will/swarm-zap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
3e198bcbb39372d02ee6d3c01803b7f3ce7c71da
swarm-zap/memory/2026-03-05.md
zap 3e198bcbb3 docs(council): add experimental findings from all 3 flow types 
- Tested parallel 1-round, sequential 1-round, debate/parallel 3-round
- 3 rounds is sweet spot: positions converge, meaningful evolution
- Sequential most token-efficient; parallel 3-round best depth-to-cost
- Debate and parallel 3-round mechanically identical (prompt tone differs)
- Added cost profiles, recommended defaults by use case
- Updated TODOs: unify flows, test 2-round, test mixed model tiers
2026-03-05 16:39:32 +00:00

2.6 KiB
Raw Blame History

2026-03-05

Council skill created and iterated

  • Built skills/council/ — multi-perspective advisory council using subagents.
  • Design decisions (agreed with Will):
    • Implemented as a skill (not standalone agents).
    • 3 advisors (Pragmatist, Visionary, Skeptic) + 1 Referee = 4 subagents total.
    • Referee is a separate subagent (not the session model) — can use a stronger model tier.
    • Default flow: Parallel + Synthesis. Sequential and Debate flows also available.
    • Final output includes individual advisor perspectives (collapsed/summarized) + referee verdict.
    • Model tier chosen per-invocation based on topic complexity.
  • Two live tests run:
    • Test 1: Parallel single-round on "Do LLM agents think?" — worked well.
    • Test 2: Parallel 3-round debate on same topic — richer output, positions evolved meaningfully across rounds.
  • Post-test iteration: updated skill with configurable parameters:
    • flow (parallel/sequential/debate), rounds (1-5), tier (light/medium/heavy)
    • Round-specific prompt templates (opening, rebuttal, final position)
    • Multi-round referee template that tracks position evolution
    • Word count guidance that decreases per round to control token cost
    • Subagent labeling convention: council-r{round}-{role}
  • Files: SKILL.md, references/prompts.md, scripts/council.sh (reference doc).
  • TODOs in memory/tasks.json:
    • Revisit advisor personality depth (richer backstories).
    • Revisit skill name ("council" is placeholder).
    • Experiment with different round counts and flows for optimal depth/cost tradeoffs.

Council experiments completed

  • Ran all 3 flow types on same topic ("Should AI assistants have persistent memory?"):
    1. Parallel 1-round (Experiment 1): Fast, clean, independent perspectives. 4 subagent calls, ~60k tokens.
    2. Sequential 1-round (Experiment 2): Tighter dialogue — later advisors build on earlier. 4 calls, ~55k tokens. Less redundancy.
    3. Debate/Parallel 3-round (Experiment 3): Richest output. Positions evolved significantly across rounds (Visionary backed off always-on, Skeptic softened on trajectory). 10 calls, ~130k tokens.
  • Key findings:
    • 3 rounds is the sweet spot for depth — positions converge by round 3.
    • Sequential is most token-efficient for focused topics.
    • Parallel 3-round is best depth-to-cost ratio for substantive topics.
    • Debate and parallel 3-round are mechanically identical — differ only in prompt tone.
  • Updated SKILL.md with experimental findings, recommended defaults by use case, cost profiles.
  • New TODOs added: unify debate/parallel flows, test 2-round sufficiency, test mixed model tiers.