About 7 min read
Skills, agents, and the file system
Agent workspaces, skills as packaged playbooks, and governed file access so capabilities stay consistent and auditable.
Agents and workspaces
- Each agent has a workspace slice: files, prompts, and session history that belong to that identity.
- Keep agent-specific context (brand voice, product facts) close to the agent; keep org-wide policy in skills or shared docs.
File system and previews
- Agents read and write under governed paths; previews and artifacts turn folders into shareable outputs when you publish them.
- Reserve sensitive material for secrets and connectors—not ad-hoc pastes into chat.
Tools behind the scenes
Capabilities (browser, connectors, workspace tools) are allowlisted per deployment. Operators can see health and configuration in workspace settings.
If an agent “cannot” do something, check skills, tool enablement, and connector auth before blaming the model.
Related pages
- What is Smart AI Team? — Smart AI Team is the operational home for your AI workforce—workspaces, agents, tasks, and governed execution in one place.
- The AI operating layer for teams — Why a chat window is not enough, and how Smart AI Team maps intelligence onto real org structure and workflows.
- How it works — Control plane, tenant runtimes, sessions, skills, and channels—how the pieces fit without sacrificing isolation.
- Workspaces and tenants — Per-customer runtimes, branded domains, SSO handoff, and why isolation is a product feature—not an afterthought.
- Documentation overview