Latest AI posts
Search
A human look at the AI future
Honest reflections on the uncertainty, excitement, and opportunities of the agentic era.
Sarah Day
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
ML Experiment Tracking: What to Track Across Models, Data, and Production
The vast majority of teams working on large language models (LLMs) and machine learning (ML) systems diligently track hyperparameters.
Scarlett Attensil
Best Practices for Experiment Tracking in MLOps
Machine learning experimentation scales quickly.
Scarlett Attensil
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
The Complete AI Experimentation Guide: Test, compare, validate, and ship safely
Artificial intelligence tools aren’t like traditional software.
Scarlett Attensil
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
