Skip to main content
PATCH
Update a guardrail

Authorizations

Authorization
string
header
required

API key from waterr.ai/settings?tab=api-keys. Send as Authorization: Bearer wai_<your_key>.

Path Parameters

id
string<uuid>
required

Body

application/json
guardrail_name
string
Pattern: ^[a-zA-Z0-9_-]{1,64}$
guardrail_prompt
string
Maximum string length: 10000
active
boolean

Response

Guardrail updated.

A named prompt fragment. Every guardrail attached to a scenario is appended to that scenario's system prompt as a bullet under a ## Guardrails heading, so the persona treats it as a non-negotiable rule for the whole conversation.

id
string<uuid>
required
Example:

"9b1f3d70-2a4e-4c8b-8f1a-6d5c4b3a2e10"

guardrail_name
string
required

Handle for the rule. Unique per account. Used in the API and in your logs — it is never shown to the persona or the participant.

Maximum string length: 64
Pattern: ^[a-zA-Z0-9_-]{1,64}$
Example:

"no_competitors"

guardrail_prompt
string
required

The rule itself, appended verbatim to the system prompt. Write it as a direct instruction. Encrypted at rest.

Maximum string length: 10000
Example:

"Only mention products within Our Company Inc. during conversations; never discuss competitors."

active
boolean
default:true
required

Account-level kill-switch. false removes the rule from every scenario at once.

Example:

true

membership_id
string<uuid>
Example:

"a1b2c3d4-e5f6-7890-abcd-ef0123456789"

scenarios
object[]

Scenarios this guardrail is attached to. Returned only on the single-guardrail read.

created_at
string<date-time>
Example:

"2026-09-09T12:34:56.000Z"

updated_at
string<date-time>
Example:

"2026-09-09T12:34:56.000Z"