3`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Explain this in simple terms that a non-technical business owner `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`would understand.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Provide context`,icon:`circle-info`,id:`provide-context`,children:[_jsx(_components.p,{children:`Give the AI relevant background information to tailor its response.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`5`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`5`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`I'm a product manager at a fintech startup. We're deciding between `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`microservices and monolithic architecture for our MVP. What factors `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`should we consider given our 3-month launch timeline and team of `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`4 developers?`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsx(Tip,{children:_jsx(_components.p,{children:`Think of the AI as a knowledgeable colleague who needs context to give you the best advice.`})})]})]}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`context-setting-techniques`,children:`Context Setting Techniques`}),`\n`,_jsx(_components.p,{children:`Proper context ensures the AI understands your goals, audience, and constraints.`}),`\n`,_jsxs(CardGroup,{cols:2,children:[_jsx(Card,{title:`Define Your Audience`,icon:`users`,children:_jsx(_components.p,{children:`Specify who will use or read the response to adjust complexity and tone.`})}),_jsx(Card,{title:`Set the Scope`,icon:`bullseye`,children:_jsx(_components.p,{children:`Clearly define boundaries to prevent overly broad or narrow responses.`})}),_jsx(Card,{title:`Provide Examples`,icon:`lightbulb`,children:_jsx(_components.p,{children:`Show examples of what you’re looking for to guide the output style.`})}),_jsx(Card,{title:`State Your Goal`,icon:`flag-checkered`,children:_jsx(_components.p,{children:`Explain what you’ll do with the response to get more actionable results.`})})]}),`\n`,_jsx(Heading,{level:`3`,id:`effective-context-setting-pattern`,children:`Effective Context-Setting Pattern`}),`\n`,_jsx(_components.p,{children:`Use this structure to provide comprehensive context:`}),`\n`,_jsx(CodeBlock,{numberOfLines:`19`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`19`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`[Role/Perspective]: I'm a [your role] working on [project/task]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`[Situation]: Currently, [describe your situation]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`🎯 [GOAL]: What I need to achieve`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`📏 [SCOPE - Constraints]: `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- [Constraint 1]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- [Constraint 2]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- [Constraint 3]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`👥 [AUDIENCE]: Who will use/read this or explain the format the output needs to have`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`💡 [EXAMPLES]: Relevant examples or current approach (if applicable)`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`[OUTPUT]: Specify the exact format you want for the answer here. For example, request a table, summary, list of action steps, email draft, or bullet points - whatever would be most useful for your people or stakeholders.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`[Your specific question]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),`\n`,_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),`\n`,_jsx(CodeBlock,{numberOfLines:`37`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`37`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Role: I'm a data analyst at a healthcare startup`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Situation: We have patient satisfaction survey data from 500 respondents `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`across 3 clinic locations over 6 months.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`🎯 GOAL: Identify the top 3 factors affecting patient satisfaction to `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`present to our executive team`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`📏 SCOPE - Constraints:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Focus on actionable insights our clinics can implement`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Results must be statistically significant (p \u003c 0.05)`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- 6-month timeframe across 3 clinic locations`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Use Tableau for data visualization (required by our organization)`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`👥 AUDIENCE: Non-technical executives who need clear, actionable insights`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Prefer visual presentations over raw statistics`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Need to understand business impact`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`💡 EXAMPLES: Current approach includes basic satisfaction scores, but `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`executives have requested deeper analysis linking satisfaction to specific `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`operational factors`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Output:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Please provide your answer in the following format:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- [Factor Name]: [Brief explanation or insight]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- [Factor Name]: [Brief explanation or insight]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- [Factor Name]: [Brief explanation or insight]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`For example:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Waiting times: How quickly patients are attended impacts satisfaction`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Staff friendliness: Positive staff interactions improve experience`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Clarity of instructions: Patients value clear after-visit information`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Question: What analysis approach would you recommend, and what `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`visualization types should I use for the executive presentation?`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),`\n`,_jsx(Check,{children:_jsxs(_components.p,{children:[`This structure applies all four context-setting techniques: `,_jsx(_components.strong,{children:`stating your goal`}),` 🎯, `,_jsx(_components.strong,{children:`defining your audience`}),` 👥, `,_jsx(_components.strong,{children:`setting the scope`}),` 📏, and `,_jsx(_components.strong,{children:`providing relevant examples`}),` 💡.`]})}),`\n`,_jsx(Heading,{level:`3`,id:`see-it-in-action-video-example`,children:`See It In Action: Video Example`}),`\n`,_jsx(_components.p,{children:`Watch the following video for a practical demonstration of using these best practices to instruct an AI agent and achieve high-quality results.`}),`\n`,_jsx(OptimizedFrame,{className:`mint-w-full mint-aspect-video mint-rounded-xl`,src:`https://www.youtube.com/embed/rfY0m-yQ3fE`,title:`How to Write Effective Instructions for an AI Agent`,frameBorder:`0`,allow:`accelerometer; clipboard-write; encrypted-media; gyroscope; picture-in-picture`,allowFullScreen:true}),`\n`,_jsx(Info,{children:_jsx(_components.p,{children:`This video guides you step-by-step in applying clarity, positive instructions, and effective context setting when prompting an AI agent.`})}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`structured-output-requests`,children:`Structured Output Requests`}),`\n`,_jsx(_components.p,{children:`Requesting specific formats helps you get responses that are immediately usable.`}),`\n`,_jsxs(AccordionGroup,{children:[_jsxs(Accordion,{title:`Lists and Bullet Points`,icon:`list`,id:`lists-and-bullet-points`,children:[_jsx(_components.p,{children:`Request organized information in scannable format.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`6`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`6`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`List the 5 most important considerations when choosing a database `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`for a real-time analytics platform. For each point:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- State the consideration`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Explain why it matters`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Provide one concrete example`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Tables and Comparisons`,icon:`table`,id:`tables-and-comparisons`,children:[_jsx(_components.p,{children:`Get side-by-side comparisons for decision-making.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`7`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`7`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Create a comparison table of React, Vue, and Angular with these columns:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Framework name`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Learning curve (easy/moderate/steep)`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Best use case`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Community size`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Enterprise adoption`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Step-by-Step Instructions`,icon:`list-ol`,id:`step-by-step-instructions`,children:[_jsx(_components.p,{children:`Request procedures in sequential format.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`7`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`7`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Provide step-by-step instructions to set up CI/CD for a Node.js `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`application using GitHub Actions. Include:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`1. Prerequisites needed`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`2. Each configuration step`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`3. How to verify each step worked`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`4. Common troubleshooting tips`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Code Examples`,icon:`code`,id:`code-examples`,children:[_jsx(_components.p,{children:`Request working code with explanations.