> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kafkalabs.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LLMAnalyzer

> API reference for the LLMAnalyzer class

## Overview

The `LLMAnalyzer` class uses AI/LLM to perform contextual analysis of code for privacy issues that go beyond simple pattern matching.

## Constructor

```javascript theme={null}
new LLMAnalyzer()
```

**Example:**

```javascript theme={null}
const LLMAnalyzer = require('kafkacode/dist/LLMAnalyzer');

const analyzer = new LLMAnalyzer();
```

## Properties

### verbose

```javascript theme={null}
analyzer.verbose
```

Controls verbose logging output.

**Type:** `boolean`

## Methods

### analyzeFile(filePath, content, patternFindings)

Performs AI-powered analysis on file content.

```javascript theme={null}
async analyzeFile(
  filePath: string,
  content: string,
  patternFindings: Finding[]
): Promise<Finding[]>
```

**Parameters:**

* `filePath` (string): Path to the file
* `content` (string): File content
* `patternFindings` (Finding\[]): Findings from pattern scanner (context)

**Returns:** Promise resolving to array of findings

**Example:**

```javascript theme={null}
const LLMAnalyzer = require('kafkacode/dist/LLMAnalyzer');
const PatternScanner = require('kafkacode/dist/PatternScanner');

const patternScanner = new PatternScanner();
const llmAnalyzer = new LLMAnalyzer();

const content = fs.readFileSync('./src/config.js', 'utf-8');

// First, pattern scan
const patternFindings = patternScanner.scanContent('./src/config.js', content);

// Then, LLM analysis
const llmFindings = await llmAnalyzer.analyzeFile(
  './src/config.js',
  content,
  patternFindings
);

console.log(`LLM found ${llmFindings.length} additional issues`);
```

## How It Works

The LLM Analyzer:

1. **Takes context from pattern findings** - Uses initial pattern matches to focus analysis
2. **Analyzes code semantically** - Understands code context and intent
3. **Identifies subtle issues** - Finds privacy concerns that patterns miss
4. **Reduces false positives** - Filters out non-issues based on context
5. **Provides specific recommendations** - Gives actionable advice

## Usage Examples

### Basic LLM Analysis

```javascript theme={null}
const analyzer = new LLMAnalyzer();

const code = `
  const config = {
    apiKey: process.env.API_KEY,  // Good
    password: "hardcoded123"      // Bad
  };
`;

const findings = await analyzer.analyzeFile('config.js', code, []);

findings.forEach(f => {
  console.log(`${f.severity}: ${f.description}`);
  console.log(`Recommendation: ${f.recommendation}`);
});
```

### Combined Analysis

```javascript theme={null}
const patternScanner = new PatternScanner();
const llmAnalyzer = new LLMAnalyzer();

async function fullAnalysis(filePath) {
  const content = fs.readFileSync(filePath, 'utf-8');

  // Pattern-based detection
  const patternFindings = patternScanner.scanContent(filePath, content);

  // AI-powered analysis
  const llmFindings = await llmAnalyzer.analyzeFile(
    filePath,
    content,
    patternFindings
  );

  return [...patternFindings, ...llmFindings];
}
```

<Info>
  The LLM Analyzer helps reduce false positives by understanding code context, such as distinguishing between test data and real credentials.
</Info>

## Next Steps

<CardGroup cols={2}>
  <Card title="PatternScanner" icon="magnifying-glass" href="/api-reference/pattern-scanner">
    Pattern-based detection
  </Card>

  <Card title="How It Works" icon="cog" href="/concepts/how-it-works">
    Understand the dual-layer approach
  </Card>
</CardGroup>