Research Deep

Council

Multi-agent collaborative debate producing visible round-by-round transcripts with real intellectual friction.

03
Workflows
03
References
08
Triggers
high
Effort

The Problem

Asking an AI to give you multiple perspectives usually produces a single voice wearing different hats. The "devil's advocate" agrees with the main position at the end. The "skeptic" shares no domain expertise with the topic at hand. You get the appearance of debate without the actual friction that makes it useful.

How This Skill Approaches It

Council composes 4-6 custom agents via ComposeAgent with domain expertise and personality traits tailored to the specific question — never generic types. Those agents run in parallel within each round, read each other's actual arguments, and respond to them directly. Three sequential rounds let positions evolve through genuine friction. The DEBATE workflow produces a full round-by-round transcript plus synthesis; QUICK produces first-round positions for a fast sanity check. The collaborative-adversarial framing keeps it aimed at finding the best path rather than just attacking, which separates it from RedTeam.

  • Members custom-composed via ComposeAgent with domain expertise tailored to the topic — never generic
  • Workflows: DEBATE (3 rounds, full transcript + synthesis, parallel within rounds, 40-90s), QUICK (1 round, fast perspective check)
  • 4-6 well-composed agents outperform 12 generic ones
  • Collaborative-adversarial — debate to find the best path
Not for pure adversarial attack (use RedTeam)

In Action

What you say to your DA, and what the Council skill actually does.

  • You say "council: should we use WebSockets or SSE for real-time updates?"
    Composes 4 agents with traits drawn from real-time systems, frontend, ops, and protocol research; runs the DEBATE workflow across 3 rounds with a full transcript showing how positions shift as each agent responds to the others' actual arguments.
  • You say "quick council check: is this API design reasonable?"
    Runs the QUICK workflow — one round of initial positions from custom-composed agents with API-relevant expertise — fast enough to serve as a sanity check before committing to the design.

Inside the Skill

The thinking, frameworks, and architecture that distinguish this skill from a generic version of the same task.

What It Does

Runs a multi-agent debate. Custom-composed agents discuss a topic over rounds, respond to each other's actual points, and surface insights through real intellectual friction. You get a visible round-by-round transcript plus a synthesis. DEBATE runs three rounds; QUICK runs one for a fast perspective check.

The Problem

When you ask one model for an opinion, you get one frame and one set of blind spots. Asking for "pros and cons" gives you a flat list with no one actually pushing back. Real deliberation needs distinct experts who disagree on the merits and argue it out, so the weak parts of an idea get exposed before you commit. Generic built-in agents all sound the same and produce bland agreement; this skill composes topic-specific agents that create genuine friction.

How It Works

Custom-composed agents discuss topics in rounds, respond to each other's points, and surface insights through intellectual friction.

Quick Reference

Workflow Purpose Rounds Output
DEBATE Full structured discussion 3 Complete transcript + synthesis
QUICK Fast perspective check 1 Initial positions only

Context Files

File Content
CouncilMembers.md How to compose custom agents for councils (ComposeAgent)
RoundStructure.md Three-round debate structure and timing
OutputFormat.md Transcript format templates

Core Philosophy

Origin: Best decisions emerge from diverse perspectives challenging each other. Not just collecting opinions - genuine intellectual friction where domain-specific experts respond to each other's actual points.

Agents: Every council uses custom-composed agents via the Agents skill. This gives each member a unique voice, personality, and domain expertise tailored to the topic. Generic built-in agents produce generic debate. Custom agents produce sharp, informed debate.

Speed: Parallel execution within rounds, sequential between rounds. A 3-round debate of 4 agents = 12 agent calls but only 3 sequential waits. Complete in 40-90 seconds.

Examples

"Council: Should we use WebSockets or SSE?"
-> Compose 4 custom agents with relevant traits (real-time, frontend, ops, research)
-> DEBATE workflow -> 3-round transcript

"Quick council check: Is this API design reasonable?"
-> Compose 4 custom agents with API-relevant traits
-> QUICK workflow -> Fast perspectives

"Council: Is AI overhyped?"
-> Compose agents: AI builder, security skeptic, pragmatic engineer, evidence analyst
-> DEBATE workflow -> 3-round transcript

Integration

Depends on:

  • Agents skill - ComposeAgent tool for creating all council members

Works well with:

  • RedTeam - Pure adversarial attack after collaborative discussion
  • Research - Gather context before convening the council

Best Practices

  1. Use QUICK for sanity checks, DEBATE for important decisions
  2. Design agent traits around the specific topic, not generic roles
  3. Review the transcript - insights are in the responses, not just positions
  4. Trust multi-agent convergence when it occurs
  5. NEVER use built-in agent types — ALWAYS use ComposeAgent

Last Updated: 2026-03-18

Gotchas

  • Council uses the Agents skill (ComposeAgent) for custom agents — NOT built-in agent types. Never use Designer, Architect, etc. for Council debates.
  • Debates need genuine disagreement to be valuable. If all agents agree, the topic may not warrant Council.
  • More agents ≠ better debate. 4-6 well-composed agents outperform 12 generic ones.

Workflows · 3

  1. 01
    `Workflows/Debate.md` Workflows/`Workflows/Debate.md`.md

    Full structured debate (3 rounds, visible transcript)

  2. 02
    `Workflows/Quick.md` Workflows/`Workflows/Quick.md`.md

    Quick consensus check (1 round, fast)

  3. 03
    RedTeam skill Workflows/RedTeam skill.md

    Pure adversarial analysis

How to Invoke

Say any of these to your DA and PAI activates the Council skill automatically:

  • "council"
  • "debate"
  • "multiple perspectives"
  • "weigh options"
  • "deliberate"
  • "get different views"
  • "what would experts say"
  • "pros and cons"

Or invoke explicitly:

Skill("Council")

References · 3

Auxiliary files the skill loads at runtime — frameworks, guides, configs.

  • CouncilMembers
  • OutputFormat
  • RoundStructure

References & Credits

The thinkers, books, frameworks, and research this skill is built on. The ideas belong to them — the integration belongs to PAI.

Want PAI to do this for you?

Install PAI on your machine — your DA gets the Council skill plus 44 others, all hooked into one Life OS.