Skip to main content
A chat agent is configured like any other agent — instructions, tools, integration permissions. The differences: no trigger, no entity filter, and approvals land in the chat.

​
Create the agent

1

Create

Go to Chat → New Chat Agent (or create an agent in chat mode). There is no Triggers & Filters step — chat agents start when someone messages them.
Chat agent editor — name, test mode, sandbox, and subagent fan-out; no Triggers & Filters tab
2

Write instructions

Custom instructions define the agent’s job, tone, and limits. Be explicit about what it should refuse and when to ask a technician. If end users will talk to it, write for them — not for your technicians.
3

Enable tools and permissions

Pick tools and set per-integration permissions exactly as for other agents. Enable the minimum the job needs — every enabled write permission is reachable from a chat message.
4

Test in the dashboard

Chat with it on the Chat page before exposing it anywhere. With test mode on, the agent describes side-effecting actions in its reply instead of performing them.

​
Settings that work differently in chat

SettingBehavior for chat agents
Trigger & filtersNone — user-initiated
Technician-in-the-LoopAlways delivered as an inline approval card in the chat
Test mode reportAlways reported in the chat reply
Model & reasoningPlatform-managed; no per-agent override
Mention modeIn Teams group chats and channels: mention-only (default) responds only when @mentioned; read-all responds to every message. 1:1 chats always respond.

​
Per-client instructions for end-user agents

If the agent serves end users through a channel, you can add Chat Instructions per client company (Companies → edit company). They’re injected when a user from that company is talking — use them for company-specific policies, escalation contacts, or tone.

​
Before going live

  • Require Technician-in-the-Loop on write permissions.
  • For end-user-facing agents, prefer read-only permissions plus “create a ticket” over direct writes.