* feat: add link auditor tools and fix broken docs links - Add audit-doc-links.js to scan docs for broken links with auto-resolution - Add fix-doc-links.js to apply suggested fixes (dry-run by default) - Remove stale "Back to Core Concepts" breadcrumb links - Update BMad acronym to "Breakthrough Method of Agile AI Driven Development" - Update README links to docs.bmad-method.org - Simplify upgrade callout in getting-started tutorial Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: reorganize docs structure and archive v4 tutorial - Remove unused section index files (tutorials, how-to, explanation, reference) - Move getting-started-bmadv4.md to _archive - Update quick-start-bmgd.md to remove archived file reference - Update upgrade-to-v6.md - Update astro.config.mjs for new structure Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: ignore underscore directories in link checker Update check-doc-links.js to skip _archive, _planning, and other underscore-prefixed directories when validating links. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: add v4 users section to README Add links to v4 documentation archive and upgrade guide for users migrating from previous versions. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat: convert docs to site-relative links and add validation tools - Convert all relative links (./ ../) to site-relative paths (/path/) - Strip .md extensions and use trailing slashes for Astro/Starlight - Add fix-doc-links.js to convert relative links to site-relative - Add validate-doc-links.js to check links point to existing files - Remove old audit-doc-links.js and check-doc-links.js - Update build-docs.js to use new validation script - Add npm scripts: docs:fix-links, docs:validate-links - Update style guide with validation steps Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: standardize acronym to BMad across documentation Replace incorrect "BMAD" with correct "BMad" in text and frontmatter while preserving "BMAD-METHOD" in GitHub URLs. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: fix BMad acronym and remove draft README - Correct acronym to "Breakthrough Method of Agile AI Driven Development" - Remove unused README-draft.md Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: standardize BMad acronym in README Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: standardize FAQ format across all FAQ pages - Add TOC with jump links under "## Questions" - Use ### headers for questions (no Q: prefix) - Direct answers without **A:** prefix - Remove horizontal rules and "Related Documentation" sections - End each FAQ with issue/Discord CTA - Update style guide with new FAQ guidelines - Delete redundant faq/index.md (sidebar handles navigation) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: use repo-relative links with .md for GitHub compatibility Convert all documentation links to repo-relative format (/docs/path/file.md) so they work when browsing on GitHub. The rehype plugin strips /docs/ prefix and converts .md to trailing slash at build time for Astro/Starlight. - Update rehype-markdown-links.js to strip /docs/ prefix from absolute paths - Update fix-doc-links.js to generate /docs/ prefixed paths with .md extension - Convert 217 links across 64 files to new format Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: handle /docs/ prefix in link validator Update resolveLink to strip /docs/ prefix from repo-relative links before checking if files exist. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: restore FAQ index page Re-add the FAQ index page that was accidentally deleted, with updated repo-relative link format. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
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:
- Receives the current section content that was just generated
- Applies elicitation methods iteratively to enhance that content
- Returns the enhanced version when user selects 'x' to proceed
- 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 |