Stories by Kelvin Yap
3 reasons teams can’t trust their AI agents with more
Here’s why the teams that are trying to build capable, trustworthy agents without adjusting their development process are struggling.
Kelvin Yap
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
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
Adaptive Triggers: AI that corrects itself in production
Adaptive Triggers is now available in closed beta.
Kelvin Yap
Introducing AgentControl
AgentControl is the operational layer for managing agents in production.
Kelvin Yap
Agent graphs bring control and visibility to multi-agent AI workflows
Agent graphs bring real-time control to multi-agent AI workflows.
Kelvin Yap
Online evals in AI Configs is now GA
Online evals in AI Configs help you define and monitor quality in production.
Kelvin Yap
Introducing LLM Playground for AI Configs
Test, compare, and trace LLM prompt and model variations before they reach production.
Kelvin Yap
Online evals: LLM-as-a-Judge
Online evals in AI Configs give teams quality signals to successfully ship AI changes.
Kelvin Yap
Understanding AI behavior: LLM observability in AI Configs
Get deeper visibility into model behavior and impact with LLM observability.
Kelvin Yap
