> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-docsja-1783484944-f86c4f0.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# How to add evaluators to an existing experiment

After running an experiment, you may want to **add new evaluation metrics without re-running your application**. This is useful when you've added new evaluators or want to apply different scoring criteria to existing results. Instead of re-executing your target function on all examples, you can evaluate the existing experiment traces directly.

To add evaluators to an existing experiment, pass the experiment name or ID to `evaluate()` / `aevaluate()` (Python), or `Evaluation.evaluateExisting()` (Java) instead of a target function. The evaluators run on the cached traces from the original experiment, accessing the inputs, outputs, and any intermediate steps that were logged.

## Example

<CodeGroup>
  ```python Python theme={null}
  from langsmith import evaluate

  def always_half(inputs: dict, outputs: dict) -> float:
      return 0.5

  experiment_name = "my-experiment:abc"  # Replace with an actual experiment name or ID

  evaluate(experiment_name, evaluators=[always_half])
  ```

  ```java Java theme={null}
  import com.langchain.smith.evaluation.DynamicRunEvaluatorKt;
  import com.langchain.smith.evaluation.Evaluation;
  import com.langchain.smith.evaluation.EvaluateExistingParams;
  import com.langchain.smith.evaluation.RunEvaluator;

  String experimentId = "your-experiment-id";

  RunEvaluator alwaysHalf =
      DynamicRunEvaluatorKt.runEvaluatorFromOutputsReference(
          (outputs, reference) -> 0.5);

  Evaluation.evaluateExisting(
      client,
      experimentId,
      EvaluateExistingParams.builder().addEvaluator(alwaysHalf).build());
  ```
</CodeGroup>

## Related topics

* [Retry failed examples in experiments](/langsmith/evaluate-with-retry)
* [Run an evaluation](/langsmith/evaluate-llm-application)
* [Run an evaluation asynchronously](/langsmith/evaluation-async)

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/evaluate-existing-experiment.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>