> Markdown version of [/videos/2164-wearedevelopers-live-project-chopin-make-your-team-and-agents-play-along](https://www.wearedevelopers.com/videos/2164-wearedevelopers-live-project-chopin-make-your-team-and-agents-play-along). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# WeAreDevelopers LIVE - Project Chopin: Make Your Team and Agents Play Along

Are AI agents turning your development into an isolated, single-player game? Discover how Project Chopin uses Markdown to make coding with AI a collaborative, multiplayer workflow.

- **Speakers:** [Chris Heilmann](https://www.wearedevelopers.com/@chris-heilmann), [Daniel Cranney](https://www.wearedevelopers.com/@daniel-cranney), [Krzysztof Cieślak](https://www.wearedevelopers.com/@krzysztof-cieslak)
- **Event:** WeAreDevelopers LIVE
- **Published:** September 9, 2026
- **Duration:** 1:21:17
- **URL:** https://www.wearedevelopers.com/videos/2164-wearedevelopers-live-project-chopin-make-your-team-and-agents-play-along

## Summary

The rapid integration of autonomous AI agents has largely solved the mechanical task of writing code, but it has introduced significant workflow challenges by making development an isolated, single-player experience. While engineers rely on agents for implementation, the critical planning and architectural phases often remain disjointed and lost in ephemeral terminal logs. To bridge this gap, GitHub Next researchers developed Project Chopin, a self-hostable, open-source prototype that reimagines software development as an inherently multiplayer activity. Often described as "Google Docs for software development," Chopin elevates Markdown to the primary interface for managing AI agents, ensuring that strategic planning and architectural logic remain central to the workflow.\n\nThe core philosophy driving Chopin is that software engineering is fundamentally "collaborative problem-solving." By anchoring AI interactions in a shared, version-controlled document with a persistent decision log, teams can reason about their codebase collectively rather than isolating context within individual agent sessions. This shift is crucial as AI adoption matures; organizations are realizing that merely accelerating code generation does not automatically map to revenue growth, and an overreliance on automation can lead to "workslop"—overwhelming colleagues with AI-generated action items. Software development remains uniquely suited for AI optimization because of its built-in verification loops through compilation and testing, a definitive advantage over purely creative fields.\n\nAs developers increasingly delegate implementation to agents, managing the associated security risks becomes paramount. The reliance on AI introduces novel attack vectors, such as agent slot squatting and UTF-8 smuggling, making it essential for teams to establish secure, internal package feeds to prevent autonomous agents from hallucinating and installing malicious dependencies. Alongside exploring these future paradigms with experimental tools like Chopin, developers continue to optimize their foundational workflows using privacy-focused resources and native utilities like Marta, a two-pane macOS file manager that restores classic, keyboard-driven efficiency to modern file organization.

**Keywords:** project chopin, github next research, multiplayer ai agents, markdown-driven development, agentic workflow planning, ai generated workslop, software verification loops, agent slot squatting, utf-8 smuggling attacks, internal package feeds, marta file manager, macos file organization, collaborative problem-solving, self-hosted developer tools

## Chapters

1. **Introduction and upcoming developer events in San Jose** (00:07) — Updates on the WeAreDevelopers conference and reflections on retro gaming hardware.
1. **Product onboarding friction and invite-only application launches** (06:35) — How forced friction and invite-only models impact early user adoption.
1. **Managing browser tabs and network ad blocking** (11:36) — Strategies for handling browser tab overload and the shift toward privacy-focused tools.
1. **Cloud tools preferred by AI coding agents** (15:11) — An analysis of the external services and databases frequently selected by AI tools like Cursor.
1. **Evaluating citations in AI search engines** (18:52) — How AI amplifies existing internet problems like link farming and unreliable source indexing.
1. **Measuring the business impact of AI development tools** (23:39) — Why increased developer productivity with AI does not automatically translate to revenue growth.
1. **Security risks of autonomous AI coding agents** (28:01) — The dangers of agents installing hallucinated dependencies and bypassing corporate network audits.
1. **Visualizing geographical scale with map projections** (31:57) — How standard map projections distort country sizes and impact global perspective.
1. **Exploring early web design history and styling** (35:34) — A nostalgic look at 1990s HTML layouts, inline styles, and the evolution of CSS.
1. **The hidden hurdles of indie app development** (42:35) — Simulating the bureaucratic and marketing challenges developers face when launching app store products.
1. **Testing tech headlines in fake or news** (45:10) — A trivia game guessing the authenticity of bizarre AI and technology news headlines.
1. **Collaborative AI planning with Project Chopin** (53:39) — How Project Chopin enables multiplayer markdown editing and decision logging for software teams.
1. **Deploying and researching GitHub Next with Project Chopin** (58:31) — The rationale behind open-sourcing GitHub Next experiments and instructions for self-hosting the tool.
1. **Keyboard-driven macOS file management with Marta** (75:10) — How the Marta file manager improves macOS productivity with two-pane navigation and plugin support.

## Related Moments

- [Shifting developer workloads and realistic AI productivity gains](https://www.wearedevelopers.com/videos/1830-wearedevelopers-live-speculaitions) (from "WeAreDevelopers LIVE - SpeculAItions")
- [Integrating AI agents as collaborative software team members](https://www.wearedevelopers.com/videos/1539-agentic-devops-how-ai-powered-automation-transforms-software-delivery-on-github-and-azure) (from "Agentic DevOps: How AI-Powered Automation Transforms Software Delivery on GitHub and Azure")
- [Shifting from chat interfaces to autonomous agentic co-piloting](https://www.wearedevelopers.com/videos/2097-ai-code-then-vs-now-from-complex-rubbish-to-co-piloting-in-12-months) (from "AI Code then vs now: From Complex rubbish to co-piloting in 12 months")
- [Orchestrating local developer environments with AI tools](https://www.wearedevelopers.com/videos/1392-mcp-mashups-how-ai-agents-are-reviving-the-programmable-web) (from "MCP Mashups: How AI Agents are Reviving the Programmable Web")
- [Introduction to GitHub Next and AI prototyping](https://www.wearedevelopers.com/videos/1268-innovating-developer-tools-with-ai-insights-from-github-next) (from "Innovating Developer Tools with AI: Insights from GitHub Next")
- [Balancing developer autonomy with the adoption of coding agents](https://www.wearedevelopers.com/videos/100198-the-last-mile-of-ai-from-prototype-to-production) (from "The Last Mile of AI: From Prototype to Production")

## Related Articles

- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)
- [How we Build The Software of Tomorrow](https://www.wearedevelopers.com/magazine/120-how-we-build-the-software-of-tomorrow)
- [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this)

## Related Jobs

- [Senior Software Engineer, Sandboxes (Eu Or East Coast Preferred)](https://www.wearedevelopers.com/jobs/ext/2161904-senior-software-engineer-sandboxes-eu-or-east-coast-preferred) at **Docker, Inc.**
- [Staff Software Engineer, GitHub Intelligence (Copilot Agents)](https://www.wearedevelopers.com/jobs/ext/2650582-staff-software-engineer-github-intelligence-copilot-agents) at **GitHub**
- [Senior AI/ML Engineer](https://www.wearedevelopers.com/jobs/48352-senior-ai-ml-engineer) at **PagerDuty**
- [Junior Engineer (AI)](https://www.wearedevelopers.com/jobs/ext/2458261-junior-engineer-ai) at **Almedia**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**
- [Founding Developer Advocate](https://www.wearedevelopers.com/jobs/48425-founding-developer-advocate) at **Plumber**