LaunchDarkly llms.txt

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Showing the first 18000 characters. Load the complete file to read the remainder.

# LaunchDarkly Documentation

> Learn how to ship features, AI updates, and releases with confidence using LaunchDarkly.

This is the LaunchDarkly documentation index for AI agents and LLMs, organized by product area. Each link below resolves to the markdown version of the page.

For the full documentation snapshot in one file, see [https://launchdarkly.com/docs/llms-full.txt](https://launchdarkly.com/docs/llms-full.txt).

## Get started

- [Welcome to LaunchDarkly Docs](https://launchdarkly.com/docs/home.md)
- [Launch Insights](https://launchdarkly.com/docs/home/getting-started/launch-insights.md): This topic describes the Launch Insights dashboard. Launch Insights is an executive-level dashboard that summarizes how your organization is adopting the best practices associated with risk-free releases.
- [LaunchDarkly architecture](https://launchdarkly.com/docs/home/getting-started/architecture.md): This topic gives a high-level explanation of LaunchDarkly's platform architecture.
- [LaunchDarkly vocabulary](https://launchdarkly.com/docs/home/getting-started/vocabulary.md): This topic defines common words used in the LaunchDarkly application and documentation.

### Onboarding

- [Onboarding](https://launchdarkly.com/docs/home/onboarding.md): Quickstart guides to get up and running with LaunchDarkly SDKs in minutes.
- [Set up .NET (server-side) SDK](https://launchdarkly.com/docs/home/onboarding/dotnet-server.md): Install and initialize the LaunchDarkly .NET (server-side) SDK to start evaluating feature flags in your application.
- [Set up Android SDK](https://launchdarkly.com/docs/home/onboarding/android.md): Install and initialize the LaunchDarkly Android SDK to start evaluating feature flags in your application.
- [Set up Go SDK](https://launchdarkly.com/docs/home/onboarding/go.md): Install and initialize the LaunchDarkly Go SDK to start evaluating feature flags in your application.
- [Set up iOS SDK](https://launchdarkly.com/docs/home/onboarding/ios.md): Install and initialize the LaunchDarkly iOS SDK to start evaluating feature flags in your application.
- [Set up Java (server-side) SDK](https://launchdarkly.com/docs/home/onboarding/java.md): Install and initialize the LaunchDarkly Java SDK to start evaluating feature flags in your application.
- [Set up JavaScript SDK](https://launchdarkly.com/docs/home/onboarding/javascript.md): Install and initialize the LaunchDarkly JavaScript SDK to start evaluating feature flags in your application.
- [Set up Node.js (client-side) SDK](https://launchdarkly.com/docs/home/onboarding/node-client.md): Install and initialize the LaunchDarkly Node.js (client-side) SDK to start evaluating feature flags in your application.
- [Set up Node.js (server-side) SDK](https://launchdarkly.com/docs/home/onboarding/node-server.md): Install and initialize the LaunchDarkly Node.js (server-side) SDK to start evaluating feature flags in your application.
- [Set up Python SDK](https://launchdarkly.com/docs/home/onboarding/python.md): Install and initialize the LaunchDarkly Python SDK to start evaluating feature flags in your application.
- [Set up React Native SDK](https://launchdarkly.com/docs/home/onboarding/react-native.md): Install and initialize the LaunchDarkly React Native SDK to start evaluating feature flags in your application.
- [Set up React Web SDK](https://launchdarkly.com/docs/home/onboarding/react-web.md): Install and initialize the LaunchDarkly React Web SDK to start evaluating feature flags in your application.
- [Set up Vue SDK](https://launchdarkly.com/docs/home/onboarding/vue.md): Install and initialize the LaunchDarkly Vue SDK to start evaluating feature flags in your application.

