Skip to main content
Create a Review Run to analyze a document collection using one or more configured AI models. A Review Run can apply document classifications, generate document narratives, or perform both types of analysis to support your review objectives.
Note: Every Review Run is strategy-specific. The tags, models, instructions, and output fields shown in this documentation are examples only. Configure your Review Run to reflect the claims, defenses, themes, risks, and evaluation criteria defined in your approved strategy.
Before you begin
  • The required Review Run models have been created.
  • The document collection has been prepared.
To create a Review Run, complete the following steps.
  1. In the Project space menu, select Collections.
  2. Select a collection.
  3. Select Review Runs.
  4. Select Create Review Run.
  5. Enter a Name.
  6. Select the Review task for Text Classification or Text Generation.
  7. Select the model that corresponds with the task.
  8. Select the model version.
  9. Optional. Click Add Model to include additional models in your Review Run.
  10. Select either a Review batch or Dataset you want to use for the Review Run.
  11. Optional. Select the Multimodal processing toggle to include or exclude different file types.
  12. Optional. Select the checkbox for Favor recall over precision.
  13. Select Run.

​
Next steps

After creating the Review Run, monitor the processing status and review the results. You can use the classifications, narratives, and other outputs generated by the Review Run to identify documents that require additional analysis or review.