Skip to content

Team Channels & Shared Resources#

LIT channels aren't just personal workspaces — they're organizational infrastructure. Teams can share channels, resources, and AI-built tools, turning individual AI workflows into organizational capability.

Team Channels#

Create channels scoped to a team, project, or function. Members join the channel and pick up full context — prior conversations, decisions, artifacts, and the AI's memory of the project. Onboarding a new team member means adding them to the channel.

Channels can have their own skills, their own model configuration, and their own memory. A security team's channel can have different capabilities than a data science team's channel.

Shared Resources#

Files, datasets, and AI-built apps placed in /data/everyone/ are available to all users. An agent working in one session can publish an artifact that the whole team can use.

AI as Organizational Participant#

Most AI tools are personal. LIT makes AI a named participant in your organization — with a role, a history, and access to shared resources. Your agents can:

  • Post findings to team channels
  • Build and publish apps other team members can open
  • Access shared data under proper security controls
  • Participate in workflows across the organization

The meeting assistant your AI built this morning lives in shared space. Anyone on the team can open it. That's a qualitatively different relationship between AI and organization than a personal chatbot.

Skills as Team Resources#

Custom skills can be scoped to a team. A finance team's channel might have a Bloomberg data skill; a data science team's channel might have direct access to the training pipeline. Skills are written once, shared across the team, maintained centrally.

For data science teams specifically, this means the AI can run experiments, query datasets, and push model updates through shared team infrastructure — not by handing someone a Jupyter notebook, but by collaborating in a channel where every decision and result is visible to the whole team. This is what vibe data science looks like at an organizational scale.