### Get started

- [Get started with LaunchDarkly](https://launchdarkly.com/docs/home/getting-started.md): This topic walks you through creating a LaunchDarkly account, installing an SDK, and creating and targeting your first feature flag.
- [Exploring sample data](https://launchdarkly.com/docs/home/getting-started/sample-data.md): This topic explains the sample flags, metrics, segments, and context kinds that LaunchDarkly creates for new trial accounts. It also explains how to use them to learn what LaunchDarkly can do.
- [Developer tools](https://launchdarkly.com/docs/home/getting-started/dev-tools.md): LaunchDarkly offers several developer tools to help you work faster and more efficiently.
- [Vega](https://launchdarkly.com/docs/home/getting-started/vega.md): This topic explains Vega, the LaunchDarkly AI-powered agent for investigating and fixing issues and managing feature flags.
- [Connecting Vega to GitHub](https://launchdarkly.com/docs/home/getting-started/vega-github.md): This topic explains how to connect Vega to your GitHub account so that Vega can read code, make code changes, and open pull requests.
- [Using Vega in Slack](https://launchdarkly.com/docs/home/getting-started/vega-slack.md): This topic explains how to use Vega directly in Slack to investigate issues, clean up flags, and interact with LaunchDarkly's AI agent from your team's workspace.
- [LaunchDarkly CLI](https://launchdarkly.com/docs/home/getting-started/ldcli.md): This topic describes how to get started with the LaunchDarkly CLI.
- [LaunchDarkly CLI commands](https://launchdarkly.com/docs/home/getting-started/ldcli-commands.md): This topic describes common commands and configuration options in the LaunchDarkly CLI.
- [LaunchDarkly MCP server](https://launchdarkly.com/docs/home/getting-started/mcp.md): This topic explains how to get started with the LaunchDarkly Model Context Protocol (MCP) server.
- [LaunchDarkly hosted MCP server](https://launchdarkly.com/docs/home/getting-started/mcp-hosted.md): This topic explains how to connect your AI client to the LaunchDarkly hosted Model Context Protocol (MCP) server.
- [LaunchDarkly local MCP server](https://launchdarkly.com/docs/home/getting-started/mcp-local.md): This topic describes how to get started with the LaunchDarkly local Model Context Protocol (MCP) server.
- [LaunchDarkly developer toolbar](https://launchdarkly.com/docs/home/getting-started/dev-toolbar.md): This category has documentation topics about the LaunchDarkly developer toolbar.
- [Setting up the LaunchDarkly developer toolbar](https://launchdarkly.com/docs/home/getting-started/dev-toolbar-setup.md): This topic describes how to install the LaunchDarkly developer toolbar.
- [Using the LaunchDarkly developer toolbar](https://launchdarkly.com/docs/home/getting-started/dev-toolbar-using.md): This topic describes how to use the LaunchDarkly developer toolbar.
- [LaunchDarkly agent skills](https://launchdarkly.com/docs/home/getting-started/skills.md): This topic describes the AI agent skills that LaunchDarkly offers for various AI applications.
- [IDE connectors and agents](https://launchdarkly.com/docs/home/getting-started/ide.md): This category lists integrated development environment (IDE) connector integrations and agents for third-party apps.
- [IntelliJ IDEA](https://launchdarkly.com/docs/home/getting-started/intellij.md): This topic explains how to use the LaunchDarkly IntelliJ IDEA plugin to interact with feature flags from within IntelliJ IDEs.
- [LaunchDarkly extension for GitHub Copilot](https://launchdarkly.com/docs/home/getting-started/github-copilot-extension.md): This topic links to documentation on using the LaunchDarkly extension for GitHub Copilot on Visual Studio Marketplace.
- [Visual Studio Code (VSCode)](https://launchdarkly.com/docs/home/getting-started/vscode.md): This topic explains how to use the LaunchDarkly VSCode extension to interact with feature flags from within VSCode.
- [Flag cleanup custom agent for GitHub Copilot](https://launchdarkly.com/docs/home/getting-started/github-copilot-agent.md): This topic describes how to install and use the LaunchDarkly flag cleanup custom agent for GitHub Copilot.
- [Setting up an SDK](https://launchdarkly.com/docs/home/getting-started/setting-up.md): This topic explains how to set up an SDK to begin using LaunchDarkly.
- [Joining an account](https://launchdarkly.com/docs/home/getting-started/join-account.md): This topic explains how to join LaunchDarkly as a new account member.
- [Logging in with SSO](https://launchdarkly.com/docs/home/getting-started/login-sso.md): This topic explains how to log into LaunchDarkly for the first time using an SSO provider.
- [Using feature management](https://launchdarkly.com/docs/home/getting-started/feature-management.md): This topic discusses using feature management at a high level, describes some key parts of the LaunchDarkly user interface (UI), and suggests different ways to learn more about working in LaunchDarkly.
- [Getting started in different roles](https://launchdarkly.com/docs/home/getting-started/roles.md): This topic includes suggested paths through the LaunchDarkly documentation specific to your role.