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`7`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`7`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Write a Python function to validate email addresses using regex.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Include:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Complete, runnable code with type hints`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Inline comments explaining the regex pattern`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Example usage`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Edge cases it handles`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Output Length and Format`,icon:`book`,id:`output-length-and-format`,children:[_jsx(_components.p,{children:`Specify desired length and structure to get appropriately detailed responses.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Examples:`})}),_jsx(CodeBlock,{numberOfLines:`4`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`4`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Summarize this in exactly 3 bullet points.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Provide a comprehensive analysis (approximately 500 words).`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Give me a brief one-sentence answer first, then expand with details.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]})]}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`prompt-engineering`,children:`Prompt Engineering`}),`\n`,_jsx(_components.p,{children:`Use tailored prompt engineering strategies to get high-quality, targeted responses from AI. Choose the approach that matches your needs and your current experience level.`}),`\n`,_jsxs(Tabs,{children:[_jsxs(Tab,{title:`Basic Strategies`,id:`basic-strategies`,children:[_jsx(_components.p,{children:`Master these foundational techniques to consistently get better results:`}),_jsxs(AccordionGroup,{children:[_jsxs(Accordion,{title:`Iterative refinement`,icon:`arrows-rotate`,id:`iterative-refinement`,children:[_jsx(_components.p,{children:`Don’t expect the perfect answer on your first try. Adjust your prompt each time based on the previous AI response.`}),_jsxs(Steps,{children:[_jsxs(Step,{title:`Start with a basic prompt`,children:[_jsx(_components.p,{children:`Begin with a clear but simple question.`}),_jsx(CodeBlock,{numberOfLines:`2`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`2`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Explain how context windows work in AI models.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsx(Step,{title:`Evaluate the response`,children:_jsx(_components.p,{children:`Check if the answer meets your needs. Was it too technical, too vague, or off-topic?`})}),_jsxs(Step,{title:`Refine and add specificity`,children:[_jsx(_components.p,{children:`Adjust your question to clarify what you want.`}),_jsx(CodeBlock,{numberOfLines:`4`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`4`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Explain how context windows work in AI models in simple terms. `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Use an analogy to help a non-technical person understand, and `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`explain why this matters for everyday AI users.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Step,{title:`Iterate until satisfied`,children:[_jsx(_components.p,{children:`Repeat this process until the answer matches your needs.`}),_jsx(Check,{children:_jsx(_components.p,{children:`You’ll learn what works best for your goals by refining each time.`})})]})]})]}),_jsxs(Accordion,{title:`Building on responses`,icon:`comments`,id:`building-on-responses`,children:[_jsx(_components.p,{children:`Use the AI’s previous answers as a springboard for further exploration or greater depth.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Pattern:`})}),_jsx(CodeBlock,{numberOfLines:`9`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`9`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`First prompt: \"Explain the benefits of microservices architecture.\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Follow-up: \"You mentioned scalability as a key benefit. Can you provide `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`a concrete example of how microservices enabled scalability for a company `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`handling rapid growth?\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Further follow-up: \"Given those scalability benefits, what are the main `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`challenges small teams face when adopting microservices?\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsx(Tip,{children:_jsx(_components.p,{children:`This approach leads to more natural, conversational, and productive exploration of complex topics.`})})]}),_jsxs(Accordion,{title:`Assign roles for perspective`,icon:`user-tie`,id:`assign-roles-for-perspective`,children:[_jsx(_components.p,{children:`Ask the AI to take on a specific professional or subject matter expert role.