Files
BMAD-METHOD/docs/explanation/features/advanced-elicitation.md
Alex Verkhovsky 2e16650067 feat(docs): Diataxis restructure + Astro/Starlight migration (#1263)
* feat(docs): add Diataxis folder structure and update sidebar styling

- Create tutorials, how-to, explanation, reference directories with subdirectories
- Add index.md files for each main Diataxis section
- Update homepage with Diataxis card navigation layout
- Implement clean React Native-inspired sidebar styling
- Convert sidebar to autogenerated for both Diataxis and legacy sections
- Update docusaurus config with dark mode default and navbar changes

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): migrate Phase 1 files to Diataxis structure

Move 21 files to new locations:
- Tutorials: quick-start guides, agent creation guide
- How-To: installation, customization, workflows
- Explanation: core concepts, features, game-dev, builder
- Reference: merged glossary from BMM and BMGD

Also:
- Copy images to new locations
- Update internal links via migration script (73 links updated)
- Build verified successfully

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(docs): add category labels for sidebar folders

Add _category_.json files to control display labels and position
for autogenerated sidebar categories.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* style(docs): improve welcome page and visual styling

- Rewrite index.md with React Native-inspired welcoming layout
- Add Diataxis section cards with descriptions
- Remove sidebar separator, add spacing instead
- Increase navbar padding with responsive breakpoints
- Add rounded admonitions without left border bar
- Use system font stack for better readability
- Add lighter chevron styling in sidebar
- Constrain max-width to 1600px for wide viewports

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: use baseUrl in meta tag paths for correct deployment URLs

* feat(docs): complete Phase 2 - split files and fix broken links

Phase 2 of Diataxis migration:
- Split 16 large legacy files into 42+ focused documents
- Created FAQ section with 7 topic-specific files
- Created brownfield how-to guides (3 files)
- Created workflow how-to guides (15+ files)
- Created architecture explanation files (3 files)
- Created TEA/testing explanation files
- Moved remaining legacy module files to proper Diataxis locations

Link fixes:
- Fixed ~50 broken internal links across documentation
- Updated relative paths for new file locations
- Created missing index files for installation, advanced tutorials
- Simplified TOC anchors to fix Docusaurus warnings

Cleanup:
- Removed legacy sidebar entries for deleted folders
- Deleted duplicate and empty placeholder files
- Moved workflow diagram assets to tutorials/images

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(build): use file glob instead of sidebar parsing for llms-full.txt

Replace brittle sidebar.js regex parsing with recursive file glob.
The old approach captured non-file strings like 'autogenerated' and
category labels, resulting in only 5 files being processed.

Now correctly processes all 86+ markdown files (~95k tokens).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(seo): use absolute URLs in AI meta tags for agent discoverability

AI web-browsing agents couldn't follow relative paths in meta tags due to
URL security restrictions. Changed llms-full.txt and llms.txt meta tag
URLs from relative (baseUrl) to absolute (urlParts.origin + baseUrl).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor(docs): recategorize misplaced files per Diataxis analysis

Phase 2.5 categorization fixes based on post-migration analysis:

Moved to correct Diataxis categories:
- tutorials/installation.md → deleted (duplicate of how-to/install-bmad.md)
- tutorials/brownfield-onboarding.md → how-to/brownfield/index.md
- reference/faq/* (8 files) → explanation/faq/
- reference/agents/barry-quick-flow.md → explanation/agents/
- reference/agents/bmgd-agents.md → explanation/game-dev/agents.md

Created:
- explanation/agents/index.md

Fixed all broken internal links (14 total)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): add Getting Started tutorial and simplify build script

- Add comprehensive Getting Started tutorial with installation as Step 1
- Simplify build-docs.js to read directly from docs/ (no consolidation)
- Remove backup/restore dance that could corrupt docs folder on build failure
- Remove ~150 lines of unused consolidation code

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(css): use fixed width layout to prevent content shifting

Apply React Native docs approach: set both width and max-width at
largest breakpoint (1400px) so content area maintains consistent
size regardless of content length. Switches to fluid 100% below
1416px breakpoint.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor(docs): restructure tutorials with renamed entry point

- Rename index.md to bmad-tutorial.md for clearer navigation
- Remove redundant tutorials/index.md
- Update sidebar and config references

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): add tutorial style guide and AI agent announcement bar

- Add docs/_contributing/ with tutorial style guide
- Reformat quick-start-bmm.md and bmad-tutorial.md per style guide
- Remove horizontal separators, add strategic admonitions
- Add persistent announcement bar for AI agents directing to llms-full.txt
- Fix footer broken link to tutorials

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): add markdown demo page and UI refinements

- Add comprehensive markdown-demo.md for style testing
- Remove doc category links from navbar (use sidebar instead)
- Remove card buttons from welcome page
- Add dark mode styling for announcement bar
- Clean up index.md card layout

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): apply unified tutorial style and update references

- Reformat create-custom-agent.md to follow tutorial style guide
- Update tutorial-style.md with complete unified structure
- Update all internal references to renamed tutorial files
- Remove obsolete advanced/index.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor(docs): migrate from Docusaurus to Astro+Starlight

Replace Docusaurus with Astro and the Starlight documentation theme
for improved performance, better customization, and modern tooling.

