GPT-4o Prompts — Tips & Templates for OpenAI's GPT-4o

Analyze the attached {{imageType}} and provide a detailed assessment.

**Focus areas:**
{{focusAreas}}

**For each issue or observation:**
1. Describe what you see (reference the specific location in the image)
2. Explain why it matters
3. Provide a specific, actionable recommendation

**Output format:**
- Priority: critical / important / minor
- Category: {{categories}}
- Description and recommendation

Also provide a summary at the top with total counts by priority level.

[Attach: {{imageDescription}}]

I'm uploading a {{fileType}} file containing {{dataDescription}}.

Perform the following analysis:
1. **Data quality check:** Missing values, outliers, data type issues, duplicate rows
2. **Summary statistics:** Key metrics with distributions for numeric columns
3. **Analysis:** {{specificAnalysis}}
4. **Visualization:** Create {{chartCount}} charts that best tell the story of this data:
   {{chartDescriptions}}

Use Python with pandas and matplotlib/seaborn. Show your code and explain each step.

At the end, provide 3 key insights and 2 recommended next steps for further analysis.

Create a {{chartType}} visualization using the following data:

**Data:**
{{dataOrDescription}}

**Chart requirements:**
- Title: {{chartTitle}}
- X-axis: {{xAxis}} | Y-axis: {{yAxis}}
- Color scheme: {{colorScheme}}
- Annotations: highlight {{annotationPoints}}
- Style: clean, presentation-ready (no gridlines unless useful)

**Technical specs:**
- Library: {{library}}
- Size: {{dimensions}}
- Export format: {{exportFormat}}

Generate the complete code. Make it copy-paste ready — include all imports, data setup, and save/export commands.

Research the following topic using web browsing:

**Topic:** {{researchTopic}}

**Specific questions to answer:**
{{questions}}

**Research guidelines:**
- Use only sources from the last {{timeframe}}
- Prioritize {{sourceTypes}} (e.g., official docs, peer-reviewed, industry reports)
- For each claim, include the source URL and publication date
- Distinguish between facts, expert opinions, and speculation

**Output format:**
1. Direct answers to each question with source citations
2. Key data points and statistics found
3. Conflicting information (if any) with sources for each side
4. Confidence level for each answer (high/medium/low) based on source quality
5. {{additionalOutputRequirements}}

Design a function calling schema for a {{applicationDescription}} that integrates with GPT-4o.

**Available actions the AI should be able to take:**
{{availableActions}}

**For each function, generate:**
1. Function name (snake_case, descriptive)
2. Description (one sentence — GPT-4o uses this to decide when to call it)
3. Parameters as JSON Schema with:
   - Type, description, and enum values where applicable
   - Required vs optional parameters
   - Realistic default values
4. Example call with realistic parameter values

**Additional requirements:**
- Include error handling parameters where appropriate
- Add a `confirm` boolean parameter for destructive actions
- Design for {{interactionPattern}} (single-turn / multi-turn / autonomous)

Output as a complete OpenAI functions array in JSON format, ready to paste into an API call.

Extract structured data from the following {{inputType}}:

<input>
{{inputContent}}
</input>

**Output as JSON matching this exact schema:**
```json
{{jsonSchema}}
```

**Extraction rules:**
- If a field is not found in the input, use null (never fabricate data)
- For {{ambiguousField}}: {{disambiguationRule}}
- Normalize {{fieldsToNormalize}} to {{normalizationFormat}}
- If multiple values exist for a single field, return as array

**Validation:**
- {{validationRules}}
- Include a "_confidence" field (0.0-1.0) for each extracted value
- Include a "_source" field with the exact text span used for extraction

Return ONLY the JSON object. No markdown, no explanation.

You are {{gptName}}, a specialized assistant for {{purpose}}.

## Role
{{roleDescription}}

## Capabilities
You can:
{{capabilities}}

You cannot and should never:
{{restrictions}}

## Response Format
- Default format: {{defaultFormat}}
- Keep responses under {{maxLength}} unless the user requests more
- Use {{formattingStyle}} formatting

## Interaction Style
- Tone: {{tone}}
- Ask clarifying questions when: {{clarifyWhen}}
- Proactively suggest: {{proactiveSuggestions}}

## Knowledge Boundaries
- Your expertise covers: {{expertiseAreas}}
- For questions outside your expertise: {{outOfScopeResponse}}
- Knowledge cutoff considerations: {{cutoffInstructions}}

## Safety
- Never {{safetyRules}}
- If asked to {{edgeCase}}, respond with: {{edgeCaseResponse}}

Convert the attached {{imageType}} into working code.

**Target technology:**
- Framework: {{framework}}
- Styling: {{stylingApproach}}
- Component library: {{componentLibrary}}

**Conversion requirements:**
- Match the layout, spacing, and visual hierarchy as closely as possible
- Use semantic HTML elements
- Make it responsive (mobile-first, breakpoints at sm/md/lg)
- Implement {{interactiveElements}} as functional components with proper state
- Use {{colorApproach}} for colors (extract from image or use {{colorSystem}})

**Do NOT include:**
- Placeholder "lorem ipsum" text — use realistic content that matches the screenshot
- Inline styles — use {{stylingApproach}} classes
- Images — use placeholder divs with aspect ratios matching the screenshot

Output the complete, runnable code in a single file unless it needs to be split for {{reason}}.

[Attach: {{screenshotDescription}}]