The launch of Release Autopilot comes as AI accelerates code creation, making manual release processes an increasingly significant bottleneck in software delivery. Coding agents have made writing software dramatically faster, but even the best testing can’t catch everything that can go wrong in production. In the LaunchDarkly 2026 AI Control Gap Report, 94% of respondents said AI has increased their code velocity, but 91% said it has made them more cautious about pushing to production. Under pressure to deliver, 82% reported shipping changes with unresolved risk in the past six months.

That pressure is greatest at companies building AI software factories, where agents handle more of the development lifecycle and engineers set the rules. But any team shipping more AI-written code than it can review faces the same challenge: how to scale safe release practices without slowing delivery. In many of those teams, releasing software still depends on manual work. For each change, an engineer often decides whether it needs a feature flag, sets up the rollout, watches the dashboards, rolls it back if something breaks and cleans up afterward.

“Human attention is among the scarcest resources in the software factory, and it belongs on the highest-value work,” said Jonathan Nolen, chief product officer of LaunchDarkly. “Today too much of it goes to the toil of managing release risk: deciding what needs a flag, configuring rollouts, watching and jumping in if something goes wrong. If the plan for AI-written code is for a person to catch every problem before it ships, you don’t have a software factory. You have a longer production line. Release Autopilot handles much of that toil, which lowers risk and frees engineers to build the changes that actually move the business.”

Release Autopilot manages that risk one change at a time. It assesses each change’s type, impact and risk, and wraps those that warrant control in a flag. Then it exposes them to progressively larger audiences while monitoring error rates, latency and other release metrics. If a change breaches a threshold, Release Autopilot pauses the rollout or returns the change to its last good state without a redeploy. Once the rollout completes, it automatically cleans up temporary release flags that are no longer needed. Engineers set the policies and choose how much to automate, from reviewing and approving Release Autopilot’s recommendations to letting it take action on its own. It works alongside whatever agents, pipelines and clouds make up a company’s factory and runs on the LaunchDarkly platform, which evaluates 70 trillion feature flags a day.

“Our customers are the world’s largest law firms, and they have no tolerance for error,” said Tiama Hanson-Drury, chief product and technology officer of Opus 2, a legal technology company. “By separating deployment from release, we now ship continuously and release only when we’re ready. The result: 3.9 times more work delivered to customers, and escaped defects down from 64 per release to virtually zero. Release Autopilot helps us move this fast without asking customers to take on more risk.”

“Generative AI is accelerating code output, but for many organizations that has just moved the bottleneck later in the SDLC. Release is the last mile of the delivery pipeline and often still runs on bespoke, manual workflows. Teams are finding that those high-friction gates aren’t scaling with today’s volume,” said Rachel Stephens, Research Director at RedMonk. “Release Autopilot is a clear step toward making progressive delivery a repeatable, low-friction default rather than an occasional risk-mitigation tactic.”

Release Autopilot will be generally available Nov. 16 (some features in beta).