---
title: Custom extractors | Letta Docs
description: Build custom extractors to parse specific information patterns from agent responses for evaluation.
---

Create your own extractors to pull exactly what you need from agent trajectories.

While built-in extractors cover common cases, custom extractors let you implement specialized extraction logic for your specific use case.

## Why Custom Extractors?

Use custom extractors when you need to:

- **Extract structured data**: Parse JSON fields from agent responses
- **Filter specific patterns**: Extract code blocks, URLs, or formatted content
- **Combine data sources**: Merge information from multiple messages or memory blocks
- **Count occurrences**: Track how many times something happened
- **Complex logic**: Implement domain-specific extraction

## Basic Structure

```
from letta_evals.decorators import extractor
from letta_client import LettaMessageUnion
from typing import List


@extractor
def my_extractor(trajectory: List[List[LettaMessageUnion]], config: dict) -> str:
    """Extract custom content from trajectory."""
    # Your extraction logic here
    return extracted_text
```

## Example: Extract Memory Insert

```
from letta_evals.decorators import extractor


@extractor
def memory_insert_args(trajectory, config):
    """Extract arguments from memory_insert tool calls."""
    for turn in trajectory:
        for message in turn:
            if hasattr(message, 'tool_call') and message.tool_call:
                if message.tool_call.name == "memory_insert":
                    return str(message.tool_call.arguments)
    return ""
```

## Registration

Custom extractors are automatically registered when you import them in your suite’s setup script or custom evaluators file.

## Next Steps

- [Built-in Extractors](/guides/evals/extractors/builtin/index.md) - Available extractors
- [Extractors Concept](/guides/evals/concepts/extractors/index.md) - Understanding extractors