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`6`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`6`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`You are an experienced DevOps engineer with expertise in Kubernetes. `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Review this deployment configuration and identify potential security `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`vulnerabilities and performance bottlenecks.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`[Your configuration here]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Use constraints effectively`,icon:`sliders`,id:`use-constraints-effectively`,children:[_jsx(_components.p,{children:`Clearly specify response rules to limit scope, structure, or style.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`6`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`6`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Analyze this dataset with the following constraints:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Focus only on Q4 2024 data`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Exclude outliers beyond 2 standard deviations`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Present findings in order of business impact`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`- Include statistical confidence levels`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]})]})]}),_jsxs(Tab,{title:`Advanced Techniques`,id:`advanced-techniques`,children:[_jsx(_components.p,{children:`Level up your prompting with these more sophisticated approaches:`}),_jsxs(AccordionGroup,{children:[_jsxs(Accordion,{title:`Chain-of-thought prompting`,icon:`list-ol`,id:`chain-of-thought-prompting`,children:[_jsx(_components.p,{children:`Ask for step-by-step reasoning to see how the AI arrives at a solution.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`9`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`9`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Solve this problem step-by-step, explaining your reasoning at each stage:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Our e-commerce site has a 68% cart abandonment rate. Average cart `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`value is $120. We have 50,000 monthly visitors with a 12% add-to-cart `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`rate. Calculate the potential monthly revenue increase if we reduce `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`abandonment to 55%, and explain what interventions might achieve this.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Show your calculations and reasoning for each step.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Why it works:`}),` Step-by-step requests generate more transparent, verifiable answers and reduce mistakes.`]})]}),_jsxs(Accordion,{title:`Few-shot learning`,icon:`graduation-cap`,id:`few-shot-learning`,children:[_jsx(_components.p,{children:`Show a few example inputs and the type of answers you expect. The AI will mimic your structure and approach.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`24`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`24`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`I'll show you examples of customer feedback and how I want them `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`categorized, then you categorize new feedback the same way:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Example 1:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Feedback: \"The app crashes every time I try to upload photos\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Category: Bug - Critical`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Sentiment: Frustrated`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Action: Escalate to engineering`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Example 2:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Feedback: \"Love the new dark mode! Makes it easier to use at night\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Category: Feature feedback - Positive`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Sentiment: Satisfied`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Action: Share with product team`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Example 3:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Feedback: \"It would be great if we could export data to CSV\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Category: Feature request`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Sentiment: Neutral`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Action: Add to feature backlog`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Now categorize this feedback:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`\"The search function doesn't find exact matches sometimes\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Zero-shot prompting`,icon:`wand-magic-sparkles`,id:`zero-shot-prompting`,children:[_jsx(_components.p,{children:`Use this when your task is simple and expectations are obvious - no examples needed.