Running an Experiment

Prerequisite

First configure your Experiment, see Creating an Experiment

Running an Experiment

Once configured, you can run the Experiment using the Run button.

Depending on the Dataset size it may take a few minutes to run all model prompts generations.

Once successful your Experiment Run Status will change to Completed. You can then see Experiment Results.

📘

To run another iteration of the Experiment, with different prompts or data, use the New Run button. A new Experiment Run will be created in Draft state.

Seeing Experiment Results

Report

Once an Experiment is ran, its status will change from Running to Completed

The right side of the table will be filled with results.

Under each Column corresponding to each Prompt you can see results for:

• Latency.
• Costs.
• Evaluators.

Logs

Switching to the Logs tab lets you see the details of each call.

Within logs you can process Feedback and build Curated datasets.

By hovering a cell you can also directly access the related log using the See log button.

For easy comparison between models and prompts, you can also click the Show Comparison button. This will open the panel below which allows you to quickly compare the output side by side and navigate through the different rows.

Export

You can export datasets and results in CSV, JSON and JSONL formats using the Export button.