> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tuteliq.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Quickstart
> Get up and running with Tuteliq in under 5 minutes
Sign up and create an API key from the [Tuteliq Dashboard](https://tuteliq.ai/dashboard). Each key is scoped to an environment (production, staging, or development) which determines your rate limits and tier.
Store your API key securely. It is displayed only once at creation time and is hashed server-side.
```bash npm theme={"dark"}
npm install @tuteliq/sdk
```
```bash pip theme={"dark"}
pip install tuteliq
```
```swift Swift Package Manager theme={"dark"}
// Add to Package.swift dependencies:
.package(url: "https://github.com/Tuteliq/swift.git", from: "1.0.0")
```
Use `detectUnsafe` to analyze a piece of text for harmful content.
```typescript Node.js theme={"dark"}
import { Tuteliq } from "@tuteliq/sdk";
const tuteliq = new Tuteliq(process.env.TUTELIQ_API_KEY);
const result = await tuteliq.detectUnsafe({
content: "Hey, want to meet up after school? Don't tell your parents.",
context: { ageGroup: "10-12" },
});
console.log(result.severity); // "high"
console.log(result.categories); // ["grooming"]
console.log(result.credits_used); // 1
```
```python Python theme={"dark"}
from tuteliq import Tuteliq
client = Tuteliq(api_key=os.environ["TUTELIQ_API_KEY"])
result = client.detect_unsafe(
text="Hey, want to meet up after school? Don't tell your parents.",
age_group="10-12",
)
print(result.severity) # "high"
print(result.categories) # ["grooming"]
print(result.credits_used) # 1
```
```bash cURL theme={"dark"}
curl -X POST https://api.tuteliq.ai/api/v1/safety/unsafe \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Hey, want to meet up after school? Don'\''t tell your parents.",
"context": { "age_group": "10-12" }
}'
```
**Expected response:**
```json theme={"dark"}
{
"unsafe": true,
"severity": "high",
"risk_score": 0.91,
"categories": ["grooming"],
"confidence": 0.92,
"rationale": "Potential grooming pattern detected: solicitation of a private meeting with secrecy directive.",
"recommended_action": "immediate_intervention",
"language": "en",
"language_status": "stable",
"credits_used": 1
}
```
Use the fraud detection endpoints to analyze content for social engineering, scams, and more.
```typescript Node.js theme={"dark"}
const result = await tuteliq.detectSocialEngineering({
content: "I'm from your school's IT department. I need your password to fix your account urgently.",
context: { ageGroup: "10-12" },
});
console.log(result.detected); // true
console.log(result.severity); // 0.89
console.log(result.categories); // [{ tag: "AUTH_IMPERSONATION", label: "Authority Impersonation", confidence: 0.92 }]
console.log(result.recommended_action); // "Block and report to platform administrators"
```
```python Python theme={"dark"}
result = client.detect_social_engineering(
text="I'm from your school's IT department. I need your password to fix your account urgently.",
context={"age_group": "10-12"},
)
print(result.detected) # True
print(result.severity) # 0.89
print(result.categories) # [{"tag": "AUTH_IMPERSONATION", "label": "Authority Impersonation", "confidence": 0.92}]
print(result.recommended_action) # "Block and report to platform administrators"
```
```bash cURL theme={"dark"}
curl -X POST https://api.tuteliq.ai/v1/fraud/social-engineering \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "I'\''m from your school'\''s IT department. I need your password to fix your account urgently.",
"context": { "ageGroup": "10-12" }
}'
```
Analyze content against multiple detectors in a single API call using `/analyse/multi`.
```typescript Node.js theme={"dark"}
const result = await tuteliq.analyseMulti({
content: "Send me your bank details and I'll transfer the money. Don't tell anyone about this.",
detections: ["social-engineering", "mule-recruitment", "coercive-control"],
context: { ageGroup: "13-15" },
});
console.log(result.summary.highest_severity); // "critical"
console.log(result.summary.total_credits_used); // 3
console.log(result.results.length); // 3
```
```bash cURL theme={"dark"}
curl -X POST https://api.tuteliq.ai/v1/analyse/multi \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Send me your bank details and I'\''ll transfer the money. Don'\''t tell anyone about this.",
"endpoints": ["social-engineering", "mule-recruitment", "coercive-control"],
"context": { "ageGroup": "13-15" }
}'
```
**Testing without credits?** Create a sandbox API key in your [Dashboard](https://tuteliq.ai/dashboard) (Settings > API Keys > Environment: Sandbox). Sandbox keys run real analysis with zero credit consumption — 50 calls/day for free.
**What's next?** Explore the full [API Reference](/api-reference/introduction) or dive into one of our SDKs: [Node.js](/sdks/node), [Python](/sdks/python), [Swift](/sdks/swift), [Kotlin](/sdks/kotlin), [Flutter](/sdks/flutter), [React Native](/sdks/react-native), [.NET](/sdks/dotnet), [Unity](/sdks/unity), [CLI](/sdks/cli), or [MCP Server](/sdks/mcp).
## Next steps
Learn about API key environments and authentication methods.
Understand per-endpoint credit costs and usage tracking.
Handle errors gracefully with retry strategies.
Full coverage of all nine KOSA harm categories.