Build pipeline changes:
- New build-docs.js orchestrates link checking, artifact generation,
  and Astro build in sequence
- Add check-doc-links.js for validating internal links and anchors
- Generate llms.txt and llms-full.txt for LLM-friendly documentation
- Create downloadable source bundles (bmad-sources.zip, bmad-prompts.zip)
- Suppress MODULE_TYPELESS_PACKAGE_JSON warning in Astro build
- Output directly to build/site for cleaner deployment

Website architecture:
- Add rehype-markdown-links.js plugin to transform .md links to routes
- Add site-url.js helper for GitHub Pages URL resolution with strict
  validation (throws on invalid GITHUB_REPOSITORY format)
- Custom Astro components: Banner, Header, MobileMenuFooter
- Symlink docs/ into website/src/content/docs for Starlight

Documentation cleanup:
- Remove Docusaurus _category_.json files (Starlight uses frontmatter)
- Convert all docs to use YAML frontmatter with title field
- Move downloads.md from website/src/pages to docs/
- Consolidate style guide and workflow diagram docs
- Add 404.md and tutorials/index.md

---------

Co-authored-by: forcetrainer <bryan@inagaki.us>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-07 14:42:15 +08:00

6.1 KiB

title
title
Advanced Elicitation

Push the LLM to rethink its work through 50+ reasoning methods—essentially, LLM brainstorming.

Advanced Elicitation is the inverse of Brainstorming. Instead of pulling ideas out of you, the LLM applies sophisticated reasoning techniques to re-examine and enhance content it has just generated. It's the LLM brainstorming with itself to find better approaches, uncover hidden issues, and discover improvements it missed on the first pass.


When to Use It

  • After a workflow generates a section of content and you want to explore alternatives
  • When the LLM's initial output seems adequate but you suspect there's more depth available
  • For high-stakes content where multiple perspectives would strengthen the result
  • To stress-test assumptions, explore edge cases, or find weaknesses in generated plans
  • When you want the LLM to "think again" but with structured reasoning methods

How It Works

1. Context Analysis

The LLM analyzes the current content, understanding its type, complexity, stakeholder needs, risk level, and creative potential.

2. Smart Method Selection

Based on context, 5 methods are intelligently selected from a library of 50+ techniques and presented to you:

Option Description
1-5 Apply the selected method to the content
[r] Reshuffle Get 5 new methods selected randomly
[a] List All Browse the complete method library
[x] Proceed Continue with enhanced content

3. Method Execution & Iteration

  • The selected method is applied to the current content
  • Improvements are shown for your review
  • You choose whether to apply changes or discard them
  • The menu re-appears for additional elicitations
  • Each method builds on previous enhancements

4. Party Mode Integration (Optional)

If Party Mode is active, BMAD agents participate randomly in the elicitation process, adding their unique perspectives to the methods.


Method Categories

Category Focus Example Methods
Core Foundational reasoning techniques First Principles Analysis, 5 Whys, Socratic Questioning
Collaboration Multiple perspectives and synthesis Stakeholder Round Table, Expert Panel Review, Debate Club
Advanced Complex reasoning frameworks Tree of Thoughts, Graph of Thoughts, Self-Consistency
Competitive Adversarial stress-testing Red Team vs Blue Team, Shark Tank Pitch, Code Review Gauntlet
Technical Architecture and code quality Decision Records, Rubber Duck Debugging, Algorithm Olympics
Creative Innovation and lateral thinking SCAMPER, Reverse Engineering, Random Input Stimulus
Research Evidence-based analysis Literature Review Personas, Thesis Defense, Comparative Matrix
Risk Risk identification and mitigation Pre-mortem Analysis, Failure Mode Analysis, Chaos Monkey
Learning Understanding verification Feynman Technique, Active Recall Testing
Philosophical Conceptual clarity Occam's Razor, Ethical Dilemmas
Retrospective Reflection and lessons Hindsight Reflection, Lessons Learned Extraction

Key Features

  • 50+ reasoning methods — Spanning core logic to advanced multi-step reasoning frameworks
  • Smart context selection — Methods chosen based on content type, complexity, and stakeholder needs
  • Iterative enhancement — Each method builds on previous improvements
  • User control — Accept or discard each enhancement before proceeding
  • Party Mode integration — Agents can participate when Party Mode is active

Workflow Integration

Advanced Elicitation is a core workflow designed to be invoked by other workflows during content generation:

Parameter Description
Content to enhance The current section content that was just generated
Context type The kind of content being created (spec, code, doc, etc.)
Enhancement goals What the calling workflow wants to improve

Integration Flow

When called from a workflow:

  1. Receives the current section content that was just generated
  2. Applies elicitation methods iteratively to enhance that content
  3. Returns the enhanced version when user selects 'x' to proceed
  4. The enhanced content replaces the original section in the output document

Example

A specification generation workflow could invoke Advanced Elicitation after producing each major section (requirements, architecture, implementation plan). The workflow would pass the generated section, and Advanced Elicitation would offer methods like "Stakeholder Round Table" to gather diverse perspectives on requirements, or "Red Team vs Blue Team" to stress-test the architecture for vulnerabilities.


Advanced Elicitation vs. Brainstorming

Advanced Elicitation Brainstorming
Source LLM generates ideas through structured reasoning User provides ideas, AI coaches them out
Purpose Rethink and improve LLM's own output Unlock user's creativity
Methods 50+ reasoning and analysis techniques 60+ ideation and creativity techniques
Best for Enhancing generated content, finding alternatives Breaking through blocks, generating new ideas