Skip to main content

MoLOS-LLM-Council Module

Multi-LLM consultation system that brings multiple AI perspectives together through a structured 3-stage deliberation process, enabling better decision-making through diverse expert viewpoints.

Overview

Location: /ui/MoLOS-LLM-Council

The LLM Council module implements a "council of experts" approach to AI consultation. Instead of relying on a single LLM response, you can query multiple AI models simultaneously, have them critique each other's responses, and synthesize a final, well-considered answer.

LLM Council main interface Placeholder: Screenshot showing the main council interface with the consultation input and persona selection

The Council Concept

Think of it as convening a panel of experts:

  • Multiple Perspectives: Different LLMs bring different strengths and viewpoints
  • Structured Deliberation: A 3-stage process ensures thorough analysis
  • Persona-Based Expertise: Assign specific roles and expertise to AI participants
  • Synthesized Outcomes: The President persona combines insights into a final recommendation

The module provides four main sections:

SectionPathDescription
Council/ui/MoLOS-LLM-CouncilStart and conduct consultations
Personas/ui/MoLOS-LLM-Council/personasCreate and manage AI personas
History/ui/MoLOS-LLM-Council/historyBrowse and search past consultations
Settings/ui/MoLOS-LLM-Council/settingsConfigure providers and module options

The 3-Stage Council Process

The LLM Council uses a structured deliberation process inspired by real-world expert panels:

Stage 1: Initial Responses

Stage 1 - Initial responses Placeholder: Screenshot showing multiple persona responses appearing simultaneously in Stage 1

All selected personas receive your prompt and provide their initial responses independently. This ensures diverse, unbiased perspectives before any cross-influence occurs.

What happens:

  • Each persona generates an independent response
  • Responses are displayed side-by-side for comparison
  • You can review each perspective before proceeding
tip

Use diverse personas in Stage 1 to maximize perspective variety. A "Devil's Advocate" persona alongside an "Optimist" persona yields richer discussions.

Stage 2: Discussion and Critique

Stage 2 - Discussion and critique Placeholder: Screenshot showing personas responding to and critiquing each other's Stage 1 responses

Personas review each other's Stage 1 responses and engage in discussion. They can agree, disagree, add nuance, or challenge points made by other council members.

What happens:

  • Each persona sees all Stage 1 responses
  • Personas provide critiques and additional insights
  • Areas of agreement and disagreement become clear
  • Weak arguments are challenged and strengthened
info

Stage 2 helps identify blind spots and strengthens weak arguments through peer review among the AI personas.

Stage 3: Final Synthesis

Stage 3 - Final synthesis Placeholder: Screenshot showing the President persona's synthesized final response incorporating all perspectives

The President persona (or designated synthesizer) reviews all discussion and produces a unified, synthesized response that incorporates the best insights from the entire council.

What happens:

  • President persona reviews Stage 1 and Stage 2 outputs
  • Key insights are extracted and combined
  • Conflicts are resolved with reasoned explanations
  • Final recommendation is presented with supporting rationale
note

The President persona can be customized with specific synthesis instructions. For technical decisions, configure it to prioritize accuracy. For creative tasks, configure it to preserve diverse viewpoints.

Core Features

Multi-LLM Consultation

Query multiple LLMs simultaneously and compare their responses in real-time.

Capabilities:

  • Simultaneous Queries: Send identical prompts to all selected personas at once
  • Parallel Processing: Responses arrive as they're generated
  • Side-by-Side Comparison: View all responses in a unified interface
  • Token Tracking: Monitor usage and costs per consultation

Persona Management

Personas list view Placeholder: Screenshot showing the personas management page with a list of created personas

Create AI personas with specific expertise, personalities, and viewpoints.

