Instead of relying on engineers to remember documented procedures (e.g., pre-commit checklists), encode these processes into custom AI skills. This turns static best-practice documents into automated, executable tools that enforce standards and reduce toil.

Block's AI agent, Goose, has an accessible UI that allows non-technical employees in roles like sales and finance to build their own software dashboards and tools. This democratizes software creation within the enterprise, turning domain experts into citizen developers.

AI can now handle complex coding tasks, leaving ecosystem-specific knowledge like using GitHub as the final barrier. As these last 'nerdy' steps get abstracted away by AI tools, truly non-technical individuals will be able to build and deploy sophisticated applications within months.

Manage collective team context—docs, queries, research—in a version-controlled repository. Everyone, including non-technical members like ops and strategy, contributes via pull requests, creating a single, evolving source of truth for AI agents and humans.

To serve both solo developers and large enterprises, GitHub focuses on creating horizontal "primitives" and APIs first. This foundational layer allows different user types to build their own specific workflows on top, avoiding the trap of creating a one-size-fits-none user experience.

GitHub is abandoning complex, "mega-skills" for AI agents, finding large all-in-one workflows brittle and hard to maintain. The better approach is to build atomic "micro-skills"—like Lego blocks—that do one thing well. These can then be composed and orchestrated into more complex, flexible automations.

A shared AI knowledge repository ("Team OS") is not just for technical roles. Partners in business operations, strategy, and other non-technical functions are active daily contributors via GitHub, adding their context and making the system more powerful for everyone.

With AI, codebases become queryable knowledge bases for everyone, not just engineers. Granting broad, read-only access to systems like GitHub from day one allows new hires in any role (product, design, data) to use AI to get context and onboard dramatically faster.

The barrier to creating AI-powered solutions has dropped dramatically. An HR team member with no AI expertise built a Slack bot trained on the employee handbook to answer common questions, saving hours of repetitive work. Every department should be empowered to identify and automate its own low-value, repetitive tasks using accessible AI tools.