Get started

Quickstart

Send text, get back the AI-slop patterns found in it. Three steps, about two minutes.

1. Create an account and a key

Sign up: you get $3 of free credit and no card is needed. Open API keys in the console, choose Create key, and copy it. It is shown once.

export ELLORA_API_KEY="elk_live_..."

2. Send text

One request to POST https://platform-api.getellora.com/v1/detect:

curl https://platform-api.getellora.com/v1/detect \
  -H "Authorization: Bearer $ELLORA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Let'\''s delve into the rich tapestry of modern marketing. It'\''s worth noting that every team must navigate an ever-evolving landscape."}'
import os
import requests

response = requests.post(
    "https://platform-api.getellora.com/v1/detect",
    headers={"Authorization": f"Bearer {os.environ['ELLORA_API_KEY']}"},
    json={"text": "Let's delve into the rich tapestry of modern marketing. It's worth noting that every team must navigate an ever-evolving landscape."},
    timeout=10,
)
response.raise_for_status()
result = response.json()

print(result["findings_count"])
for finding in result["findings"]:
    print(finding["severity"], finding["rule_id"], "-", finding["suggestion"])
const response = await fetch("https://platform-api.getellora.com/v1/detect", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ELLORA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ text: "Let's delve into the rich tapestry of modern marketing. It's worth noting that every team must navigate an ever-evolving landscape." }),
});

if (!response.ok) throw new Error(`Ellora ${response.status}: ${await response.text()}`);
const result = await response.json();

console.log(result.findings_count);
for (const finding of result.findings) {
  console.log(finding.severity, finding.rule_id, "-", finding.suggestion);
}

3. Read the findings

Each finding names the rule that matched, the sentence, the matching excerpt, why it reads as machine-written, and a suggestion. findings_count counts findings by severity. The API gives no verdict: if you want a pass or fail rule, build it from findings_count, for example findings_count.red === 0. Yellow findings need a judgment call and blue findings are optional polish.

{
  "id": "req_01jc8m3y6q0v7k2h9d4x5n8r1t",
  "ruleset_version": "3.4.0-feedhive.1",
  "words_count": 20,
  "characters_count": 119,
  "cost": 0.0002,
  "findings_count": {
    "total": 8,
    "red": 5,
    "yellow": 0,
    "blue": 3
  },
  "findings": [
    {
      "id": "01m6ya0a1b2c3d4e5f6g7h8j9k",
      "rule_id": "ai.delve",
      "category": "ai",
      "severity": "red",
      "scope": "sentence",
      "sentence": 1,
      "excerpt": "Let's delve into the rich tapestry of modern marketing.",
      "reason": "A stock phrase can flatten the writer's meaning.",
      "suggestion": "use a specific verb: dig, explore, look at"
    }
  ],
  "stored": true
}

The example is trimmed to the first of its eight findings. cost is what this call cost, in US dollars, as a number. The response has no score and never contains rewritten text.

Next