LaunchDarkly Labs
Official@launchdarkly-labs
Experimental (unsupported) software by LaunchDarkly. See https://github.com/launchdarkly for our official GitHub organization.
Agent Skills by LaunchDarkly Labs
Showing 14 vetted skills indexed across 1 GitHub repositories.
launchdarkly-labsaiconfig-variations
Manage AI Config variations across models, prompts, and parameters via API.
launchdarkly-labsaiconfig-sdk
Consume LaunchDarkly AI Configs in Python applications via the Python AI SDK.
launchdarkly-labsaiconfig-api
Manage LaunchDarkly AI Configs via REST API with authentication headers.
launchdarkly-labsaiconfig-tools
Automate creation, management, and attachment of tools for LaunchDarkly AI Configs.
launchdarkly-labsaiconfig-create
Create LaunchDarkly AI Configs with variations, model configurations, and targeting via REST API.
launchdarkly-labsaiconfig-targeting
Configure LaunchDarkly AI Config targeting rules via API.
launchdarkly-labsaiconfig-online-evals
Automate scoring of AI Config responses with LLM-as-a-judge.
launchdarkly-labsaiconfig-custom-metrics
Automates lifecycle management of custom metrics in LaunchDarkly via API and SDK.
launchdarkly-labsaiconfig-segments
Create, update, and query LaunchDarkly segments for AI Config targeting.
launchdarkly-labsaiconfig-update
Manage LaunchDarkly AI Configs via PATCH, archive, and delete operations.
launchdarkly-labsaiconfig-ai-metrics
Instrument AI metrics tracking in Python projects using LaunchDarkly's SDK.
launchdarkly-labsaiconfig-context-advanced
Compose cardinality-safe user, organization, and agent-graph contexts for LaunchDarkly AI Configs.
launchdarkly-labsaiconfig-projects
Create and manage LaunchDarkly projects for AI Configs via the API.
launchdarkly-labsaiconfig-context-basic
Build and manage LaunchDarkly AI Config user contexts with the Python SDK.
Frequently Asked Questions About LaunchDarkly Labs
FAQPage SchemaWhat specific tasks can engineers perform using these experimental configurations?▼
Engineers can manage model parameters, define prompt variations, and implement targeting rules for production deployments. These capabilities allow for granular control over model behavior, enabling A/B testing of prompts and dynamic adjustment of response logic based on user or organization context without redeploying code.
Which technical personas are the primary users of these experimental repositories?▼
These repositories are designed for machine learning engineers, backend developers, and site reliability engineers. The functionality targets technical teams responsible for integrating model-driven features into production systems, requiring precise control over configuration lifecycle, performance metrics, and contextual user segmentation.
What are the prerequisites for implementing these configurations in a production environment?▼
Implementation requires an active LaunchDarkly account and familiarity with REST-based configuration management. Developers must integrate the provided libraries into their application runtime to handle context composition, metric instrumentation, and the retrieval of configuration variations during the request lifecycle.