AI Teammates
Use terraform to manage Kubiya AI Teammates
Last updated
Was this helpful?
Use terraform to manage Kubiya AI Teammates
Last updated
Was this helpful?
AI Teammates are the heart of Kubiya. As an operator, you may prefer to create and manage your AI Teammates using IaC.
Want to know more about AI Teammates in Kubiya?
Note: Creating an AI Teammate requires having already created a and a , as these are mandatory fields for AI Teammates.
Provides a Kubiya Agent resource. This allows AI Teammates to be created, updated, and deleted on the Kubiya platform.
The following arguments are supported:
name
- (Required) The name of the agent.
runner
- (Required) The runner that will execute the agent. Must reference an existing runner.
description
- (Required) A detailed description of the agent's capabilities and purpose.
model
- (Optional) The LLM model to use. Defaults to "gpt-4o".
is_debug_mode
- (Optional) Whether to enable debug mode. Defaults to false.
users
- (Optional) List of users that have access to this agent. Each user must exist in the Kubiya platform.
groups
- (Optional) List of groups that have access to this agent. Each group must exist in the Kubiya platform.
sources
- (Optional) List of knowledge sources to be used by the agent. Each source must exist in the Kubiya platform.
secrets
- (Optional) List of secrets accessible to the agent. Each secret must exist in the Kubiya platform.
integrations
- (Optional) List of integrations to enable for the agent. Each integration must exist in the Kubiya platform.
environment_variables
- (Optional) Map of environment variables for the agent.
starters
- (Optional) List of conversation starters. Each starter has:
name
- The display name of the starter.
command
- The command or prompt for the starter.
In addition to the arguments above, the following attributes are exported:
id
- The ID of the agent.
owner
- The owner of the agent.
created_at
- The timestamp when the agent was created.
Agents can be imported using the id
: