Sign inSign up
Product docsGuidesSDKsIntegrationsAPI docsTutorialsFlagship Blog
Product docsGuidesSDKsIntegrationsAPI docsTutorialsFlagship Blog
  • Getting started
    • Overview
    • Launch Insights
    • LaunchDarkly architecture
    • LaunchDarkly vocabulary
  • Feature flags and AI Configs
    • Create flags
    • Target with flags
    • Flag templates
    • Manage flags
    • Code references
    • AI Configs
    • Contexts
    • Segments
  • Releases
    • Releasing features with LaunchDarkly
    • Release policies
    • Percentage rollouts
    • Progressive rollouts
    • Guarded rollouts
    • Feature monitoring
    • Release pipelines
    • Engineering insights
    • Release management tools
    • Applications and app versions
    • Change history
  • Observability
    • Observability
    • Session replay
    • Error monitoring
    • Logs
    • Traces
    • LLM observability
    • Alerts
    • Dashboards
    • Search specification
    • Monitoring settings
  • Product analytics
    • Product analytics
    • Setting up product analytics
    • Using product analytics charts
  • Experimentation
    • Experimentation
    • Creating experiments
    • Managing experiments
    • Analyzing experiments
    • Experimentation and metric events
    • Multi-armed bandits
    • Holdouts
  • Metrics
    • Metrics
    • Metric groups
    • Autogenerated metrics
    • Metric impact
    • Metric events
  • Warehouse native
    • Warehouse native Experimentation
    • Warehouse native metrics
    • Creating warehouse native experiments
  • Infrastructure
    • Connect apps and services to LaunchDarkly
    • LaunchDarkly in China and Pakistan
    • LaunchDarkly in the European Union (EU)
    • LaunchDarkly in federal environments
    • Public IP list
  • Your account
    • Projects
    • Views
    • Environments
    • Tags
    • Teams
    • Members
    • Roles
    • Account security
    • Billing and usage
    • Changelog
Sign inSign up
LogoLogo
On this page
  • Overview
  • Privacy and PII in LaunchDarkly
  • LaunchDarkly and AI models
Feature flags and AI ConfigsAI Configs

Overview

This topic describes how the LaunchDarkly AI Configs product treats personally identifiable information (PII).

Privacy and PII in LaunchDarkly

End-user data is information about your customers that your application sends to LaunchDarkly as part of a context. End user data can include PII, including names, email addresses, or other unique identifiers, depending on how you define your context attributes.

The AI Configs product works similarly to LaunchDarkly feature flags with respect to PII in end-user data. Specifically:

  • We recommend that you use private attributes when you target on PII or other sensitive data. To learn more, read Minimizing LaunchDarkly’s access to end user data.
  • If your organization prohibits sending PII to AI providers, then you must take care not to include PII in any of the context attributes that you reference in the messages in your AI Config variations. LaunchDarkly does not have guardrails that prevent you from sending PII from your application to LaunchDarkly, or from LaunchDarkly to a third party, such as an AI model.

LaunchDarkly and AI models

LaunchDarkly is not integrating directly into the response from any AI provider.

When you work with AI Configs, LaunchDarkly does not send any information you provide to any AI provider or model, and does not use any information you provide as part of an AI Config to fine-tune any models. This includes information you provide when you create an AI Config and its variations, as well as the information you provide in context attributes.

If you use variables within your AI Config variation messages, either from a context attribute or directly from your application, LaunchDarkly substitutes the values of those variables into the message. If your organization prohibits sending PII to AI providers, then you must take care not to include PII in any of the variables that you reference in the messages in your AI Config variations.

Was this page helpful?
Previous

Agents in AI Configs

Next
Built with
AI Configs and information privacy