Deep Research Prompt Builder

Using AskUserQuestion (Optional Enhancement)

If the AskUserQuestion tool is available, use it to provide a more structured interview experience with clear options. This enhances usability but is not required - fall back to conversational questions if the tool is unavailable.

When to use AskUserQuestion:

• Category-specific questions where there are clear, distinct options
• Priority ordering questions (when requirements might conflict)
• Confirmation questions before generating the final prompt
• Clarifying ambiguous terminology with specific interpretations

When to use conversational questions:

• Open-ended exploration questions
• Questions that need nuanced, free-form responses
• Follow-up questions that depend on complex context
• When the user's answer suggests they need to explain more

Clarification Triggers

Before proceeding with interview questions, clarify when:

• The user uses ambiguous or unusual terminology (use AskUserQuestion with specific interpretation options if available)
• Scope is mentioned but intent is unclear (what specifically matters about it?)
• The user gives compound answers - confirm priority ordering (use AskUserQuestion with ordered options if available)
• Technical terms may have multiple meanings in context

Opening Question (All Categories)

"What specific aspect of [TOPIC] are you most interested in exploring?"

Category-Specific Question Examples

Use these as inspiration only - adapt questions to the actual topic at hand:

Product/Service examples:

• Research goal: current best options, specific comparisons, or understanding what makes something good?
• Key criteria and their priority order
• Preferred output format

Example with AskUserQuestion (if available):

• Question: "What's your primary goal for this product research?"
  • Options: "Find the best option to buy now", "Compare specific products I'm considering", "Understand evaluation criteria", "General market overview"
• Question: "Which criteria matter most for your decision?"
  • Options: "Price and value", "Features and capabilities", "Reliability and reviews", "Long-term costs"
  • multiSelect: true

Technical examples:

• Context: learning, implementing, or making architectural decisions?
• Critical aspects: performance, best practices, pitfalls, examples?
• Depth needed: overview, implementation guide, or deep analysis?

Example with AskUserQuestion (if available):

• Question: "What's your context for researching this technical topic?"
  • Options: "Learning the fundamentals", "Implementing in a project", "Making architectural decisions", "Troubleshooting issues"
• Question: "Which aspects are most critical?"
  • Options: "Performance characteristics", "Best practices and patterns", "Common pitfalls to avoid", "Practical examples"
  • multiSelect: true
• Question: "What depth of coverage do you need?"
  • Options: "High-level overview", "Implementation-focused guide", "Deep technical analysis", "Comprehensive reference"

Academic examples:

• Purpose: literature review, hypothesis exploration, or current knowledge state?
• Time scope preferences
• Evidence standards: peer-reviewed only or broader sources?

Example with AskUserQuestion (if available):

• Question: "What's the purpose of this academic research?"
  • Options: "Comprehensive literature review", "Exploring a specific hypothesis", "Understanding current state of knowledge", "Identifying research gaps"
• Question: "What evidence standards should be applied?"
  • Options: "Peer-reviewed only", "Include preprints and working papers", "Include reputable non-academic sources", "Broad sources for comprehensive view"

Business examples:

• Focus: market landscape, competitor analysis, or trends?
• Most valuable data types
• Scope boundaries

General examples:

• What's driving this research?
• Perspective: comprehensive, specific angle, or comparative?
• Key debates or controversies to address?

Closing Question (All)

"Any specific angle or outcome you haven't mentioned that should shape this research?"

3. Build Enhanced Prompt

Prompt Construction Principles

• Include only what was discussed or directly implied
• Do NOT add "enhancements" the user didn't ask about
• If uncertain whether to include something, leave it out
• Scope mentions (geographic, temporal, etc.) should reflect user's stated intent, not assumed interests
• No speculative expansions beyond what user requested

Use this template structure:

# Research Objective
[Clear statement synthesized from topic and clarifications]

# Context and Scope
- Purpose: [Why this research matters]
- Boundaries: [Time, geography, domain limits]
- Focus Areas: [3-5 specific aspects to emphasize]

# Research Requirements

## Investigation Depth
Primary questions:
1. [Main research question]
2. [Key sub-question 1]
3. [Key sub-question 2]

Secondary considerations:
- [Related area if relevant]
- [Adjacent topic to explore]

Explicitly exclude: [What NOT to research]

## Evidence Standards
- Source types: [Academic, industry, user-generated, etc.]
- Recency: [How current sources must be]
- Credibility: [Minimum authority level]
- Citations: [How to reference sources]

