Using Madjik API for AI

Integrate Madjik's crypto market intelligence into your AI applications for enhanced decision-making and analysis.

Overview

Madjik API provides real-time and historical crypto market data optimized for AI consumption:

• Structured JSON responses ready for AI processing

• Normalized metrics (0-100 scales) for easy interpretation

• Rich context with related hypotheses and trading signals

• Low latency for real-time AI applications

Use Cases

1. AI Trading Assistants

Build AI assistants that provide trading insights:

import requests
import openai

def get_market_context():
    metrics = ["ME10030", "ME10014", "ME10016"]  # Sentiment, Funding, Liquidation
    context = []
    for m in metrics:
        resp = requests.get(
            f"https://api.madjik.io/v1/metrics/{m.lower()}",
            headers={"Authorization": "Bearer YOUR_API_KEY"}
        )
        context.append(resp.json())
    return context

# Feed to AI
context = get_market_context()
response = openai.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": "You are a crypto trading assistant."},
        {"role": "user", "content": f"Given this market data: {context}, what's your analysis?"}
    ]
)

2. Sentiment Analysis Enhancement

Combine Madjik sentiment with your own NLP:

# Get Madjik sentiment baseline
madjik_sentiment = requests.get(
    "https://api.madjik.io/v1/metrics/me10030",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
).json()

# Compare with your AI sentiment
your_sentiment = your_nlp_model.analyze(tweets)

# Weighted combination
combined = 0.6 * madjik_sentiment['value'] + 0.4 * your_sentiment

3. Risk Assessment AI

def ai_risk_assessment():
    risk_metrics = {
        "liquidation": "ME10016",
        "volatility": "ME10018",
        "counterparty": "ME10005"
    }
    
    risks = {}
    for name, metric_id in risk_metrics.items():
        resp = requests.get(
            f"https://api.madjik.io/v1/metrics/{metric_id.lower()}",
            headers={"Authorization": "Bearer YOUR_API_KEY"}
        )
        risks[name] = resp.json()['value']
    
    # AI interprets risk levels
    return ai_model.assess_risk(risks)

Best Practices

1. Cache responses - Reduce API calls, metrics update every 5 minutes

2. Batch requests - Request multiple metrics in parallel

3. Handle errors gracefully - AI should work with partial data

4. Provide context - Include metric descriptions in AI prompts

Related Metrics for AI

Metric	Best For
ME10030	Sentiment analysis input
ME10016	Risk assessment
ME10010	Whale behavior prediction
ME10014	Market positioning analysis

See Also

• ML Integration Guide

• A2A Integration Guide

• All Metrics