Data handling and classification
Promptless practices data minimization, storing only the data it needs to automate your documentation. This page classifies the data Promptless stores, the data it processes without storing, and the data it never processes. It also covers how Promptless authenticates users and encrypts data, so you can answer a security reviewer’s data-handling questions.
Use cases
Section titled “Use cases”- Answer a security questionnaire’s questions about data retention, encryption, and end-user data.
- Check what happens to a pull request, Slack thread, or Jira issue after Promptless reads it, before you connect that source.
- Confirm which sign-in and multi-factor authentication options your plan includes.
Data classification
Section titled “Data classification”Promptless handles each category of data differently:
| Data category | How Promptless handles it | Description |
|---|---|---|
| Documentation | Processed, not stored | Promptless reads your documentation from its repository when it works on an update, and stores records of the updates it suggests. See How Promptless reads your documentation. |
| Third-party integration data | Processed, not stored | Content from the tools that trigger Promptless or give it context. Promptless keeps it only as long as it needs to produce a documentation update. |
| End-user data | Not processed | Promptless doesn’t process or store sensitive end-user data. |
Data that Promptless stores
Section titled “Data that Promptless stores”Promptless stores the minimum it needs and otherwise operates statelessly:
| Data | What Promptless keeps |
|---|---|
| Suggestion records | The title, description, and branch name of each documentation update, the paths of the files it changes, and the citations attached to it. The changed content lives on the suggestion’s branch in your documentation repository. |
| Knowledge Base | The files in your Agent Knowledge Base, including the analysis Promptless writes of your documentation’s structure, style, and product coverage. |
| Feedback for Promptless | Feedback on the quality of documentation updates: your edits to Promptless suggestions, and comments you leave in the Promptless dashboard. |
| Integration auth data | The data needed to connect to a third-party tool, typically an authentication token. Promptless doesn’t store the content behind the token. |
How Promptless reads your documentation
Section titled “How Promptless reads your documentation”For each session, Promptless clones your documentation repository into a temporary workspace and deletes the workspace when the session ends. If you use the GitHub (read-only) app, Promptless publishes from its own fork of your public documentation repository.
Data that Promptless processes, but does not store
Section titled “Data that Promptless processes, but does not store”Integrations with third-party tools trigger documentation updates or give Promptless context for them. Promptless uses that data to provide its service and doesn’t store it. Promptless does not retain a copy of customer source code, support conversations, or any other data from third-party integrations. For example:
- When a GitHub pull request triggers a documentation check, Promptless analyzes the changes in real time without storing the pull request’s content.
- When you use the Slack integration, Promptless processes conversations to find documentation needs and keeps no copies of them.
- When Promptless reads context from tools like Linear or Jira, it uses that information only at generation time. It keeps no copy of the issues or projects.
Promptless also redacts credentials and known secret values from the records it logs, stores, and transmits. See How Promptless protects secrets and sensitive data.
Promptless does not use customer data to pre-train or fine-tune language models.
Data that Promptless does not process
Section titled “Data that Promptless does not process”Promptless doesn’t process or store sensitive end-user data for your organization, and you can’t configure it to.
User authentication and access controls
Section titled “User authentication and access controls”Standard authentication features
Section titled “Standard authentication features”Every Promptless user gets these authentication features:
- Single sign-on with Google or GitHub
- Password policies that enforce complexity requirements
- Two-factor authentication (2FA) with time-based one-time password (TOTP) codes
- Password reset with verification
Enterprise authentication features
Section titled “Enterprise authentication features”Enterprise plan customers also get:
- Single sign-on (SSO) through major identity providers
- SAML 2.0, with just-in-time user provisioning, role mapping, and certificate-based authentication
- OpenID Connect (OIDC)
- Custom multi-factor authentication (MFA) policies and enforcement
To set up enterprise SSO, see Single sign-on (SSO) setup.
Data security
Section titled “Data security”Encryption standards
Section titled “Encryption standards”Promptless encrypts data in transit and at rest:
| Data | Encryption |
|---|---|
| Data in transit, between all system components | TLS 1.2 or higher |
| Data at rest, in primary data stores and secondary backups | AES-256, with keys managed through a key management system |
| Backup data | Encrypted with independent encryption keys |
Enterprise security support
Section titled “Enterprise security support”Enterprise customers can request additional security features and support, such as custom data retention policies. For questions about how Promptless handles data, email security@gopromptless.ai.