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Best for:`})}),_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`Clear tasks like summarization, translation, or classification`}),`\n`,_jsx(_components.li,{children:`When you want unbiased answers`}),`\n`]}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`5`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`5`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Translate the following English text to French, maintaining the `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`professional tone:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`[Your text here]`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})})]}),_jsxs(Accordion,{title:`Prompt chaining`,icon:`link`,id:`prompt-chaining`,children:[_jsx(_components.p,{children:`Break bigger challenges into smaller, sequential prompts. Use the output from one step as the input to the next.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example sequence:`})}),_jsx(CodeBlock,{numberOfLines:`9`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`9`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Prompt 1: \"Extract all customer pain points mentioned in these `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`support tickets: [tickets]\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Prompt 2: \"Take these pain points: [output from prompt 1] `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`and group them into themes.\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Prompt 3: \"For each theme: [output from prompt 2], suggest `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`one product improvement that addresses multiple pain points.\"`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Why chain prompts:`})}),_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`Breaks up complex tasks`}),`\n`,_jsx(_components.li,{children:`Lets you check (and fix) partial steps`}),`\n`,_jsx(_components.li,{children:`Increases accuracy on multi-stage workflows`}),`\n`]})]}),_jsxs(Accordion,{title:`Template creation`,icon:`file-code`,id:`template-creation`,children:[_jsxs(_components.p,{children:[`Save time by building your own prompt templates for tasks you repeat often. Store them in the `,_jsx(_components.a,{href:`/en/improved-usage/prompt-library`,children:`Prompt Library`}),`.`]}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Template Example:`})}),_jsx(CodeBlock,{numberOfLines:`13`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`13`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Analyze this {{document_type}} for a {{target_audience}} audience.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Document:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`{{content}}`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Provide:`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`1. Executive summary (2-3 sentences)`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`2. Key insights (3-5 bullet points)`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`3. Recommended actions`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`4. Potential risks or considerations`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Format: {{output_format:bullets|paragraphs|table}}`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsx(Info,{children:_jsxs(_components.p,{children:[`For details on managing and sharing prompts, see the `,_jsx(_components.a,{href:`/en/improved-usage/prompt-library`,children:`Prompt Library`}),`.`]})})]}),_jsxs(Accordion,{title:`Using tools in prompts`,icon:`wrench`,id:`using-tools-in-prompts`,children:[_jsx(_components.p,{children:`Direct the AI to use plugins or integrations when available, like business data connectors.`}),_jsx(_components.p,{children:_jsx(_components.strong,{children:`Example:`})}),_jsx(CodeBlock,{numberOfLines:`4`,language:`text`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`text`,children:_jsxs(_components.code,{language:`text`,numberOfLines:`4`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`Use the database connection tool to query our customer table and find `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`all customers who signed up in the last 30 days but haven't made a `})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{children:`purchase. Then analyze the data and suggest targeted retention strategies.`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{})})]})})}),_jsx(Info,{children:_jsxs(_components.p,{children:[`For more on AI tool integration, visit `,_jsx(_components.a,{href:`/en/tools-connection/introduction`,children:`Tools Connection`}),`.`]})})]})]}),_jsx(Info,{children:_jsxs(_components.p,{children:[`For further learning on prompt engineering, see guides from `,_jsx(_components.a,{href:`https://platform.openai.com/docs/guides/prompt-engineering`,children:`OpenAI`}),`, `,_jsx(_components.a,{href:`https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview`,children:`Anthropic`}),`, and `,_jsx(_components.a,{href:`https://ai.google.dev/gemini-api/docs/prompting-intro`,children:`Google`}),`.`]})})]})]}),`\n`,_jsx(Heading,{level:`2`,id:`common-mistakes-to-avoid`,children:`Common Mistakes to Avoid`}),`\n`,_jsxs(AccordionGroup,{children:[_jsxs(Accordion,{title:`Being Too Vague`,id:`being-too-vague`,children:[_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Problem:`}),` “Tell me about AI.”