## AgentControl

### AgentControl

- [AgentControl](https://launchdarkly.com/docs/home/agentcontrol.md): The topics in this category explain how to use LaunchDarkly AgentControl to manage your AgentControl configs. You can use AgentControl to customize, test, and roll out new large language models (LLMs) within your generative AI applications.
- [Quickstart for AgentControl](https://launchdarkly.com/docs/home/agentcontrol/quickstart.md): This topic explains how to get started with LaunchDarkly AgentControl to manage, deploy, and update agent configurations without redeploying your application.

### Set up AgentControl configs

- [Create configs](https://launchdarkly.com/docs/home/agentcontrol/create.md): This topic explains how to create and update AgentControl.
- [Create and manage config variations](https://launchdarkly.com/docs/home/agentcontrol/create-variation.md): This topic explains how to create and manage config variations.
- [Create and manage AI model configurations](https://launchdarkly.com/docs/home/agentcontrol/create-model-config.md): This topic explains how to create and manage custom models to use in AgentControl.
- [Agent skills](https://launchdarkly.com/docs/home/agentcontrol/agent-skills.md): This topic explains how to use agent skills to create, manage, and attach reusable agent instructions across AgentControl config variations.
- [Tools](https://launchdarkly.com/docs/home/agentcontrol/tools.md): This topic explains how to manage and use tools in AgentControl.
- [Prompt snippets](https://launchdarkly.com/docs/home/agentcontrol/snippets.md): This topic explains how to use prompt snippets to create, manage, and reuse prompts across AgentControl config variations.

### Config evaluations

- [Playgrounds](https://launchdarkly.com/docs/home/agentcontrol/playground.md): This topic explains how to use LLM playgrounds to create and run evaluations that measure the quality of model outputs before deployment.
- [Offline evaluations](https://launchdarkly.com/docs/home/agentcontrol/offline-evaluations.md): This topic explains how to use offline evaluations to validate config variations before releasing them to production.
- [Datasets](https://launchdarkly.com/docs/home/agentcontrol/datasets.md): This topic explains how to create, manage, and use datasets for offline evaluations.
- [Online evaluations](https://launchdarkly.com/docs/home/agentcontrol/online-evaluations.md): This topic describes how to run online evaluations on config variations by attaching judges that score responses for accuracy, relevance, and toxicity.
- [Judges](https://launchdarkly.com/docs/home/agentcontrol/judges.md): This topic explains how to create and manage custom judges for online evaluations in AgentControl.
- [Run experiments with AgentControl](https://launchdarkly.com/docs/home/agentcontrol/experimentation.md): This topic introduces the role of AgentControl configs in LaunchDarkly Experimentation.

### Agents

- [Agents](https://launchdarkly.com/docs/home/agentcontrol/agents.md): This topic explains how to create and use agent-based configs to support structured, multi-step AI workflows with shared configuration, judge models that evaluate response quality, and performance monitoring.
- [Agent graphs](https://launchdarkly.com/docs/home/agentcontrol/agent-graphs.md): This topic explains how to create and use agent graphs to orchestrate multi-agent workflows with AgentControl.

### Deliver and monitor configs

- [Config targeting](https://launchdarkly.com/docs/home/agentcontrol/target.md): This topic explains how to use AgentControl config targeting to control which of your customers receive a particular variation of a config, based on their context.
- [Monitor config performance](https://launchdarkly.com/docs/home/agentcontrol/monitor.md): This topic explains how to monitor the performance of your configs.
- [Understand AI impact with AI Insights](https://launchdarkly.com/docs/home/agentcontrol/insights.md): This topic explains how to use AI insights to understand the impact of AgentControl configs by analyzing metrics across your project.
- [The trends explorer](https://launchdarkly.com/docs/home/agentcontrol/trends.md): This topic explains how to use the AgentControl trends explorer to view aggregated performance data across multiple configs, providers, and models.
- [Manually instrument LLM spans](https://launchdarkly.com/docs/home/agentcontrol/manual-llm-span-tracing.md): This topic explains how to manually instrument LLM spans so LaunchDarkly can observe model activity when automatic instrumentation is not available.

