In the Settings view, you'll see a tab for Filters. Toggle these filters on to prevent questions from being stored in the Questions view if they contain:
- A link
- Sensitive information (credit cards, SINs, SSNs, addresses)
Reminder: questions are stored in the Questions view if they are Not Understood or the Answer is downvoted (Not Helpful).
Gibberish, links, profanity and sensitive information will still be visible to the user in the chat. This information will also be visible to you in the bot dashboard.
Special Considerations for the Sensitive Information Filter
When this filter is turned on, sensitive information will still be visible in the chat interface and in the Conversations view of the dashboard. The data will also be stored on Ada's database. If you would like sensitive information scrubbed out, read more about Redaction below.
In contrast to the Sensitive Information Filter, the Redactions feature will scrub information provided by the chatter from the chat interface and dashboard. By extension, the sensitive information will not be stored in the Ada database.
Redaction of credit cards is non-configurable, and is mandatory for all bots. However, to scrub out phone numbers, email addresses, SINs and SSNs, you can turn Redactions on using the Ada platform in the Settings dashboard.
Interaction Between Sensitive Information Filter and Redaction
If you have the Sensitive Information Filter toggled on as well as Redaction enabled, Redaction will override the filter. The original question will appear in the Questions view (if Not Understood/Not Helpful) but the sensitive information will be redacted. By extension, the sensitive information will not be stored in Ada's database.
For any additional questions, contact your Customer Success Manager or email us at: firstname.lastname@example.org