Getting started

What is Turtle AI Coworker

The engine an enterprise AI workforce runs on: build agents, teams and AI employees over your own data and tools, govern every action, and audit every run.

Turtle AI Coworker is a platform for building, running and governing an AI workforce: software workers that do real work across the tools your team already uses. You configure them as deeply as you need, and every action they take is permissioned, traceable and auditable.

There are two ways to get started, and they end in the same place. You can build from the ground up, wiring workers, data and tools yourself, or you can install a Solution Pack, a complete working department that goes live in about fifteen minutes. This documentation covers both, starting with how the pieces fit together.

The three kinds of worker

Every automation in Turtle AI Coworker is built from one of three worker shapes. You pick the shape that matches the job.

Sequential Agentone job, start to finish
Agentic Teamone chat, many specialists
AI Employeea role you delegate to
Start with a single agent for one task, compose specialists into a team, or hire an AI employee that owns a whole role and remembers context between jobs.
  • Sequential Agents run one job end to end: typed inputs, ordered tasks, scoped access to your data and tools, and a traced result. They fire on demand or on a trigger.
  • Agentic Teams are a chat interface backed by several sub-agents. Each message is routed by intent to the right specialist, then handed back, all under one shared scope.
  • AI Employees are named coworkers you hire and delegate to. They own a role, hold memory across sessions, plan their own multi-step work, and ask for approval on risky actions.

What every worker runs on

Whichever worker you build, it draws on the same shared substrate. These are the building blocks documented in the sections that follow.

Knowledge Baseswhat it knows (RAG)
Tableswhat it records (data)
Toolswhat it can do (actions)
Modelshow it reasons (BYOK)
Governancewhat it may do
Knowledge Bases ground answers in your documents; Tables are the structured memory workers read and write; Tools and Integrations let workers act in your apps; Models are the reasoning engine, your keys. Governance wraps all of it: permissions, approvals, budgets and a full audit trail.

Configurable, traceable, auditable

Turtle AI Coworker is an engine, not a wrapper with a few settings. Every task, every table permission, every tool grant, every model choice, every trigger and every approval gate is yours to configure. And every run leaves a trace: what the worker read, which tools it called, what it wrote, and who approved it. That is what lets an autonomous worker pass a security review.

How this documentation is organized

  • Workers: how to build and run Sequential Agents, Agentic Teams and AI Employees.
  • Data & knowledge: creating Tables and Knowledge Bases and connecting them to workers.
  • Connect & configure: Tools & Integrations, Custom Tools and MCP, and Models.
  • Run, monitor & govern: running work, approvals, the audit trail and analytics.
  • Administration: organizations and workspaces, users and roles, groups, and settings.

Each module page opens with the concept and a flow diagram, then walks every action step by step, and ends with a reference of every field.