Determine AI Module Classification (AI Native / AI Enabled / No AI / Not Known / Not Applicable)

Intelligently classify whether an application is AI Native, AI Enabled, No AI, Not Known, or Not Applicable by prioritizing Torii tag metadata and enhancing accuracy with optional web-backed validation—then persist the result directly to Application Details via the Update App API. Use this AI Prompt in a Torii Workflow to classify whether a discovered application includes artificial intelligence functionality, and if so, how central AI is to the product.

This version incorporates Torii Application Tags as a primary, authoritative signal.

This guide follows the same implementation pattern as the SSO Classification and Hosting Type guides:

Generate a strict, single 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:

AI Native
Artificial intelligence is a core, foundational component of the product.
AI Enabled
The product includes AI-driven features, but AI is not the primary function.
No AI
There is credible evidence that the product does not include AI functionality.
Not Known
There is insufficient reliable information to confidently determine AI functionality.
Not Applicable
The entity does not represent a software product where AI classification is meaningful.

Inputs (Torii personalization tokens)

This prompt uses:

Application name: [Trigger.App.Name]
Vendor name: [Trigger.App.Vendor]
Website: [Trigger.App.Website]
Tags: [Trigger.App.Tags]

Tags are treated as an authoritative signal.
If tags clearly indicate AI classification, they override other signals.

Output field (Application Details)

Create a single-select custom Application Details field (example: AI Module Classification) with these exact options:

AI Native
AI Enabled
No AI
Not Known
Not Applicable

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: AI-Module)
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

AI (GPT) Actions documentation:
https://support.toriihq.com/hc/en-us/articles/36726298957083-AI-GPT-Actions

Prompt (paste into AI (GPT) Action)

# Prompt: Determine AI Module Classification (Tag-Aware)

```text
You are assisting with application governance inside Torii.

Your task:
Determine the AI classification for the discovered application.

IMPORTANT:
Application tags are authoritative. If tags clearly indicate AI classification, use them as the primary decision signal.

Input:
You will receive:
- Application name
- Vendor name (if available)
- Vendor website (if available)
- Tags (list of application tags)

Decision Logic (in order):

1. Evaluate Tags FIRST.

   If tags clearly indicate the product is primarily AI-focused (examples: artificial intelligence, ai platform, ai model, machine learning platform, ai development, ai agent), return:
   AI Native

   If tags indicate AI-related capabilities but not primary AI platform (examples: ai generated images, ai assistant, ai feature, ai enhancement), return:
   AI Enabled

   If tags clearly indicate absence of AI capability, return:
   No AI

2. If tags are absent or inconclusive, evaluate vendor positioning and website information.

   - If AI is a core, foundational capability, return:
     AI Native

   - If AI features are present but not primary, return:
     AI Enabled

   - If there is credible evidence that AI is not included, return:
     No AI

   - If the entity does not represent a software product in which AI classification is meaningful, return:
     Not Applicable

3. If you cannot confidently determine classification, return:
   Not Known

Input:
Application: [Trigger.App.Name]
Vendor: [Trigger.App.Vendor]
Website: [Trigger.App.Website]
Tags: [Trigger.App.Tags]

Output Requirements:
- Return ONLY one of the following exact values:
  AI Native
  AI Enabled
  No AI
  Not Known
  Not Applicable
- 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.
```

Use the output: Update the app record (Custom Action → Update app endpoint)

Method: PUT
URL: [https://api.toriihq.com/v1.0/apps/Trigger.App.ID]

Example body:

{
  "c_ai_module": "[AI action.response.AI-Module]"
}

Update app endpoint reference:
https://developers.toriihq.com/reference/putappsidapp

Optional: Enable “Search the web”

To improve classification accuracy when tags are inconclusive, enable Search the web in the AI (GPT) Action.

This requires configuring your own OpenAI API key:

https://support.toriihq.com/hc/en-us/articles/38227217845531-Managing-AI-Settings

Testing checklist

App tagged with AI platform categories → expect AI Native
App tagged with AI feature categories → expect AI Enabled
App with no AI tags but AI-heavy website → expect AI Native or AI Enabled
App with no AI signals → expect No AI or Not Known
Non-software vendor → expect Not Applicable

This version prioritizes Torii metadata first, then public signals, while maintaining deterministic workflow-safe outputs.