Run Framework

POSThttps://api.confident-ai.com/v2/rt-frameworks/{rtFrameworkId}/run

Runs the named risk categories of a red teaming framework against your AI connection or prompt, and returns the id of the risk assessment it started. The assessment runs in the background; follow it on the Confident AI platform. Provide exactly one target: aiConnectionId or promptAlias.

POST/v2/rt-frameworks/{rtFrameworkId}/run

curl -X POST "https://api.confident-ai.com/v2/rt-frameworks/{rtFrameworkId}/run" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>" \
  -H "Content-Type: application/json" \
  -d '{
  "identifier": "pre-release-2025-01",
  "riskCategories": [
    "Data protection"
  ],
  "exposure": "LOW",
  "aiConnectionId": "<AI-CONNECTION-ID>",
  "promptAlias": "customer-support",
  "promptCommit": "bab04ce",
  "generationMode": "AI_CONNECTION",
  "attackEngine": {
    "generationGuidelines": [
      "Write in the voice of a frustrated customer."
    ]
  }
}'

200

{
  "success": true,
  "data": {
    "id": "<RISK-ASSESSMENT-ID>"
  },
  "link": "https://app.confident-ai.com/project/<PROJECT-ID>/risk-profile/assessments/<RISK-ASSESSMENT-ID>",
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Path parameters

rtFrameworkIdstringRequired
The id of the red teaming framework.

Request body

identifierstring
A human-readable identifier for the risk assessment, shown on the Confident AI platform.
riskCategorieslist of stringsRequired
The names of the framework's risk categories to run. Every name must belong to this framework.
exposureenumRequired
A three-step scale, LOW to HIGH, used for how exposed a system under test is and how easily an attack method exploits it.
Show 3 enum valuesHide 3 enum values
- LOW
- MEDIUM
- HIGH
aiConnectionIdstring
The id of the AI connection to attack. Send this or promptAlias, never both.
promptAliasstring
The alias of the prompt to attack. Send this or aiConnectionId, never both.
promptCommitstring
The commit hash of the prompt to attack. Requires promptAlias; defaults to its latest commit.
generationModeenum
Where the actual outputs come from when running a dataset: AI_CONNECTION generates them with an AI connection, PROMPT with a prompt. Omit it when you supply at most one of aiConnectionId or promptAlias, and Confident AI infers the mode from whichever you sent.
Show 2 enum valuesHide 2 enum values
- AI_CONNECTION
- PROMPT
attackEngineobject
How attacks are generated for this run.
Show 1 propertyHide 1 property
- generationGuidelineslist of strings
  Extra instructions the attacker follows when generating attacks against this system.

Response

Run Framework succeeded.

successboolean
Indicates if the request was successful.
dataobject
A reference to a risk assessment by its id.
Show 1 propertyHide 1 property
- idstring
  The id of the risk assessment the run started.
linkstring
This is the URL of the resource on the Confident AI platform.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI