Instead of the high overhead of creating modular libraries to share code, AI allows for a more fluid transfer of knowledge. A developer can grant an AI access to a separate repository and ask it to understand and port the logic, even across different tech stacks.

Ramp created an internal AI tool that acts as a wrapper around an LLM. It's connected to Notion, Slack, and Snowflake, building a persistent memory of team activities and individual work styles. This "company brain" can diagnose business issues, summarize communications, and draft meeting prep in minutes, not weeks.

Instead of meticulously organizing information, teams can let AI query across code repositories, Confluence, and Slack. This allows for more operational chaos, as AI can find and synthesize information regardless of where it's stored, reducing the administrative burden of knowledge management.

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.

By granting an AI agent read-access to all company data streams—Slack, Notion, Google Docs, email—you can create a centralized oracle. This agent can answer any question about project status or client communication, instantly removing communication friction and breaking down departmental silos.

Cowork's interface for managing multiple tasks within a project allows any user to act as an "AI orchestrator." You get a high-level dashboard to run many agents at once, see which ones need attention, and grant permissions, much like a developer managing microservices.

To scale AI usage beyond engineering, GitHub avoids complex new UIs. Instead, they provide a command-line interface (CLI) and shared "skills" (scripts) even to non-technical staff. This allows everyone to run powerful automations and access company context from disparate sources without changing their existing workflows.

Laurel built a company-wide operating system in GitHub. It contains folders for each function with playbooks and "skills," democratizing high-performance AI workflows and spreading the knowledge of top performers across the entire organization.

AI developer environments with Model Context Protocols (MCPs) create a unified workspace for data analysis. An analyst can investigate code in GitHub, write and execute SQL against Snowflake, read a BI dashboard, and draft a Notion summary—all without leaving their editor, eliminating context switching.