For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.

Pricing Sign in Try it free

Docs Guides SDKs Integrations API docs Tutorials Flagship blog

Guides

Guides
Cheatsheets
Control and govern AI agents in production
Enable self-healing systems with runtime controls
Optimize AI performance and cost with AgentControl configs
Run continuous experiments in production
Ship AI-built code with AgentControl or CodeControl
Feature flags
Best practices for upgrading users to contexts
Creating flags
Deciding between flag targeting strategies
Defining and targeting mobile applications
Feature flag hierarchy
Flag conventions
Improving flag usage in code
LaunchDarkly CLI dev-server reference guide
Performing multi-stage migrations with migration flags
Reducing technical debt from feature flags
Testing code that uses feature flags
Using entitlements to manage customer experience
Using flags on static sites with JavaScript
Using the LaunchDarkly CLI for local testing
Using segments and targeting to manage early access programs
AgentControl
Getting started with OpenAI and AgentControl
Getting started with Anthropic Claude and AgentControl
Getting started with Google Gemini and AgentControl
Getting started with Amazon Bedrock and AgentControl
Getting started with LangChain and AgentControl
Getting started with LangGraph and AgentControl
Getting started with Strands and AgentControl
Managing AI model configuration outside of code
Using targeting to manage AI model usage by tier
When to use prompt-based vs agent mode
Building a chatbot with multiple AI providers using AgentControl
Observability
Getting started with observability for native Android
Experimentation
Building your first experiment
Creating an A/B experiment using a funnel metric group
Creating mutually exclusive experiments
Designing experiments
Example experiments
Experimentation best practices
Bayesian versus frequentist statistics
Maintaining consistency across user sessions when running experiments
Measuring Experimentation impact with holdout experiments
Migrating from Statsig to LaunchDarkly Experimentation
Proving ROI with data-driven AI agent experiments
Sample size calculations for frequentist experiments
Statistical methodology
Choosing a statistical methodology
Covariate adjustment and CUPED methodology
Statistical methodology for Bayesian experiments
Statistical methodology for frequentist experiments
Multiple comparisons correction
Stratified sampling
Sample ratio mismatch
Metrics
Building a metric import and sync integration
Example metrics
Understanding LaunchDarkly metrics
Using metrics from engineering insights
Infrastructure
Deployment and release strategies
Managing flags with Terraform
Using flags with Cloudflare Workers
Using LaunchDarkly in serverless environments
Account management
LaunchDarkly for large enterprise teams
Merging LaunchDarkly accounts
Migrating your existing feature flag solution to LaunchDarkly
Minimizing LaunchDarkly's access to end user data
Onboarding to views
Using LaunchDarkly with Protected Health Information (PHI)
Using SSO with LaunchDarkly
Teams and custom roles
Building teams in LaunchDarkly
Creating roles
Onboarding to preset roles
SDKs
Use cases for SDK wrappers
Using LaunchDarkly without a supported SDK
Using mobile SDKs
Using the Lua SDK with HAProxy
Using the Lua SDK with NGINX
Using the JavaScript SDK in Salesforce Lightning Web Components
Resilient architecture patterns for LaunchDarkly's SDKs
Integrations
About LaunchDarkly integrations
Integrations use cases
Using flag triggers with Dynatrace
Building a change history event hook integration
Building an ephemeral Environments as a Service integration
Building a synced segments integration
LaunchDarkly Shopify Pixel
REST API
Comparing LaunchDarkly's SDK and REST API
Using the LaunchDarkly REST API
REST API migration guide
Additional resources

Pricing Sign in Try it free

Guides Experimentation

Measuring Experimentation impact with holdout experiments

Something went wrong!

Was this page helpful?