Latest Runtime Control posts

Introducing the LaunchDarkly AI SDK

The LaunchDarkly AI SDK is available for Python and JavaScript and is the path we recommend for every new AgentControl integration.

Kelvin Yap

You can't control what you can't see

What LaunchDarkly showed live on the Control Panel: how to see what's happening in production, act on it in real time, and test on data you already trust.

Kellye King

Best CI/CD Pipelines for Containerized AI Development

Containerized AI applications require sophisticated deployment infrastructure to manage Docker images.

Scarlett Attensil

Stories from the Factory Floor: Our AI software factory saved me from an incident and I lived to tell the tale

Last summer, I shipped what I thought was a routine cleanup to production. It turned out to be a bug. But before the vast majority of users ever saw it, our AI software factory caught it and rolled back my change automatically.

Alex Engelberg

Podcast recap: Observability won’t save your agents

On a recent episode of the MonkCast, Marek Poliks spoke with James Governor about why governing agents from the outside leaves teams perpetually one step behind.

LaunchDarkly

Agent Optimization: Define what better means, and let AgentControl find it

Agent Optimization, now in beta in AgentControl, automatically searches for a better agent configuration against criteria you define.

Kelvin Yap

Why AI deployment breaks standard CI/CD

Learn why AI deployment can break standard CI/CD and how runtime controls, shadow testing, rollouts, and rollback reduce risk.

Scarlett Attensil

Entering the AI software factory era

What automating the SDLC at LaunchDarkly taught me about speed, control, and the job of an engineer.

Jonathan Nolen

Observability is not enough

With runtime control, teams can extend observability by moving beyond reactive monitoring and toward proactive remediation.

Betsy Sallee

Speed isn't the risk. Lack of control is.

Why controlling code and agents in the AI era matters—and why we built AgentControl.

Kellye King

MLOps lifecycle: Stages, workflow, and best practices

Understand the MLOps lifecycle from data preparation to monitoring.

Scarlett Attensil

AI pipeline: Preventing drift in production systems

Learn why uncontrolled AI pipeline changes can cause failures in prod.

Scarlett Attensil

Adaptive Triggers: AI that corrects itself in production

Adaptive Triggers is now available in closed beta.

Kelvin Yap

Agent Optimization: Discover better agent configurations automatically

Agent Optimization is now available in private beta for eligible customers.

Kelvin Yap

The next era of software needs runtime control

Edith Harbaugh

Introducing AgentControl

AgentControl is the operational layer for managing agents in production.

Kelvin Yap

LLM observability: Tutorial and best practices

LLM observability analyzes how models behave across development, testing, and production.

Scarlett Attensil

LLM pricing comparison: Tutorial and best practices

Large language models (LLMs) power a wide range of AI applications today.

Scarlett Attensil

Agent graphs bring control and visibility to multi-agent AI workflows

Agent graphs bring real-time control to multi-agent AI workflows.

Kelvin Yap

How to automate runtime control with kill switches, progressive rollouts, and user targeting

These strategies can help you design for control in production.

Megan Moore

Orchestrate and safeguard AI agents with AI Configs

LaunchDarkly AI Configs helps you control AI agents at runtime.

LaunchDarkly

Online evals in AI Configs is now GA

Online evals in AI Configs help you define and monitor quality in production.

Kelvin Yap

AI-generated code ships fast, but runtime control hasn’t kept up

AI is speeding up code generation, but control in production is lagging behind.

Introducing LLM Playground for AI Configs

Test, compare, and trace LLM prompt and model variations before they reach production.

Kelvin Yap