`]}),_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Better:`}),` “Explain the key differences between supervised and unsupervised machine learning for a business analyst evaluating which approach to use for customer segmentation.”`]})]}),_jsxs(Accordion,{title:`Asking Multiple Questions at Once`,id:`asking-multiple-questions-at-once`,children:[_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Problem:`}),` “How do I improve our SEO, should we use social media ads, and what content strategy works best for B2B?”`]}),_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Better:`}),` Break into separate, focused prompts or explicitly request separate treatment of each question.`]})]}),_jsxs(Accordion,{title:`Providing No Context`,id:`providing-no-context`,children:[_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Problem:`}),` “Is this a good approach?” [without explaining what ‘this’ is or what your goals are]`]}),_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Better:`}),` Provide the approach, your context, your goals, and criteria for “good.”`]})]}),_jsxs(Accordion,{title:`Assuming Prior Knowledge`,id:`assuming-prior-knowledge`,children:[_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Problem:`}),` Starting a new conversation with “Continue from where we left off” without re-establishing context.`]}),_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Why this fails:`}),` Each new conversation starts with its own context window, so the AI can’t automatically read what was discussed in a different, unrelated conversation.`]}),_jsx(Info,{children:_jsxs(_components.p,{children:[`If your organization has enabled `,_jsx(_components.a,{href:`/en/improved-usage/memories`,children:`Memories`}),` or `,_jsx(_components.a,{href:`/en/improved-usage/projects`,children:`Projects`}),`, the AI can carry some context across conversations automatically. Otherwise, learn more about context windows in `,_jsx(_components.a,{href:`/en/improved-usage/conversation-management`,children:`Conversation Management`}),`.`]})}),_jsxs(_components.p,{children:[_jsx(_components.strong,{children:`Better:`}),` Briefly summarize relevant context from previous conversations when starting a new chat, or group related work in a Project so context is shared automatically.`]})]})]}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`best-practices-summary`,children:`Best Practices Summary`}),`\n`,_jsxs(CardGroup,{cols:2,children:[_jsx(Card,{title:`Start Simple`,icon:`seedling`,children:_jsx(_components.p,{children:`Begin with a clear basic prompt, then add complexity as needed.`})}),_jsx(Card,{title:`Be Specific`,icon:`bullseye`,children:_jsx(_components.p,{children:`Vague questions get vague answers. Provide details and context.`})}),_jsx(Card,{title:`Iterate`,icon:`arrows-rotate`,children:_jsx(_components.p,{children:`Refine your prompts based on the responses you receive.`})}),_jsx(Card,{title:`Save What Works`,icon:`bookmark`,children:_jsx(_components.p,{children:`Build a library of effective prompts for recurring tasks.`})})]}),`\n`,_jsx(Tip,{children:_jsx(_components.p,{children:`The best prompt is one that gets you the result you need. Experiment with different approaches and learn what works for your use cases.`})}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`next-steps`,children:`Next Steps`}),`\n`,_jsxs(CardGroup,{cols:2,children:[_jsx(Card,{title:`Conversation Management`,icon:`comments`,href:`/en/improved-usage/conversation-management`,children:_jsx(_components.p,{children:`Learn how to manage long conversations and understand context windows.`})}),_jsx(Card,{title:`Prompt Library`,icon:`bookmark`,href:`/en/improved-usage/prompt-library`,children:_jsx(_components.p,{children:`Save and reuse your best prompts with variables for efficiency.`})}),_jsx(Card,{title:`Choosing a Model`,icon:`sliders`,href:`/en/improved-usage/choosing-a-model`,children:_jsx(_components.p,{children:`Pick the right model size, or let the Router choose for you.`})})]})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(`Expected `+(component?`component`:`object`)+\" `\"+id+\"` to be defined: you likely forgot to import, pass, or provide it.\")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"Asking Great Questions","description":"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.","href":"/en/improved-usage/asking-great-questions"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"Basic Prompting Principles","slug":"basic-prompting-principles","depth":2,"children":[]},{"title":"Context Setting Techniques","slug":"context-setting-techniques","depth":2,"children":[{"title":"Effective Context-Setting Pattern","slug":"effective-context-setting-pattern","depth":3,"children":[]},{"title":"See It In Action: Video Example","slug":"see-it-in-action-video-example","depth":3,"children":[]}]},{"title":"Structured Output Requests","slug":"structured-output-requests","depth":2,"children":[]},{"title":"Prompt Engineering","slug":"prompt-engineering","depth":2,"children":[]},{"title":"Common Mistakes to Avoid","slug":"common-mistakes-to-avoid","depth":2,"children":[]},{"title":"Best Practices Summary","slug":"best-practices-summary","depth":2,"children":[]},{"title":"Next Steps","slug":"next-steps","depth":2,"children":[]}],"codeExamples":{}},"jsLinks":[],"dynamicCss":".mint-aspect-video {\n aspect-ratio: 16 / 9\n}\n.mint-w-full {\n width: 100%\n}\n.mint-rounded-xl {\n border-radius: 0.75rem\n}","subdomain":"wonkaai","siteName":"WonkaChat Wiki","title":"Asking Great Questions - WonkaChat Wiki","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{"en":{"href":"/en/improved-usage/asking-great-questions","matchLevel":0},"fr-CA":{"href":"/fr/improved-usage/asking-great-questions","matchLevel":1},"nl":{"href":"/nl/improved-usage/asking-great-questions","matchLevel":1},"fr":{"href":"/fr/improved-usage/asking-great-questions","matchLevel":1}}},"lastModified":"2026-09-28T08:14:02.187Z","originalFileLocation":"en/improved-usage/asking-great-questions.mdx","locale":"en"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.