​

Why Shim Exists

1. Retry → Expensive ($0.002/retry × 1000 failures =$2/day)
2. OutputFixingParser → Slow (waits for full output, 2-5s delay)
3. Regex hacks → Brittle (breaks on nested objects)

​

What Shim Does

• Real-time repair (token-by-token, no buffering)
• Schema validation (type coercion, missing field detection)
• Confidence scoring (high/medium/low, never silent corruption)
• Zero data storage (privacy-first, GDPR compliant)

​

How It Works

// Before: Broken JSON from LLM
const raw = '{"name": "John", "age": "30"'; // Missing closing brace

// After: Shim repairs it
const response = await fetch('https://api.shim.so/v1/repair', {
  method: 'POST',
  headers: { 'Authorization': 'Bearer sk_xxx' },
  body: JSON.stringify({ raw_output: raw })
});

const { repaired, metadata } = await response.json();
// repaired: { name: "John", age: 30 }
// metadata.confidence: "high"
// metadata.repairs_applied: ["closed_object_bracket", "type_coercion"]

​

Key Features

​

1. Streaming-First Architecture

​

2. Schema-Aware Repair

• Coerce types ("30" → 30)
• Detect missing required fields
• Remove extra fields (strict mode)
• Validate nested objects

​

3. Never Fails Silently

• Confidence score (high/medium/low)
• Exact repairs applied
• Warnings for risky changes
• Errors for unrecoverable issues

​

4. Zero Data Persistence

• Raw LLM outputs
• Repaired JSON
• Field names or values

​

5. Performance

​

Who Uses Shim

​

Next Steps