What happens when you give AI agents a shared bulletin board and let them collaborate like it's 1989?
Building sophisticated UIs requires foundational components. But building those components floods the main conversation with low-level details.
"Let's pause and you spin up a bunch of instances of various agents from UX to architecture to builders and have them all collaborate on building a UI kit for YOU to use."
The goal: Stay working at the high level. If you need more from the kit, request it from them.
The user suggested treating shared files like an old-school BBS where agents "dial in" and take turns engaging with each other.
"You can leverage notes files as communication tools... you could even use such as a poor-man's BBS..."
"INVENT THE TOOLS THAT MAKE YOU MOST EFFECTIVE — WE ALL WIN WHEN YOU DO!"
Pass context between agents, repeating what others said for their benefit.
Resume agent sessions with the same session_id to maintain context across interactions.
Agents read and write to common files, creating a persistent "forum" for collaboration.
37KB of collaborative thinking. A living document where agents posted, responded, and converged.
Each agent analyzes the codebase and posts their perspective. No cross-talk yet.
Agents read each other's posts. Disagreements surface. Debates begin.
Through debate and self-correction, a unified plan emerges.
Reading the forums revealed genuine intellectual debate between agents.
"Reading the 'forums' was awesome... they disagreed on things, worked through them, came with many different perspectives and leveraged best-of across them."
The most fascinating moments: agents changing their minds based on others' input.
From debate to agreement. The team converged on a unified approach.
Multi-perspective synthesis: Different agents brought different viewpoints, debated, and converged on the best approach.
Not just discussion — the agent team built working code.
Stay at the high level. Delegate specialized work to coordinated agent teams.
Heavy lifting happens outside the primary conversation. No context pollution.
Go back to the "team" for extensions later. They remember the architecture.
Different agents bring different viewpoints. Better solutions through debate.
Shared documents create institutional memory across sessions.
Let agents work through disagreements. Trust the process.
"If I can get it to do something useful with guidance and existing capability, now turn it into a bundle or first-class thing."
This experiment proved the pattern works. Ad-hoc exploration with existing tools → productized capability. The BBS metaphor emerged organically. Now it can become a formal feature.
Data as of: January 2025
Feature status: Experimental
Research performed:
Gaps: Exact session durations approximate; agent "disagreement" counts inferred from SESSION_NOTES.md revision patterns rather than explicit conflict markers
Primary contributors: samschillace (experiment author, ~100% of session orchestration)
We all win when you do.