\">\u003cmeta data-mint-head name=\"application-name\" content=\"WonkaChat Wiki\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Asking Great Questions - WonkaChat Wiki\">\u003cmeta data-mint-head property=\"og:description\" content=\"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"WonkaChat Wiki\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://help.wonka.chat/en/improved-usage/asking-great-questions\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://wonkaai.mintlify.site/_mintlify/api/og/v2?division=Improved+Usage\u0026amp;title=Asking+Great+Questions\u0026amp;description=Master+the+fundamentals+of+effective+prompting+and+advanced+techniques+to+get+the+best+results+from+AI+models.\u0026amp;theme=4a422f18455eaca6f0a3694c\u0026amp;signature=f4540a9fbc45f6f67527b2eded6a2b23a97b9b95a64262c0d9054b463f0a514c\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Asking Great Questions - WonkaChat Wiki\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://wonkaai.mintlify.site/_mintlify/api/og/v2?division=Improved+Usage\u0026amp;title=Asking+Great+Questions\u0026amp;description=Master+the+fundamentals+of+effective+prompting+and+advanced+techniques+to+get+the+best+results+from+AI+models.\u0026amp;theme=4a422f18455eaca6f0a3694c\u0026amp;signature=f4540a9fbc45f6f67527b2eded6a2b23a97b9b95a64262c0d9054b463f0a514c\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/wonkaai/6onukrmd7J65O3O2/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"WonkaChat Wiki\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#2f6de0\">\u003clink data-mint-head rel=\"canonical\" href=\"https://help.wonka.chat/en/improved-usage/asking-great-questions\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/en/improved-usage/asking-great-questions.md\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"en\" href=\"https://help.wonka.chat/en/improved-usage/asking-great-questions\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"fr-CA\" href=\"https://help.wonka.chat/fr/improved-usage/asking-great-questions\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"nl\" href=\"https://help.wonka.chat/nl/improved-usage/asking-great-questions\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"fr\" href=\"https://help.wonka.chat/fr/improved-usage/asking-great-questions\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"x-default\" href=\"https://help.wonka.chat/en/improved-usage/asking-great-questions\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://help.wonka.chat/#organization\",\"name\":\"WonkaChat Wiki\",\"url\":\"https://help.wonka.chat\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/wonkaai/sJA7XYqvmb80Vuja/logo/wonka-logo-black.svg?fit=max\u0026auto=format\u0026n=sJA7XYqvmb80Vuja\u0026q=85\u0026s=dea1abfec97032f9ea8a961f35923e31\"}},{\"@type\":\"WebSite\",\"@id\":\"https://help.wonka.chat#website\",\"name\":\"WonkaChat Wiki\",\"url\":\"https://help.wonka.chat\",\"publisher\":{\"@id\":\"https://help.wonka.chat/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions#webpage\",\"url\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions\",\"name\":\"Asking Great Questions\",\"description\":\"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.\",\"dateModified\":\"2026-09-28T08:14:02.187Z\",\"isPartOf\":{\"@id\":\"https://help.wonka.chat#website\"},\"breadcrumb\":{\"@id\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"WonkaChat Wiki\",\"item\":\"https://help.wonka.chat\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Asking Great Questions\",\"item\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions#article\",\"headline\":\"Asking Great Questions\",\"name\":\"Asking Great Questions\",\"description\":\"Master the fundamentals of effective prompting and advanced techniques to get the best results from AI models.\",\"url\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions\",\"mainEntityOfPage\":{\"@id\":\"https://help.wonka.chat/en/improved-usage/asking-great-questions#webpage\"},\"dateModified\":\"2026-09-28T08:14:02.187Z\",\"publisher\":{\"@id\":\"https://help.wonka.chat/#organization\"},\"isPartOf\":{\"@id\":\"https://help.wonka.chat#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"WonkaChat Wiki\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"WonkaChat Wiki\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/en/improved-usage/asking-great-questions.md","siteName":"WonkaChat Wiki","nav":{"global":null,"languages":[{"language":"en","tabs":[{"tab":"WonkaChat","groups":[{"group":"Welcome to WonkaChat","pages":[{"title":"What is WonkaChat?","href":"/en/welcome/introduction"},{"title":"Why Choose