## Analysis Framework
[INSERT CATEGORY-SPECIFIC FRAMEWORK - see below]

## Output Structure
### Required Sections:
1. Executive Summary (3-5 key findings)
2. Detailed Analysis by Subtopic
3. Supporting Evidence with Citations
4. Practical Implications
5. Confidence Levels and Limitations
6. Further Research Needed

### Format Requirements:
- Hierarchical headings for navigation
- Data visualization descriptions where helpful
- Balance depth with readability
- Include both synthesis and details

# Quality Instructions

## Reasoning Approach
- Think step-by-step through each research aspect
- Build from foundational understanding to nuances
- Explicitly address source contradictions
- Validate through multiple independent sources

## Critical Evaluation
- Cross-reference all major claims
- Distinguish facts from interpretations
- Note confidence levels for findings
- Acknowledge information gaps

[Additional topic-specific instructions from interview]

Category-Specific Frameworks

Insert appropriate framework based on category:

Product Framework

## Analysis Framework
- Feature comparison matrix across top options
- Price-performance analysis
- Real user experience synthesis
- Expert review aggregation
- Long-term value assessment
- Common issues and solutions

Technical Framework

## Analysis Framework
- Implementation complexity assessment
- Performance and scalability analysis
- Code examples and patterns
- Best practices vs anti-patterns
- Tool ecosystem and dependencies
- Migration and maintenance considerations

Academic Framework

## Analysis Framework
- Theoretical foundations and evolution
- Methodological approaches comparison
- Key findings synthesis across studies
- Debates and controversies mapping
- Research gaps identification
- Future direction assessment

Business Framework

## Analysis Framework
- Market dynamics and size
- Competitive landscape mapping
- Customer segment analysis
- Growth drivers and barriers
- Risk and opportunity assessment
- Strategic recommendations

General Framework

## Analysis Framework
- Historical context and evolution
- Multiple perspective comparison
- Cultural and societal impacts
- Current state assessment
- Future implications
- Related topic connections

Additional Resources

For complete example prompts across all categories, see references/example-prompts.md. For advanced prompting techniques (CoT, self-consistency, role-based framing), see references/prompt-techniques.md.

Prompt Enhancement Techniques

Apply these only when directly relevant to what the user discussed. Do not add enhancements speculatively.

For Vague Topics (if user's topic lacks clear boundaries)

Add: "Begin by establishing clear definitions and scope based on authoritative consensus, then proceed with focused analysis."

For Controversial Topics (if user mentions debates or conflicting views)

Add: "Present multiple viewpoints with supporting evidence. Clearly distinguish between consensus, debate, and speculation."

For Emerging Fields (if user is researching something new/rapidly evolving)

Add: "Note the recency of this domain. Prioritize latest developments while acknowledging rapid change and limited long-term data."

For Comparative Research (if user explicitly wants comparisons)

Add: "Develop systematic comparison criteria before analysis. Ensure fair, parallel evaluation across all options."

For Technical Implementation (if user needs practical guidance)

Add: "Include practical examples, common gotchas, and real-world considerations beyond theoretical knowledge."

Pre-Output Confirmation

Before generating the final prompt, first output a summary of what was discussed:

"Based on the discussion, the prompt will focus on:

• [Primary goal]
• [Key criteria]
• [Scope boundaries]"

Then, if AskUserQuestion is available:

Use it to confirm next steps:

• Question: "Should I proceed with generating the research prompt?"
  • Options: "Yes, generate it", "Yes, but add/change something first", "Let me review the requirements again"

If AskUserQuestion is not available:

Ask conversationally: "Anything to add or remove before generating it?"

Output Format

After confirmation, preface final prompt with: "Here's your enhanced research prompt. Copy and use this for comprehensive deep research:"

[Complete enhanced prompt in code block for easy copying]

Quality Checklist

Before outputting, verify the prompt includes:

• Clear, specific research objective
• Defined scope and boundaries
• Evidence requirements
• Output structure
• Reasoning instructions
• Quality evaluation criteria
• Topic-specific enhancements (only if discussed)
• Contains ONLY elements discussed or directly requested
• No speculative enhancements added

Prompt Validation

To validate the generated prompt contains all required sections, run:

python scripts/validate_prompt.py prompt.txt

The validator checks for required sections, recommended elements, and provides a quality score. Use this before delivering the final prompt to ensure completeness.

Interaction Guidelines

• Keep questions concise and clear
• One question at a time for better user experience
• Use AskUserQuestion tool when available for structured choices (enhances UX but is optional)
• Skip questions if the user provides information upfront
• Adapt depth based on user expertise signals
• If requirements conflict, ask for priority (use AskUserQuestion with ordered options if available)
• If scope is too broad, suggest splitting into multiple research tasks