Deep Research Prompt Generator Instructions

The workflow execution engine is governed by: {project_root}/bmad/core/tasks/workflow.xml You MUST have already loaded and processed: {installed_path}/workflow.yaml This workflow generates structured research prompts optimized for AI platforms Based on 2025 best practices from ChatGPT, Gemini, Grok, and Claude

Understand what the user wants to research

Let’s create a powerful deep research prompt!

What topic or question do you want to research?

Examples:

<template-output>research_topic</template-output>

What’s your goal with this research?

<template-output>research_goal</template-output>

Which AI platform will you use for the research?

  1. ChatGPT Deep Research (o3/o1)
  2. Gemini Deep Research
  3. Grok DeepSearch
  4. Claude Projects
  5. Multiple platforms
  6. Not sure yet

<template-output>target_platform</template-output>

Help user define clear boundaries for focused research

Let’s define the scope to ensure focused, actionable results:

Temporal Scope - What time period should the research cover?

<template-output>temporal_scope</template-output>

Geographic Scope - What geographic focus?

<template-output>geographic_scope</template-output>

Thematic Boundaries - Are there specific aspects to focus on or exclude?

Examples:

<template-output>thematic_boundaries</template-output>

Determine what types of information and sources are needed

What types of information do you need?

Select all that apply:

<template-output>information_types</template-output>

Preferred Sources - Any specific source types or credibility requirements?

Examples:

<template-output>preferred_sources</template-output>

Specify desired output format for the research

Output Format - How should the research be structured?

  1. Executive Summary + Detailed Sections
  2. Comparative Analysis Table
  3. Chronological Timeline
  4. SWOT Analysis Framework
  5. Problem-Solution-Impact Format
  6. Question-Answer Format
  7. Custom structure (describe)

<template-output>output_format</template-output>

Key Sections - What specific sections or questions should the research address?

Examples for market research:

Examples for technical research:

<template-output>key_sections</template-output>

Depth Level - How detailed should each section be?

<template-output>depth_level</template-output>

Gather additional context to make the prompt more effective

Persona/Perspective - Should the research take a specific viewpoint?

Examples:

<template-output>research_persona</template-output>

Special Requirements or Constraints:

<template-output>special_requirements</template-output>

<invoke-task halt=“true”>{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>

Establish how to validate findings and what follow-ups might be needed

Validation Criteria - How should the research be validated?

<template-output>validation_criteria</template-output>

Follow-up Questions - What potential follow-up questions should be anticipated?

Examples:

<template-output>follow_up_strategy</template-output>

Synthesize all inputs into platform-optimized research prompt

Generate the deep research prompt using best practices for the target platform

Prompt Structure Best Practices:

  1. Clear Title/Question (specific, focused)
  2. Context and Goal (why this research matters)
  3. Scope Definition (boundaries and constraints)
  4. Information Requirements (what types of data/insights)
  5. Output Structure (format and sections)
  6. Source Guidance (preferred sources and credibility)
  7. Validation Requirements (how to verify findings)
  8. Keywords (precise technical terms, brand names)

Generate prompt following this structure

<template-output file=“deep-research-prompt.md”>deep_research_prompt</template-output>

Review the generated prompt:

What would you like to adjust? Regenerate with modifications

Provide platform-specific usage tips based on target platform

ChatGPT Deep Research Tips:

Gemini Deep Research Tips:

Grok DeepSearch Tips:

Claude Projects Tips:

<template-output>platform_tips</template-output>

Create a checklist for executing and evaluating the research

Generate execution checklist with:

Before Running Research:

During Research:

After Research Completion:

<template-output>execution_checklist</template-output>

Save complete research prompt package

Your Deep Research Prompt Package is ready!

The output includes:

  1. Optimized Research Prompt - Ready to paste into AI platform
  2. Platform-Specific Tips - How to get the best results
  3. Execution Checklist - Ensure thorough research process
  4. Follow-up Strategy - Questions to deepen findings

Save all outputs to {default_output_file}

Would you like to:

  1. Generate a variation for a different platform
  2. Create a follow-up prompt based on hypothetical findings
  3. Generate a related research prompt
  4. Exit workflow

Select option (1-4):

Start with different platform selection

Start new prompt with context from previous

Search {output_folder}/ for files matching pattern: bmm-workflow-status.md Find the most recent file (by date in filename)

Load the status file

<template-output file=“{{status_file_path}}”>current_step</template-output> Set to: “research (deep-prompt)”

<template-output file=“{{status_file_path}}”>current_workflow</template-output> Set to: “research (deep-prompt) - Complete”

<template-output file=“{{status_file_path}}”>progress_percentage</template-output> Increment by: 5% (optional Phase 1 workflow)

<template-output file=“{{status_file_path}}”>decisions_log</template-output> Add entry:

- **{{date}}**: Completed research workflow (deep-prompt mode). Research prompt generated and saved. Next: Execute prompt with AI platform or continue with plan-project workflow.

✅ Deep Research Prompt Generated

Research Prompt:

Status file updated:

Next Steps:

  1. Execute the research prompt with your chosen AI platform
  2. Gather and analyze findings
  3. Run plan-project to incorporate findings

Check status anytime with: workflow-status

✅ Deep Research Prompt Generated

Research Prompt:

Note: Running in standalone mode (no status file).

Next Steps:

  1. Execute the research prompt with AI platform
  2. Run plan-project workflow