Skip to main content
A guardrail sits idle until it’s attached to an agent. Attach it in the Studio when creating or editing an agent, or via the API by including it in the agent’s guardrail array, the same pattern used for tool, mcp, and knowledge_base.

​
In the Studio

1

Open the agent

Open the agent you want to attach the guardrail to in app.trugen.ai, or start creating a new one.
2

Go to the Guardrails tab

In the agent’s configuration tabs, open Guardrails.
3

Select one or more guardrails

Pick from your workspace’s guardrail list. There’s no cap. Attach as many as the conversation needs.
4

Save

Save the agent. The change takes effect on the next session. See When updates take effect below.

​
Via API

Guardrail attachment goes through the same agent endpoints as everything else attached to an agent:
Body (either method):
An array of {id, name}, the same shape as the agent’s tool and mcp keys. Add more objects to attach more guardrails in one call.
Attached guardrails then appear under the "guardrail" key in GET /v1/ext/agent/{id}, alongside tool, mcp, and knowledge_base.

​
Via a template

Attach guardrails to a template instead of individual agents when you want every agent built from that template to inherit the same safety checks:
Any agent later created from this template automatically has the guardrail attached.

​
Detaching a guardrail

There’s no partial-remove endpoint. PATCH is insert-only: it cannot detach anything. The only way to remove a single guardrail from an agent is PUT with the full guardrail array minus the entry you want gone, since PUT deletes and reinserts the whole list.
If you only have the guardrail’s id you want to remove, fetch the agent first (GET /v1/ext/agent/{id}), drop that entry from the returned guardrail array, then PUT the rest back.

​
When updates take effect

Guardrails are fetched and embedded into an agent’s dispatch config exactly once, at the moment a new conversation is created. They’re never re-fetched mid-call. Any attach, detach, or edit you make after a call has already started has zero effect on that running call. It only applies to the next session. If you need a change to apply immediately, end the active session explicitly with DELETE /v1/conversation/{conversationId} after your update lands.

​
What’s Next?

Runtime Behavior

What happens the moment a guardrail fires, and the webhook payload it sends.

Creating a Guardrail

Field reference and how to write a prompt the LLM will act on.