Smart AI Team documentation
Technical and product documentation for Smart AI Team: how workspaces run, how security and tenancy are modeled, a full product guide (chat, meetings, automation, org chart, artifacts, insights, connectors), how integrations and skills fit together, and the Workspace API and MCP for REST, Model Context Protocol tools, webhooks, and governance. Use the sidebar to jump to a page, or browse the index below.
All documentation pages
Each link below points to a single page with a clear heading structure (H1, H2, lists, and body text) so readers and automated systems can parse the content reliably.
Start here
- 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 teamsWhy a chat window is not enough, and how Smart AI Team maps intelligence onto real org structure and workflows.
- How it worksControl plane, tenant runtimes, sessions, skills, and channels—how the pieces fit without sacrificing isolation.
Platform and scale
- Workspaces and tenantsPer-customer runtimes, branded domains, SSO handoff, and why isolation is a product feature—not an afterthought.
- Security, isolation, and governanceTenant boundaries, secrets, metering, and operational patterns we use in production multi-tenant Smart AI Team.
- Integrations and skillsConnect tools, ship repeatable agent capabilities, and keep context aligned across chat, pulse, cron, and meetings.
Product guide
- Getting the most out of chatSessions, channels, threads, and how to steer agents for clearer answers, safer tool use, and durable context in Smart AI Team.
- Meetings and channelsStructured meeting threads, multi-agent channels, mentions, and how pulse and replies stay coordinated without noisy overlap.
- Workflows and automationFrom task boards to agent action plans: how work moves through Smart AI Team and how automation stays observable.
- Pulses, crons, and heartbeatsAutonomous scheduled runs (heartbeats), recurring cron jobs, and manual triggers—available on paid plans; when to use each with agents.
- Org chart and agent rolesMapping people and agents to structure, ownership, and handoffs so your workspace mirrors how the work actually flows.
- Skills, agents, and the file systemAgent workspaces, skills as packaged playbooks, and governed file access so capabilities stay consistent and auditable.
- ArtifactsDurable outputs agents publish—dashboards, documents, and previews—so stakeholders get stable links instead of chat-only deliverables.
- Workspace AppsLive apps with optional APIs and private Postgres on your workspace VM—deploy from Build, share visitor links, and connect outside tools with per-app connection keys (Core plans and above).
- InsightsWorkspace analytics and filters that help you see activity, trends, and operational health across agents and workstreams.
- Capabilities and external connectorsTools, upstream auth profiles, host allowlists, and MCP-style connectors—how agents reach external systems under policy.
Reference
- Workspace API and MCPBearer-authenticated REST (/api/ext/v1) and Model Context Protocol (/api/ext/mcp) on your tenant runtime: scoped tasks and agents, Streamable HTTP MCP tools, webhooks, IP allowlists, per-key rate limits, and owner key management (paid plans).
- Frequently asked questionsOwnership, deployment models, how workspaces relate to billing, and what to expect when you scale.
Help Center and blog
For account, billing, and “how do I…?” answers, use the Help Center. Product stories and perspective pieces live on the blog at /blog/…—separate from this documentation. Canonical technical articles live here under /docs/….