Persona editing interface Placeholder: Screenshot showing the persona creation/edit form with system prompt, provider, and model selection

Persona Configuration:

  • Name: Descriptive identifier (e.g., "Senior Developer", "UX Researcher")
  • System Prompt: Custom instructions that define expertise and behavior
  • Provider Assignment: Link persona to specific LLM provider
  • Model Selection: Choose specific model (GPT-4, Claude 3, etc.)
  • President Role: Mark persona as the synthesizer for Stage 3

Built-in Persona Types:

TypeBest ForTypical Traits
AnalystData-driven decisionsLogical, methodical, evidence-focused
CriticRisk assessmentSkeptical, thorough, identifies flaws
CreativeBrainstormingImaginative, unconventional, exploratory
PragmatistImplementationPractical, resource-aware, actionable
PresidentSynthesisBalanced, comprehensive, decisive

Provider Support

The module supports multiple LLM providers:

ProviderModelsBest For
OpenAIGPT-4, GPT-4 Turbo, GPT-3.5General purpose, code, analysis
AnthropicClaude 3 Opus, Sonnet, HaikuNuanced reasoning, safety-critical
OpenRouterMultiple via single APIAccess to many models
CustomAny OpenAI-compatible APISelf-hosted, specialized models

Response Ranking

Rate and rank LLM responses to track which personas perform best for different query types.

  • Star Ratings: Rate response quality (1-5 stars)
  • Comparative Ranking: Rank responses against each other
  • Notes: Add context for why a response was preferred
  • Analytics: View aggregate performance over time

Conversation History

History page Placeholder: Screenshot showing the consultation history page with search and filter options

Track and review all past consultations with full search capabilities.

Features:

  • Full Text Search: Search across all consultation content
  • Date Filtering: Find consultations by date range
  • Persona Filtering: Filter by participating personas
  • Stage Filtering: View consultations at specific stages
  • Replay: Review complete 3-stage deliberation
  • Export: Export consultations for external documentation

Settings and Configuration

Settings page Placeholder: Screenshot showing the settings page with provider configuration and module options

Provider Configuration

Configure each LLM provider with:

Provider Settings:
- API Endpoint: Provider's API URL
- API Key: Authentication credentials
- Default Model: Primary model for this provider
- Max Tokens: Response length limit
- Temperature: Creativity/randomness (0.0-2.0)

Module Settings

  • Default Personas: Personas included in new councils by default
  • Auto-Advance Stages: Automatically progress through stages
  • Synthesis Model: Model used for final synthesis
  • Response Timeout: Maximum wait time for responses
  • Cost Alerts: Notification thresholds for spending

AI Tools (MCP)

The module exposes the following AI tools for the Architect Agent:

Council Management

ToolDescription
create_councilStart a new council consultation with prompt and selected personas
get_councilRetrieve a specific council by ID
list_councilsList councils with filtering options
advance_stageMove council to next deliberation stage

Conversation & Messages

ToolDescription
get_conversationRetrieve full conversation with all stages
get_messagesGet messages for a specific stage
add_messageAdd user message to conversation

Persona Management

ToolDescription
get_personasRetrieve all defined personas
get_personaGet specific persona by ID
create_personaCreate new persona with configuration
update_personaUpdate existing persona
delete_personaRemove a persona

Provider & Settings

ToolDescription
get_providersList configured LLM providers
get_settingsRetrieve module settings
update_settingsUpdate module configuration

Database Schema

The module uses these repositories:

RepositoryTablePurpose
ConversationRepositoryconversationsCouncil consultations
MessageRepositorymessagesIndividual messages within stages
PersonaRepositorypersonasAI persona definitions
ProviderRepositoryprovidersLLM provider configurations
SettingsRepositorysettingsModule-level settings

Use Cases

Code Review Council

Scenario: You need a thorough code review before merging a critical feature.

Council Setup:

  • Security Expert (Claude 3 Opus): Focus on vulnerabilities
  • Performance Analyst (GPT-4): Focus on efficiency
  • Maintainability Reviewer (GPT-4 Turbo): Focus on code quality

Prompt:

Review this pull request for:
1. Security vulnerabilities
2. Performance implications
3. Code maintainability
4. Best practices adherence

[code or PR link]

Outcome:

  • Stage 1: Each expert provides independent review
  • Stage 2: Experts discuss disagreements and edge cases
  • Stage 3: President synthesizes actionable review summary

Strategic Decision Making

Scenario: Evaluating whether to build a feature in-house or use a third-party solution.

