Tutorials

Technical tutorials

Explore end-to-end examples of how to build on the LaunchDarkly platform

Dive into hands-on tutorials that demonstrate how to implement LaunchDarkly in real projects. Each tutorial is built to help you experiment quickly, adopt proven patterns, and ship with confidence.

Beyond n8n for Workflow Automation: Agent Graphs as Your Universal Agent Harness

Build multi-agent systems that work across LangGraph, OpenAI Agents SDK, and other frameworks.

Catch your first silent AI failure with Vega AI in under 10 minutes

Learn how to instrument an AI agent to expose silent failures and use Vega AI to investigate the root cause.

Evaluate LLM code generation with LLM-as-judge evaluators

Build custom LLM-as-judge evaluators for AI code generation. Score security, API contracts, and scope creep.

OpenTelemetry for LLM Applications: A Practical Guide with LaunchDarkly and Langfuse

Instrument a real LLM application with OpenTelemetry spans and fan out traces to Langfuse and LaunchDarkly.

Use LaunchDarkly Agent Skills in Claude Code and Cursor

Install LaunchDarkly Agent Skills in your AI coding assistant and create AI Configs from natural language.

Detection to Resolution: Real World Debugging with Rage Clicks and Session Replay

Learn how to use session replay and rage click detection to diagnose and fix production issues fast.

Compare AI orchestrators: LangGraph vs Strands vs OpenAI Swarm

Build a 3-agent research analysis swarm that runs across three orchestrators.

Building a data extraction pipeline with LaunchDarkly

Turn unstructured text into structured JSON with runtime-configurable schemas.

Observable Multi-Modal Agentic Systems with Session Replay + Online Evals

Learn how combining session replay with online evaluations provides complete observability for multi-modal AI systems.

Day 7 | SLOs that actually drive decisions

Learn how to build SLOs that start with business impact and end with actionable targets.

Day 11 | What engineering teams really want from Observability in 2026

Santa’s advice to engineering teams in need of unified observability solutions.

Day 3 | Jingle All the Way to Zero-Config Observability

Get feature flag context automatically injected into your OTel traces without writing instrumentation code.

Day 6 | The cardinality problem that stole your cloud budget

Learn 3 ways to stop cardinality from stealing your cloud budget.

Day 1 | Observability under the Tree: What Changed in 2025

A full recap of the key innovations in observability this year.

Day 2 | He knows if you have been bad or good... But what if he gets it wrong?

Why AI agents need three layers of observability when traditional observability can’t help.

Day 4 | Tracing the impact of holiday styling in your Node.js app

Use LaunchDarkly’s flags with the observability SDK to release and observe seasonal-themed CSS.

Collecting user feedback in your app with feature flags

Learn how users feel about your app’s features so you can make data-driven product decisions.

When to Add Online Evals to Your AI Configs

A practical guide for LLM observability and real-time quality monitoring in production.

Detecting User Frustration: Understanding Rage Clicks and Session Replay

Learn how to automatically detect user frustration with LaunchDarkly’s session replay and rage clicks.

Build a User Frustration Detection & Response System

Connect rage click detection to LaunchDarkly Guarded Releases for automating actions.

Add observability to your React Native application in 5 minutes

See how your React Native iOS app is performing with LaunchDarkly’s Observability SDK.

AI Config CI/CD Pipeline: Automated Quality Gates and Safe Deployment

Build a CI/CD pipeline that validates and tests LaunchDarkly AI Configs before deployment.

Resilient architecture patterns for LaunchDarkly's SDKs

Best practices for building resilient applications with LaunchDarkly SDKs.

Proving ROI with Data-Driven AI Agent Experiments

Measure and prove the ROI of AI model changes with LaunchDarkly experiments.

A Deeper Look at LaunchDarkly Architecture: More than Feature Flags

Learn about how LaunchDarkly’s foundations works under the hood.

Smart AI Agent Targeting with MCP Tools

Transform your basic multi-agent system with business tiers and geographic targeting.

Build a LangGraph Multi-Agent System in 20 Minutes

Build a multi-agent system with dynamic configuration using LangGraph and LaunchDarkly AI Configs.

Snowflake Cortex Completion API + LaunchDarkly SDK Integration

Walk through an integration between Snowflake Cortex and LaunchDarkly’s AI SDKs.

Using AI Configs to review database changes

Learn how to use LaunchDarkly AI Configs to review and validate database schema changes.

How to implement WebSockets and kill switches in a Python application

Learn to use a websocket library to update your Python Flask app when a kill switch flag is flipped.

4 hacks to turbocharge your Cursor productivity

Tips and tricks to make Cursor more accurate, personalized, and extensible.

Create a feature flag in your IDE in 5 minutes with LaunchDarkly's MCP server

Create, evaluate, and modify flags from within your IDE using natural language.

Observability for Your Go ORM: OpenTelemetry Integration with GORM

GORM is a popular ORM for Go that allows you to interact with databases using Go structs.

The complete guide to OpenTelemetry in Next.js

OpenTelemetry defines how we send telemetry data to observability backends.

How to instrument your React Native app with OpenTelemetry

Collect traces, metrics, and logs from your React Native applications.

The complete guide to OpenTelemetry in Python

Learn how to send telemetry data from Python applications.

Monitoring Browser Applications with OpenTelemetry

Leverage OpenTelemetry on the client side to collect signals from your applications.

How to Use OpenTelemetry to Monitor Next.js Applications

Observability is key to monitoring and improving your web application’s performance.

What is OpenTelemetry and Why Should I Care?

OpenTelemetry origins, collector setup, and how to start collecting OTEL data in your applications.

Distributed Tracing in Next.js Apps

Learn how to implement distributed tracing in your Next.js applications.

Real-time Monitoring in Django: Essential Tools and Techniques

Real-time monitoring for maintaining performance and reliability of Django applications.

DeepSeek vs Qwen: local model showdown featuring LaunchDarkly AI Configs

Compare the performance of DeepSeek r1 and Alibaba’s Qwen using Ollama and AI Configs.

Application Tracing in .NET for Performance Monitoring

Implement application tracing in .NET for performance monitoring.

The Ultimate Guide to Ruby Logging: Best Libraries and Practices

In any Ruby application, logging is more than just a means to record errors.

Using Materialized Views in ClickHouse (vs. Postgres)

Learn how to use materialized views in ClickHouse for better performance.

Filtering and Sampling LaunchDarkly Ingest

Advanced ingestion filtering techniques for LaunchDarkly.

How to Set Up Your Production AWS MSK Kafka Cluster

Looking to set up your own Kafka cluster on AWS MSK?

Publishing an NPM Package with Private pnpm Monorepo Dependencies

Trying to publish an npm package but have a complicated monorepo setup?

How To Use The Chrome Inspector & Debugger

Chrome Developer Tools is a toolkit for web developers built into Google Chrome.

3 Levels of Data Validation in a Full Stack Application With React

Data validation is critical for any application that relies on input from users.

The power of the monorepo: Keep your fullstack app in sync!

Use JavaScript or TypeScript for both your frontend and your backend.

Compression: The simple, powerful upgrade for your web stack

At LaunchDarkly, we’re focused on keeping our app snappy and fast.