batch filter

readme-sync/v0/best-practices/0300 - metrics.md

@@ -14,13 +14,19 @@ Extraction coverage
 
 Extraction coverage measures how fully an extraction captures your target data from the document. For example, a coverage score of 70% for an extraction with no validation errors means that 30% of output fields are null. A low percentage can indicate a poor-quality extraction. Or, it can indicate that your documents contain sparse data. For example, if you define many target fields to extract from a supplemental insurance form, but applicants leave most of the questions blank, then the form's expected average extraction coverage is much less than 100%.
 
-Since coverage success criteria can vary by document type, you can set your own ranges for each document type in the Sensible app. To set ranges for coverage for past extractions, click **Dashboard** and scroll to the **Extraction coverage** section. In the section, configure date range, document type, and extraction coverage range filters:
+Since coverage success criteria can vary by document type, you can set your own ranges for each document type in the Sensible app. To set ranges for coverage for past extractions, click **Dashboard** and scroll to the **Extraction coverage** section. In the section, you can filter by:
+
+- extraction coverage range
+- extraction ID
+- date range
+- document type
+- extraction batch
 
 ![Click to enlarge](https://raw.githubusercontent.com/sensible-hq/sensible-docs/main/readme-sync/assets/v0/images/final/dashboard_coverage.png)
 
 In the preceding screenshot, 0 out of 16 extractions that used the `wells_fargo_savings` configuration in the `bank_statements` document type in the past 7 days scored in the coverage range of 60% -100%.
 
-To determine your own coverage criteria, examine your past extractions. For example, if you find that home inspectors typically report about 60 out of your 100 target data points, you can set a range of 60%-100% for your `home_inspection_report` document type to assess extraction success. In contrast, if you find that drivers licenses typically contain all your target data points, you can set a range of 95%-100% or even 100%-100% to assess extraction success for the `drivers_license` document type.
+To determine your own coverage criteria, examine your past extractions. For example, if home inspectors typically report about 60 out of your 100 target data points, you can set a range of 60%-100% for your `home_inspection_report` document type to assess extraction success. In contrast, if you find that drivers licenses typically contain all your target data points, you can set a range of 95%-100% or even 100%-100% to assess extraction success for the `drivers_license` document type.
 
 To view an individual extraction's coverage score, click **Dashboard** and scroll to the **Recent** section:
 

readme-sync/v0/welcome/2000 - getting-started-ai.md

@@ -52,7 +52,7 @@ Take the following steps to create a prompt to extract more data from the docume
 
 ![Click to enlarge](https://raw.githubusercontent.com/sensible-hq/sensible-docs/main/readme-sync/assets/v0/images/final/quickstart_instruct_2.png)
 
-2. Edit the query as shown in the following screenshot by entering `checking account number (not savings)` in the query field. Give the query an ID, `account_num_checking`, then click the **Send** icon:
+2. Edit the query as shown in the following screenshot by entering `checking account number (not savings)` in the query field. Click the **Send** icon. Sensible generates an ID for your query, in this case, `account_num_checking`.
 
 ![Click to enlarge](https://raw.githubusercontent.com/sensible-hq/sensible-docs/main/readme-sync/assets/v0/images/final/quickstart_instruct_3.png)