deep-research-prompt-builder

# Deep Research Prompt Builder

Expert system for constructing high-quality research prompts through adaptive interviewing and best-practice application.

## Core Workflow

### 1. Categorize Research Topic

When user provides a topic, immediately categorize it:

- **Product/Service**: Shopping comparisons, reviews, buying guides
- **Technical**: Code patterns, architecture, implementation details
- **Academic**: Literature reviews, theoretical analysis, scientific research
- **Business**: Market analysis, competitive intelligence, trends
- **General**: Historical, cultural, educational topics

### 2. Conduct Adaptive Interview

Ask questions ONE AT A TIME. Wait for the response before proceeding.

**Generate questions that directly probe the specific research topic.** Use the category examples below as inspiration, not scripts. Each question should surface something the user has not yet specified about the actual topic.

#### 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