# Multiplayer AI Manifesto

## Executive summary

The video outlines a 'Multiplayer AI Manifesto,' detailing the necessary shift from siloed, single-user AI chats to collaborative, cloud-native agent sessions. This transition is driven by the need for true co-working experiences that eliminate context switching and data fragmentation (the 'context task tax'). The manifesto proposes five core principles—such as agents living next to the work surface and keeping learning open—to guide the development of highly productive, secure, and collaborative AI workflows.

## Key takeaways

- The Need for Multiplayer AI: Current single-player AI chats force users into a 'context task' workflow (e.g., copying code from GitHub to Claude, then pasting it to Slack). Multiplayer agents allow co-workers to interact with the same agent session simultaneously, eliminating this friction.
- The Five Principles of Multiplayer AI: 1. **Refuse to Copy and Paste:** Agents must live directly next to the work surface (e.g., in Notion or GitHub) rather than within a separate chat window. The agent must access all tools available to the human team. 2. **Work with the Door Open:** Collaboration requires open learning, where best practices and insights are shared publicly, accelerating collective knowledge gain (analogous to Shopify's 'River' system). 3. **Continuously Improve:** Learning from successful prompts or complex iterations should be automatically codified as a skill for the agent. 4. **People are not Routers; Agents are:** Humans must focus on high-value activities, while agents handle routing and answering repetitive project update questions. 5. **Nothing Starts from Scratch:** The entire agent session that generated an artifact (document, PR) must persist in the cloud to ensure continuity for team members.
- Technical Requirements & Security: AI agents must reside entirely in the cloud and be managed by a robust boundary. This is crucial because local/laptop agents are insecure, cannot be preserved long-term, and prevent team access. Furthermore, strict governance (a 'black box' record) is required to track what data an agent accesses and which users interact with it.

## Technical details

- Agent Architecture: Agents must operate in the cloud environment, not on local laptops, due to security risks (exfiltration) and inability to preserve state. The architecture requires a robust boundary that manages network integration and prevents prompt injection from accessing sensitive data.
- Multi-User Context Management: A critical architectural challenge is ensuring that when multiple users interact with an agent, the scope of access remains restricted (e.g., Marcus joining Priya's chat should not grant him access to her private email search capabilities).
- Provider Agnosticism: Solutions must be provider agnostic to avoid vendor lock-in and maintain flexibility as frontier models change rapidly (e.g., GPT-6, Claude, open source models like GLM). Relying on a single model provider's incentive structure is shortsighted.

## Practical implications

- Organizations must prioritize building or adopting solutions that enable true co-working agent sessions.
- Focus development efforts on integrating agents directly into existing work surfaces (CRM, document editors) rather than relying solely on chat interfaces.
- Governance and auditability are non-negotiable requirements for enterprise adoption of AI agents.

## Topics

AI Agents, Multiplayer Computing, Workflow Automation, Enterprise Architecture, Knowledge Management, Claude, Codeex, Pi, GitHub, Notion, Linear, Shopify River

Source: https://www.youtube.com/watch?v=6L4Mt7G5s0I