Council Setup:

  • Build Advocate (GPT-4): Arguments for in-house development
  • Buy Advocate (Claude 3 Sonnet): Arguments for third-party
  • Risk Analyst (GPT-4): Risk assessment for both options

Prompt:

We need [feature capability]. Should we:
A) Build in-house using [tech stack]
B) Integrate with [third-party solution]

Budget: [amount]
Timeline: [deadline]
Team size: [number] engineers

Provide recommendation with rationale.

Outcome:

  • Stage 1: Each advocate presents their case
  • Stage 2: Cross-examination and challenge
  • Stage 3: Balanced recommendation with decision criteria

Content Generation

Scenario: Creating marketing copy that needs to balance multiple brand voices.

Council Setup:

  • Brand Voice A (Claude 3): Professional, authoritative tone
  • Brand Voice B (GPT-4): Friendly, approachable tone
  • Editor (GPT-4 Turbo): Ensures consistency and clarity

Prompt:

Write product description for [product].

Key points to include:
- [point 1]
- [point 2]
- [point 3]

Target audience: [description]
Brand guidelines: [guidelines]

Outcome:

  • Stage 1: Multiple draft versions
  • Stage 2: Editor critiques and suggests improvements
  • Stage 3: Polished final version incorporating best elements

Integration with MoLOS

Cross-Module Integration

  • MoLOS-AI-Knowledge: Use saved prompts as council inputs
  • MoLOS-Tasks: Create task-linked consultations for project decisions
  • MoLOS-Goals: Council input for goal planning and review
  • Architect Agent: Direct access to all council features via MCP tools

Architect Agent Access

The Architect Agent can leverage the LLM Council for:

  • Multi-perspective analysis of complex problems
  • Consensus building on recommendations
  • Diverse brainstorming sessions
  • Quality assurance through multiple reviewers

Getting Started

Quick Start

  1. Navigate to Council: Go to /ui/MoLOS-LLM-Council
  2. Configure Providers: Add API keys in Settings
  3. Create Personas: Build 2-3 personas with different perspectives
  4. Start a Council: Enter your prompt and select personas
  5. Progress Through Stages: Review responses at each stage
  6. Get Synthesis: Review the President's final synthesis

Best Practices

Diverse Personas

Create personas with genuinely different perspectives. Two "helpful assistant" personas add less value than pairing an "optimist" with a "skeptic."

Stage Timing

Don't rush through stages. Stage 2 discussions often reveal insights that weren't apparent in Stage 1.

President Configuration

Customize your President persona for your use case. For technical decisions, emphasize accuracy. For creative work, emphasize preserving unique insights.

Cost Management

Multi-stage consultations with multiple personas increase token usage. Monitor costs in Settings and start with fewer personas for routine queries.

Troubleshooting

Provider Not Responding

Symptoms: Timeout errors, missing responses

Solutions:

  1. Verify API key is valid and has credits
  2. Check provider status page for outages
  3. Confirm API endpoint is correct
  4. Test provider independently first

Stage Not Advancing

Symptoms: Council stuck at current stage

Solutions:

  1. Check if all expected responses have arrived
  2. Verify auto-advance is enabled in Settings
  3. Manually advance using the "Next Stage" button
  4. Check browser console for errors

High Token Costs

Symptoms: Unexpected API charges

Solutions:

  1. Review cost tracking in Settings
  2. Reduce number of personas per council
  3. Use smaller models for routine queries
  4. Enable cost alerts for budget management

Synthesis Quality Issues

Symptoms: Stage 3 output is generic or misses key points

Solutions:

  1. Refine President persona's system prompt
  2. Add explicit synthesis instructions to President
  3. Ensure Stage 2 discussion is substantive
  4. Try different models for President role

Module Version: 1.1.0
Last Updated: March 21, 2026