Skip to content

Configure an agent

Open a company in HQ Console, choose Agents, then choose the Settings gear for an agent. Agent Settings keeps the full operating picture in one compact workspace:

  • Configuration contains profile and model values that save together.
  • Controls contains access, capacity, and runtime actions that apply immediately.
  • Live systems contains health signals and expandable connection managers.

Most explanatory copy lives behind the help icon beside each section, leaving the values and current state visible at a glance.

Editing efficiently

Choose a configuration value to edit it in place. Only one editor or picker stays open at a time. Clicking elsewhere closes the open editor while keeping its draft staged for Save; pressing Escape cancels that field’s current edit instead. The footer tells you whether there are unsaved configuration changes, and Save remains disabled until a staged value differs from the saved configuration.

Connection rows and the Agent size row expand in place. Clicking elsewhere collapses the open panel without changing anything. Actions labeled Applies now do not wait for the configuration Save button and show their own confirmation when the change is consequential.

Configuration reference

SettingPurposeNotes
HandleStable agent identifierChosen during creation. It is used in company identity, email, and vault paths and is not a normal profile edit.
Display nameHuman-readable name shown in HQ and connected channelsThe Console enforces channel-safe length limits.
AvatarProfile imageHQ validates the image and file size before saving.
TitleShort role labelUse a role people can recognize, such as Research Lead.
DescriptionOne-line responsibility statementState what the agent owns and when teammates should contact it.
ProviderRuntime familySelected at creation from the providers enabled for your account. Provider migration is not available in general Agent Settings.
ModelModel used for new workMust be compatible with the provider and authentication method.
Reasoning effortDepth used for supported modelsConsole values are Low, Medium, High, and Extra high. Grok does not use this setting.
SpeedStandard or Fast service tierAvailable for supported Codex configurations. Fast can increase provider cost.
Membership roleCompany permissions granted to the agentAn agent can be a member or admin, but cannot become the company owner.
OwnersPeople responsible for the agentThe creator is the initial owner. Additional ownership is shown only when enabled for the company.
GroupsCompany groups the agent belongs toUse groups for organization and policy-driven access.
Agent sizeRuntime capacity and concurrencyShows the current size, lanes, workers, and company-specific monthly price. Open the picker to compare Basic, Power, and Dev. See Agent sizes and billing.
HQ MCPAgent connection to HQ tools and contextOwners and admins manage it under Integrations > For Agents while the runtime is running.
SlackSlack app connection and diagnosticsAttach, finish a pending install, inspect delivery, or intentionally detach the app.
TelegramTelegram bot connection and caller groupConnect a managed bot or supply a token, then choose who can call it.
Runtime controlsStart, stop, reauthenticate, or removeRemoval deprovisions the agent and requires confirmation.

Model compatibility

HQ validates the model name against the selected provider:

  • Codex supports OpenAI model families such as gpt-* and o*.
  • Grok supports grok-* models.
  • Claude supports Anthropic model families such as claude-*, sonnet, opus, and haiku.

The available list is the source of truth for your account. For Codex with ChatGPT subscription authentication, Agent Settings recommends gpt-5.6-sol; Sol is supported wherever it is available to the signed-in ChatGPT account. Only models whose names end in -codex require OpenAI API-key authentication. Agent Settings filters incompatible choices and returns an actionable message if a saved value does not match the agent’s authentication method. The Console also prevents model and reasoning combinations that the runtime cannot honor.

Profile guidance

A useful agent profile answers three questions:

  • What does this agent own?
  • What requests should teammates send it?
  • What should a teammate do when the request is outside its scope?

Keep the title short and make the description operational. Channel users should be able to decide whether to mention the agent without opening HQ Console.

Managed settings

Changing an agent’s box size is a confirmed billing action available from Agent Settings — see Agent sizes and billing. The backend also supports lower-level controls for autoscaling, caller email allowlists, provider migration, and direct MCP state. These are API or control-plane fields, not standard Agent Settings controls. An invalid value can prevent the runtime from starting or reject channel callers.

Credentials are stored as vault references. Raw provider keys and channel tokens are never returned by the settings API.