### Agent optimization

- [Agent optimization](https://launchdarkly.com/docs/home/agentcontrol/optimization.md): This topic explains what agent optimization is, its different modes, and how to start using it.
- [Optimization SDK quickstart](https://launchdarkly.com/docs/home/agentcontrol/optimization-quickstart.md): This topic explains how to configure the SDK to use agent optimization.
- [Performing optimization runs](https://launchdarkly.com/docs/home/agentcontrol/optimization-runs.md): This topic explains how to run an optimization by pulling its configuration from LaunchDarkly.
- [Optimization runs without a config](https://launchdarkly.com/docs/home/agentcontrol/optimize-without-config.md): This topic explains how to define judges, model choices, and evaluation parameters directly in code without a LaunchDarkly configuration object.
- [Expected output mode](https://launchdarkly.com/docs/home/agentcontrol/ground-truth-optimization.md): This topic explains how to use Expected output mode to optimize an agent against known input/output pairs.
- [Using tools in agent optimization](https://launchdarkly.com/docs/home/agentcontrol/optimization-tools.md): This topic explains how to pass tool definitions through to your agent and judge calls during optimization runs.
- [Other framework examples for agent optimization](https://launchdarkly.com/docs/home/agentcontrol/optimization-framework-examples.md): Code examples for the Optimization SDK using OpenAI Agents SDK, LangChain, Strands, and the Claude Agent SDK.
- [OptimizationContext reference](https://launchdarkly.com/docs/home/agentcontrol/optimization-context.md): This topic has a full field reference for the OptimizationContext object returned by all optimization methods.

### Manage AgentControl

- [Manage AgentControl](https://launchdarkly.com/docs/home/agentcontrol/manage.md): This topic explains how to view and manage AgentControl.
- [Adaptive triggers](https://launchdarkly.com/docs/home/agentcontrol/triggers.md): This topic explains how to use adaptive triggers in configs to mitigate the effect of unexpected outages or performance degradation in your LLM provider.
- [AgentControl and information privacy](https://launchdarkly.com/docs/home/agentcontrol/privacy.md): This topic describes how the LaunchDarkly AgentControl product treats personally identifiable information (PII).
- [Compare config variation versions](https://launchdarkly.com/docs/home/agentcontrol/compare-variation-versions.md): This topic explains how to compare versions of a config variation.
- [Configure Amazon Bedrock](https://launchdarkly.com/docs/home/agentcontrol/configure-amazon-bedrock.md): This topic explains how to configure Amazon Bedrock as a model provider.
- [Configure token limits](https://launchdarkly.com/docs/home/agentcontrol/configure-token-limits.md): This topic explains how to configure token limits for offline evaluations in AgentControl.

## Feature flags

### Create flags

- [Create flags](https://launchdarkly.com/docs/home/flags/create.md): This category explains how to use LaunchDarkly to create your feature flags.
- [Creating new flags](https://launchdarkly.com/docs/home/flags/new.md): This topic explains how to create new feature flags in LaunchDarkly.
- [Flag types](https://launchdarkly.com/docs/home/flags/types.md): This topic explains the four types of feature flags and when to use them.
- [Turning flags on and off](https://launchdarkly.com/docs/home/flags/toggle.md): This topic explains how to enable and disable flags from the Flags list.
- [Creating flag variations](https://launchdarkly.com/docs/home/flags/variations.md): This topic explains how to create and edit your feature flag's variations and outlines the different types of flag variations.
- [Cloning existing flags](https://launchdarkly.com/docs/home/flags/clone.md): This topic explains how to create new flags by cloning existing flags in LaunchDarkly.
- [Importing flags](https://launchdarkly.com/docs/home/flags/import.md): This topic explains how to import flags from other feature management tools into LaunchDarkly.
- [Flag settings](https://launchdarkly.com/docs/home/flags/flag-settings.md): This topic explains how to edit a feature flag's environment-specific and project-wide settings.

### Target with flags

- [Target with flags](https://launchdarkly.com/docs/home/flags/target.md): This topic explains how to use flag targeting to control which of your customers receive a variation of a feature flag, based on their contex