Heavstal Sentinel

Heavstal Sentinel is a forensic AI detector designed to analyze text patterns (perplexity and burstiness). It determines the likelihood that a piece of text was generated by an AI model (like ChatGPT, Claude, or Gemini) versus a human.

Endpoint

POST /sentinel

Request Parameters

Field	Type	Required	Description
text	string	Yes	The content to analyze. Minimum 50 characters recommended for accuracy.

Example Usage

Python

import requests

url = "https://heavstal.com.ng/api/v1/sentinel"
payload = {
  "text": "This is the text I want to scan for AI patterns."
}
headers = {
  "x-api-key": "YOUR_API_KEY",
  "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Successful Response

{
"status": "success",
"creator": "HEAVSTAL TECH",
"data": {
  "score": 98,
  "verdict": "AI-Generated",
  "analysis": "The text exhibits low perplexity and consistent sentence structure typical of LLMs."
}
}