WonkaChat?","href":"/en/welcome/why-wonka-chat"},{"title":"Quick Start Guide","href":"/en/welcome/quick-start"}]},{"group":"AI Agents","pages":[{"title":"What are AI Agents?","href":"/en/ai-agents/introduction"},{"title":"Finding and Accessing Agents","href":"/en/ai-agents/finding-and-accessing-agents"},{"title":"Using Existing Agents","href":"/en/ai-agents/using-existing-agents"},{"title":"Creating Your First Agent","href":"/en/ai-agents/creating-your-first-agent"},{"title":"Sharing Agents","href":"/en/ai-agents/sharing-agents"},{"title":"Business Teaching","href":"/en/ai-agents/business-teaching"},{"title":"Scheduled and Triggered Agents","href":"/en/ai-agents/scheduled-agents"},{"title":"Audit Your Agents","href":"/en/ai-agents/audit-your-agents"}]},{"group":"Tools \u0026 Connection","pages":[{"title":"External Connections","href":"/en/tools-connection/introduction"},{"title":"Your First External Connection","href":"/en/tools-connection/setting-up-your-first-connection"},{"title":"All integrations","href":"/en/tools-connection/integrations-catalog"},{"title":"Custom Connectors","href":"/en/tools-connection/custom-connectors"},{"title":"Troubleshooting Connections","href":"/en/tools-connection/troubleshooting-connections"},{"title":"Examples of Connection Usage","description":"See external connections (MCP) in action with real examples of Outlook, Odoo, and other business systems.","href":"/en/tools-connection/examples-of-tool-usage"}]},{"group":"Improved Usage","pages":[{"title":"Asking Great Questions","href":"/en/improved-usage/asking-great-questions"},{"title":"Choosing a Model","description":"Understand model sizes, the Router, Fast and Pro modes, and how to pick the right one for your task.","href":"/en/improved-usage/choosing-a-model"},{"title":"Model comparison","href":"/en/improved-usage/model-comparison"},{"title":"Conversation Management","href":"/en/improved-usage/conversation-management"},{"title":"Sharing Conversations","href":"/en/improved-usage/sharing-conversations"},{"title":"Prompt Library","href":"/en/improved-usage/prompt-library"},{"title":"Files \u0026 Knowledge","href":"/en/improved-usage/files-and-knowledge"},{"title":"Projects","href":"/en/improved-usage/projects"},{"title":"Memories","href":"/en/improved-usage/memories"},{"title":"Skills","href":"/en/improved-usage/skills"},{"title":"Artifacts","href":"/en/improved-usage/artifacts"},{"title":"Voice, Images \u0026 Web Search","href":"/en/improved-usage/voice-images-web-search"}]},{"group":"Pricing \u0026 Plans","pages":[{"title":"Pricing \u0026 Plans","href":"/en/pricing/plans"},{"title":"AI usage and credits","href":"/en/pricing/tokens-guide"}]},{"group":"Security \u0026 Governance","pages":[{"title":"Overview","href":"/en/security-governance/index"},{"title":"Security Overview","href":"/en/security-governance/security-overview"},{"title":"Access Control","href":"/en/security-governance/access-control"},{"title":"Best Practices","href":"/en/security-governance/best-practices"},{"title":"Compliance \u0026 Governance","href":"/en/security-governance/compliance-and-governance"}]},{"group":"Administration","pages":[{"title":"Administration","href":"/en/administration/index"},{"title":"Organization Settings","href":"/en/administration/organization-settings"},{"title":"SSO and 2FA","href":"/en/administration/sso-and-2fa"},{"title":"Groups and Tool Policies","href":"/en/administration/groups-and-tool-policies"},{"title":"Audit Log","href":"/en/administration/audit-log"},{"title":"Usage and Stats","href":"/en/administration/usage-and-stats"}]},{"group":"Developers","pages":[{"title":"Calling Agents via API","href":"/en/ai-agents/agents-api"}]},{"group":"Support \u0026 Resources","pages":[{"title":"FAQ","href":"/en/support-resources/faq"},{"title":"Troubleshooting","href":"/en/support-resources/troubleshooting"},{"title":"Getting Help","href":"/en/support-resources/getting-help"}]},{"group":"Legal","pages":[{"title":"Terms and Conditions","href":"/en/legal/terms-and-conditions"},{"title":"Terms of Service","href":"/en/legal/terms-of-service"},{"title":"Privacy Policy","href":"/en/legal/privacy-policy"},{"title":"Legal Notice","href":"/en/legal/legal-notice"},{"title":"Cookie Policy","href":"/en/legal/cookie-policy"}]}]},{"tab":"Learning","hidden":true,"pages":[{"title":"Learning","href":"/en/learn"}]},{"tab":"Updates","pages":[{"title":"Updates","href":"/en/updates/changelog"}]},{"tab":"Roadmap","hidden":true,"pages":[{"title":"Roadmap","href":"/en/roadmap"}]}],"global":{"anchors":[{"anchor":"Our website","icon":"globe","href":"https://www.wonka-ai.com/"},{"anchor":"Start for free","icon":"rocket","href":"https://wonka.chat/register"}]}},{"language":"fr-CA","pages":[{"title":"fr-CA","href":"/fr/improved-usage/asking-great-questions"}]},{"language":"nl","pages":[{"title":"nl","href":"/nl/improved-usage/asking-great-questions"}]},{"language":"fr","pages":[{"title":"fr","href":"/fr/improved-usage/asking-great-questions"}]}]},"basePath":"","title":"Asking Great Questions - WonkaChat Wiki","deploymentId":"dpl_7AgmPo2RyRWZ68ZGceW618SWGEAz","buildId":"dpl_7AgmPo2RyRWZ68ZGceW618SWGEAz","dynamics":["10e4515597"],"chunks":["BannerMarkdown-Cc6DT3k_.js","dist-BbIWfytJ.js","lib-DMeTj1gb.js","lib-B8HbPgcC.js","katex-Dbtb6Wk7.js","html-void-elements-mCSPHezU.js","marked.esm-CZWythHk.js"]}