> ## Documentation Index > Fetch the complete documentation index at: https://www.getmaxim.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Agent Evals > Test Agents using datasets to evaluate performance across examples After testing in the playground, evaluate your Agents across multiple test cases to ensure consistent performance using the test runs. Add test cases by creating a [Dataset](/library/datasets/import-or-create-datasets#create-datasets-using-templates). For this example, we'll use a Dataset of product images to generate descriptions. Dataset with product images for testing Create an Agent that processes your test examples. In this case, the agent generates product descriptions, translates them to multiple languages, and formats them to match specific requirements. Agent for product description generation Open the test configuration by clicking `Test` in the top right corner. Select your dataset from the dropdown. Test configuration with dataset and evaluator options Select [Evaluators](/library/evaluators/pre-built-evaluators/overview) to measure the quality of outputs and map the evaluator variables to the dataset columns. You can read more about mapping evaluator variables [here](/library/evaluators/variables-mapping#prompt-variable-mapping). Test configuration with dataset and evaluator options You can use create and use [Presets](/offline-evals/via-ui/advanced/presets) for your test runs to save time and avoid repeating the same configuration. Monitor the [test run](/offline-evals/concepts#test-runs) to analyze the performance of your Prompt Chain across all inputs. Test run results showing performance metrics