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

# Evaluating

> Measure workflow quality using LangWatch’s evaluation tools to ensure reliable LLM pipeline and agent test performance.

<iframe width="720" height="405" src="https://www.youtube.com/embed/-sQikz38yBI" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowFullScreen />

## The Importance of Evaluation

Evaluators are essential tools for measuring LLM output quality. When you have a reliable way to measure quality, it becomes much easier to:

* Compare different LLM models
* Test prompt variations
* Validate feature additions
* Ensure quality remains consistent during upgrades

## Types of Evaluators

On the video, a few evaluators are introduced:

### Exact Match Evaluator [(0:56)](https://www.youtube.com/watch?v=-sQikz38yBI\&t=56s)

The simplest form of evaluation, perfect for classification tasks:

* Compares LLM output directly with expected output
* Uses straightforward string matching
* Ideal for categorical outputs where precision is crucial
* Works well when you need strict matching

### Answer Correctness Evaluator [(4:44)](https://www.youtube.com/watch?v=-sQikz38yBI\&t=264s)

Comparison with golden answers for factual accuracy:

* Uses another LLM to assess if answers are factually equivalent
* Looks beyond exact wording to evaluate semantic meaning
* Particularly useful for QA systems and knowledge-based tasks
* Can handle variations in phrasing while maintaining accuracy checking

### LLM as Judge Evaluator [(7:01)](https://www.youtube.com/watch?v=-sQikz38yBI\&t=421s)

Flexible evaluation for custom criteria:

* Allows custom prompts to define evaluation criteria
* Useful when you don't have expected outputs
* Can evaluate subjective qualities (conciseness, tone, style)
* Returns boolean (true/false) or scored (0-1) results

## Working with Evaluators

### Setting Up Evaluators [(1:32)](https://www.youtube.com/watch?v=-sQikz38yBI\&t=92s)

To implement an evaluator:

1. Drag and drop the desired evaluator onto your workflow
2. Connect appropriate inputs (output from LLM, expected output from dataset)
3. Configure any additional parameters or criteria
4. Run evaluation on individual examples or full test sets

### Running Evaluations [(2:28)](https://www.youtube.com/watch?v=-sQikz38yBI\&t=148s)

The evaluation process:

1. Select your test dataset
2. Choose appropriate evaluator
3. Run evaluation across all test examples
4. Review accuracy scores and individual results

### Improving Results [(9:14)](https://www.youtube.com/watch?v=-sQikz38yBI\&t=554s)

After setting up evaluation:

* Make incremental changes to your workflow
* Test impact immediately through re-evaluation
* Track improvements in accuracy scores
* Iterate on prompts and parameters based on results

## Summary

* Choose evaluators that match your quality criteria
* Use multiple evaluators for different aspects of quality
* Start with simple evaluators before moving to complex ones
* Consider both strict and semantic matching depending on your use case
* Use evaluation results to guide optimization efforts

The ability to properly evaluate LLM outputs sets the foundation for automated optimization, which will be covered in the next tutorial.