LaunchDarkly introduces AgentControl for runtime control of AI agents
LaunchDarkly launched AgentControl, a solution aimed at giving engineering teams real-time control over AI agent behavior in production without redeployment. The release frames the move as an expansion of LaunchDarkly’s runtime control platform for agent deployments.
The company said that as AI agents move into production, teams need ways to manage configuration, quality, and runtime behavior. It also cited that agent behavior can differ across models, prompts, and production contexts even when application code remains unchanged, requiring shared standards for governance, versioning, and release controls.
AgentControl combines runtime intervention with an operational layer. The solution is described as supporting configuration of agent behavior across teams and frameworks, benchmarking quality before changes reach live traffic, releasing using progressive exposure and guarded rollouts, observing performance with trace-level visibility, and iterating based on production data, all without a redeployment cycle.
LaunchDarkly said configuration changes propagate in under 200 milliseconds with its platform. “LaunchDarkly has always been about giving software teams control at runtime over what their software does in production,” said Cameron Etezadi, CTO of LaunchDarkly. “The hardest problems in AI, like model drift, unpredictable outputs, and the inability to intervene fast enough, turn out to be exactly the problems our platform was built to solve. We didn't have to reinvent the platform; we just had to extend it to meet the demands of an AI SDLC and agentic-driven workflows.”
“Cursor is how the world's leading enterprises are building with AI. As more AI-powered products and agentic capabilities reach production, runtime control becomes essential infrastructure alongside the development workflows and controls teams already trust,” said Brian McCarthy, President, Global Revenue and Field Operations at Cursor. “LaunchDarkly built an additional layer for that environment, and AgentControl extends it to the agent lifecycle in a way that complements how Cursor's customers already build.”