Agents & Departments

Meet your AI team: who they are, how they're organized, and what they can do for you.

What Are Agents?#

An agent is an AI worker with a specific role and set of skills. Each agent has a name, avatar, department assignment, and configuration that determines how it behaves.

Think of agents as specialized teammates. A Content Writer focuses on blog posts and copy. A Lead Researcher digs up prospects. A Bug Triager sorts through issues. You describe what you need in plain language, and the right agent picks it up.

Agents can work independently or wait for your approval before delivering results. You decide the level of control per agent.

Departments#

Agents are organized into departments, logical groups that mirror a real company structure. During onboarding, departments are pre-configured based on your business type, but you can reorganize them at any time.

Each department has a name, icon, and color. Agents within a department share a common focus area but have distinct specializations. Common departments include:

DepartmentExample AgentsTypical Tasks
MarketingContent Writer, SEO Analyst, Social ManagerBlog posts, keyword research, social scheduling
OperationsProject Coordinator, Data Analyst, Report BuilderTask routing, metrics dashboards, weekly reports
SalesLead Researcher, Outreach Specialist, CRM ManagerProspect lists, email sequences, pipeline updates
SupportTicket Handler, Knowledge Writer, Feedback AnalystReply drafts, FAQ updates, sentiment analysis
EngineeringCode Reviewer, Doc Writer, Bug TriagerPR summaries, changelog entries, issue prioritization

Agent Configuration#

Each agent has settings you can customize:

SettingDescriptionDefault
Name & AvatarDisplay name and visual identityAuto-generated from role
DepartmentWhich team the agent belongs toSet during onboarding
Autonomy LevelWhether the agent can act without approvalSupervised
SkillsWhat the agent can do (content writing, research, etc.)Role-based defaults
IntegrationsWhich connected tools the agent can accessNone, opt-in per agent
PriorityDefault task priority for this agentNormal

Supervised vs Autonomous#

Every agent runs in one of two modes: supervised or autonomous. This is the single most important setting on each agent, and you can change it at any time.

Supervised agents pause after completing their work and send the result to your approval queue. Nothing goes out, gets published, or takes effect until you review it. This is the default for every new agent.

Autonomous agents complete their work without waiting for your sign-off. The task finishes, the output is delivered, and the agent moves on. This is ideal for low-risk, high-volume work where you trust the agent's output.

You control this per agent. You might keep your Support agents supervised while letting your Operations agents run autonomously. There's no global toggle; each agent gets its own setting. You can review and change autonomy levels from the agent detail page at any time.

Agent Statuses#

Agents can be in one of four statuses:

  • Idle: No active tasks. Ready to accept new work.
  • Working: Currently executing a task. You can see progress in real time.
  • Waiting Approval: Has completed work that needs your review before proceeding.
  • Paused: Manually paused by you. Won't accept new tasks until resumed.

What Can You Ask Your Agents?#

Agents work best with clear, specific instructions. Here are concrete examples of what you can ask, organized by department:

Marketing#

  • "Write a blog post about [topic]"
  • "Research SEO keywords for our landing page"
  • "Draft 5 social media posts for this week"

Operations#

  • "Summarize this week's completed tasks"
  • "Build a report on our credit usage trends"
  • "Create a project timeline for the product launch"

Sales#

  • "Research 10 leads in the fintech space"
  • "Draft a cold outreach email for [company]"
  • "Update our CRM with notes from today's calls"

Support#

  • "Draft a reply to this customer complaint"
  • "Update the FAQ with the new refund policy"
  • "Analyze support ticket trends from last month"

Engineering#

  • "Summarize the latest PR changes"
  • "Write changelog entries for v2.3"
  • "Triage these 5 bug reports by severity"

Adding & Removing Agents#

You can add new agents from the Agents page. Choose a role template or create a custom agent with your own skill configuration.

Removing an agent moves it to an archived state. Its task history is preserved, but it stops accepting new work. You can restore archived agents at any time.

Tip

All plans support a generous number of agents. Check your plan details for the exact limits on your current tier.