Determine SSO Classification (Yes / No / Not Supported / Not Known)
Automatically classify whether a discovered application has SSO enabled, supports SSO but is not integrated, does not support SSO, or cannot be reliably determined—using a structured AI (GPT) Action and updating the result directly in Torii.
Use this AI Prompt in a Torii Workflow to classify whether a discovered application is SSO-enabled (based on Torii discovery sources) or whether the vendor supports SSO but it isn’t currently integrated.
This guide is designed to:
- Generate a single, strict output value via an AI (GPT) Action
- Store that value in a single-select custom Application Details field
- Persist it onto the app record via a Custom Action calling Torii’s Update app endpoint
What this prompt determines
The prompt returns exactly one of these values:
-
Yes
The app appears in an SSO/IdP discovery source (in this example: Okta), implying SSO is enabled. -
No
The vendor/app supports SSO (SAML/OIDC/etc.), but the app is not present in the SSO/IdP source list.
(Meaning: SSO could be enabled, but it’s not integrated via the detected IdP source.) -
Not Supported
The vendor/app clearly does not support SSO. -
Not Known
There isn’t enough reliable information to determine support.
Inputs (Torii personalization tokens)
This prompt uses:
- Application name:
[Trigger.App.Name] - Vendor name:
[Trigger.App.Vendor] - Discovery sources list:
[Trigger.App.Sources](list of systems where Torii discovered the app)
Output field (Application Details)
Create a single-select custom Application Details field (example: SSO enabled state) with these exact options:
YesNoNot SupportedNot Known
When you create the field, Torii assigns an Internal Name (custom fields typically start with c_).
You’ll use that internal name in the Update app API request.
Reference (Application Details settings):
https://support.toriihq.com/hc/en-us/articles/32565395389723-Settings-Application-Details
Workflow setup
- Trigger: New application discovered (or any workflow where the subject app is set).
- Action: AI (GPT) Action
- Paste the prompt below
- Add Response mapping to store the model output into a workflow token (example:
SSO)
- Action: Custom Action (HTTP Request)
- Call
PUT /apps/{idApp}to update the app record - Set your custom field internal name to the AI output token
- Call
AI (GPT) Actions documentation:
https://support.toriihq.com/hc/en-us/articles/36726298957083-AI-GPT-Actions
Prompt (paste into AI (GPT) Action)
# Prompt: Determine SSO Classification
```text
You are assisting with application governance inside Torii.
Your task:
Determine the correct SSO classification value for the discovered application.
Input:
You will receive application data including:
- Application name
- Vendor name (if available)
- A list of "sources" (systems from which the application was discovered, e.g., Okta, Google Workspace, Slack, Browser Extension, etc.)
Decision Logic (in order):
1. If any source name contains the word "okta" (case-insensitive):
Return: Yes
2. If Okta is NOT in the sources:
Determine whether the vendor/application supports SSO.
- If the vendor clearly supports SSO (e.g., supports SAML, OIDC, SSO integrations), return:
No
- If the vendor clearly does NOT support SSO, return:
Not Supported
- If it is not possible to confidently determine whether the vendor supports SSO, return:
Not Known
Input:
Application: [Trigger.App.Name]
Vendor: [Trigger.App.Vendor]
Sources: [Trigger.App.Sources]
Output Requirements:
- Return ONLY one of the following exact values:
Yes
No
Not Supported
Not Known
- If you are uncertain, return Not Known.
- Do not include JSON.
- Do not include punctuation.
- Do not include explanations.
- Do not include markdown.
- Do not include extra whitespace.
- Output must be exactly one of the allowed values.
```Response mapping (AI action)
In the AI (GPT) Action, add Response mapping so the output is usable downstream.
Example:
- Name:
SSO - Value: the model response (single line)
Use the output: Update the app record (Custom Action → Update app endpoint)
This is the end-to-end pattern: AI output → workflow token → update the app record → populate Application Details field.
Step 1 — Identify your custom field internal name
In Settings → Application Details, locate your field (e.g., SSO enabled state) and copy its Internal Name.
Example internal name: c_sso
Step 2 — Configure the Custom Action (HTTP Request)
-
Method:
PUT -
URL:
https://api.toriihq.com/v1.0/apps/[Trigger.App.ID] -
Headers:
Content-Type: application/jsonAccept: */*Authorization: Bearer <YOUR_TORII_API_KEY>(recommended: store in Secrets Vault)
-
Body (example):
{
"c_sso": "[AI action.response.SSO]"
}Replace:
c_ssowith your field internal nameSSOwith the Response mapping token name you used in the AI action
Update app endpoint reference:
https://developers.toriihq.com/reference/putappsidapp
Testing checklist
- Sources include
Okta→ expectYes - No
Okta, vendor supports SSO → expectNo - No
Okta, vendor does not support SSO → expectNot Supported - No
Okta, cannot confirm support → expectNot Known
Customization
- If your org uses additional IdPs, expand the “Yes” check in rule #1 to match those source names (case-insensitive).
- If you want the model to research vendor SSO support, enable Search the web (requires your own OpenAI key):
https://support.toriihq.com/hc/en-us/articles/38227217845531-Managing-AI-Settings
Updated about 2 hours ago