🧠Reusable AI personas

Agents

An agent is a persistent, reusable AI persona with its own brain and tools. Configure it once — identity, instructions, model, knowledge, and capabilities — then use it across chat, workflows, and the API, or have it coordinate a team of sub-agents.

What is an agent?

Unlike a one-off chat prompt, an agent is a saved configuration you can invoke anywhere. Each agent carries its own model, a system prompt, conversation starters, attached knowledge folders, a set of tools and integration actions it may call, optional sub-agents, and an optional structured-output schema. You build it once, share it, version it, and reuse it — in chat, as a node in a workflow, behind the API, or as a fillable form.

How an agent works

Agents run on the autonomous ReAct loop: the agent reasons about your request, decides which tool or knowledge source to call, observes the result, and repeats until it can answer. That reason → act → observe cycle is what makes an agent more than a single prompt.

🙋You askA request in chat, a workflow node, or an API call
🧠Agent reasonsPlans its next step
🧩Calls a toolIntegration action, web search, or image gen
📚Pulls knowledgeRetrieves cited passages from its folders
AnswersFree text or schema-shaped JSON
The ReAct loop — reason, act on a tool or knowledge source, observe, and repeat until the agent can answer.

Agents vs Skills vs Workflows

Your Office AI gives you three building blocks for AI behaviour. They are easy to confuse, so here is the clear line between them — pick the right one for the job:

Building blockWhat it carriesHow it behavesUse it when…
AgentIts own model, system prompt, knowledge folders, tools, and sub-agentsAutonomous persona — reasons and decides which tools to callYou want a capable, reusable assistant that can act.
SkillAn instruction snippet only — no model, no knowledge, no toolsSteers an existing model's behaviour when toggled onYou just want to shape tone or rules. Skills.
WorkflowA deterministic graph of nodes with explicit wiringRuns the same path every time — branching, looping, predictableYou want a repeatable, multi-step process. Workflows.

The three compose: a workflow can contain an agent node, and an agent can attach skills and delegate to sub-agents. Skills only steer behaviour, so when you need a model, knowledge, or tools, reach for an agent.

ℹ️
The engine behind agents

Agents execute on the LangGraph ReAct runtime — a Python sidecar fronted by a Dart AI server that handles authentication, budgets, and event streaming. The same engine powers workflows, so agents and workflows share one execution backbone. Human-in-the-loop approval (the write-action gate) is implemented natively with LangGraph's interrupt mechanism.

Explore agents

This section walks through everything you can do with an agent, from building one to delegating across a team:

Choose any model

Every agent picks its own model from the providers your administrator has configured. Your Office AI supports six providers in the same organization — hosted models from OpenAI, Anthropic, Google, and Groq, plus private, self-hosted models through Ollama and Ollama Cloud. The model picker is data-driven from your organization's configuration, with current models such as claude-sonnet-4-5, gpt-4o-mini, gemini-2.0-flash, Ollama llama3.2, and Ollama Cloud gpt-oss:120b.

💡
Sharing an agent

Agents use the same four sharing scopes as the rest of Your Office AI — Private, Specific people & Agents, Workspaces, and Organisation — each with view or edit. Members & Roles.