Data retention

Overview

Ada’s data retention approach follows industry practices designed to meet operational, privacy, and compliance needs. Ada retains the resources you make available to the AI Agent and end user data only as long as necessary to provide services. End user data is automatically deleted after two years, while other categories of data may be retained longer, in accordance with the retention schedules.

Why data is stored

Data storage supports operational and compliance needs. Retaining data allows you to:

• Review and analyze conversations with your end users
• Keep platform content (such as knowledge base articles) available without needing to re-upload
• Maintain authorized user accounts and access securely

Once data is no longer required for these purposes, it is automatically deleted or has its personal details removed.

Use cases

Data retention settings help you meet privacy and compliance requirements.

• Respond to data erasure requests: Delete specific end user data on demand when users request removal under GDPR, CCPA, or similar regulations.
• Align with organizational policies: Configure retention to match your internal data governance requirements.
• Preserve records for auditing: Export conversation data before automatic deletion if you need to retain records longer for compliance or legal purposes.

Capabilities & configuration

Control how long data is retained and when it is deleted.

Delete data on demand

In addition to automatic retention rules, you can delete user data at your own pace using the Data Compliance API.

Deleting data on demand provides flexibility to:

• Remove specific end user data whenever needed
• Meet organizational retention requirements
• Reduce the amount of sensitive information stored in the system

Quick start

Manage data retention in a few steps.

For recommendations on managing data retention, see Best practices.

Best practices

Follow these recommendations to manage data retention effectively.

• Delete data on demand: Use the Data Compliance API to delete data when users request erasure (such as under GDPR/CCPA) or when your own policies require stricter retention.

• Export before deletion: If you need to keep records for longer than the retention schedules allow (for example, for compliance or auditing), export transcripts or other data before they expire using the Data Export API.

• Use redactions where appropriate: Configure redaction settings to remove sensitive details (like Social Security numbers or other PII) from transcripts before they are stored. This reduces the volume of personal information retained.

• Review access to exported data regularly: Make sure only authorized users with a business need can access exported data, especially sensitive information like transcripts and metadata.

• Stay aligned with your internal policies: Your organization may have its own rules for how long data must be kept, based on laws, industry standards, or internal governance. Compare the retention schedules with your requirements to ensure data is not stored longer than allowed or deleted sooner than needed.

FAQs

Q: Can Ada keep customer transcripts for more than two years? A: Not if they contain personal data. Transcripts are automatically deleted after two years unless personal details are removed. You can always export transcripts before deletion for record-keeping purposes.

Q: Do LLM providers keep any customer data? A: No. Ada applies strict contractual and technical safeguards to ensure that data shared with LLM providers is not persistently stored. Data is processed only in memory and retained only for the duration of the request, following Zero Data Retention (ZDR) principles.

Related features

For complete information on retention schedules, see the Trust Center: Customer Data Retention Policy.