Kore.ai, the global leader in enterprise AI platform and agentic applications, announced general availability of Autoloop™, the optimization engine of the Kore.ai Agent Platform, Artemis edition. Enterprises set the goals. Autoloop builds the agents, measures them against those goals, and keeps optimizing them automatically, from first draft through production. The launch marks a shift in how enterprise AI is run: from agents tuned by hand to those that self-improve against the goals set by the business.

Today, most enterprises maintain agents through a cycle of fixing individual failures, and a fix for one problem often creates another. The cost of that approach is now measurable: the 2026 Kore.ai Agent Productivity Index found that 79% of enterprises have reversed an action taken by an AI agent, and 70% have faced a failure their teams could not trace. However, the industry is shifting, and Gartner predicts that by 2030, autonomous learning techniques will be present in a majority of AI agents, up from less than 5% in 2026.

“Every enterprise knows what it wants from its agents: finish the job, follow the rules, stay safe, and do it at a sensible cost,” said Raj Koneru, Founder and CEO of Kore.ai. “With Autoloop, your agents keep improving against the goals you set. The companies that scale AI will be the ones using AI to build, govern, and optimize AI.”

Autoloop starts from goals, not prompts. Teams define what success looks like across the dimensions that matter to the business, and Autoloop optimizes against all of them at once:

• Task completion: the agent finishes what the user came to do, handing off to a human only when it should.
• Accuracy and grounding: every answer is correct and backed by the enterprise’s own data, with no fabricated facts.
• Business-rule adherence: complies with policies, eligibility checks, and limits on every interaction.
• Guardrails and safety: no data exposure, off-policy actions, or unsafe responses.
• Consistency: consistent behavior across phrasings, languages, channels, and edge cases.
• End-user experience: fewer turns, less repetition, and lower latency across chat and voice.
• Cost efficiency: the same outcome with fewer, faster, and more affordable model calls and tokens.

Against these goals, Autoloop runs one continuous loop spanning: build, evaluate, diagnose, optimize, and re-verify. Before launch, it builds the agent and its test coverage from the enterprise’s own operating procedures and iterates until the agent meets every goal. In production, real interactions start new optimization cycles. Every change is scored against all goals at once, so a gain on one, such as lower token spend, cannot quietly hinder another, such as task completion or safety.

Automatic optimization requires complete visibility into agent activity and control over how they change. Two Kore.ai innovations give Autoloop these capabilities:

• StateTrace delivers the visibility, evaluating agents against their full production execution context. It traces every handoff, delegation, state, tool call, and piece of context across the agent network, so Autoloop knows where and why a goal was missed. A patent-pending five-layer validation architecture makes most checks deterministic, which keeps continuous optimization affordable at enterprise scale.
• Agent Blueprint Language (ABL) delivers the control by compiling supervision, routing, handoffs, delegation, tools, business rules, and guardrails into an executable state machine. Every step in a trace maps back to the blueprint, so Autoloop changes exactly the part that caused the miss, and nothing else.

Kore.ai runs the same discipline on its own engineering, where AI agents now produce roughly 6,500 commits a month on a production codebase of 2.6 million lines, governed by 68 always-on guardrails.

“You can’t optimize what you can’t see, or fix precisely what you can’t express precisely,” said Prasanna Arikala, Chief Technology Officer and Chief Product Officer at Kore.ai. “StateTrace lets Autoloop see exactly what agents did, and ABL allows it to change anything that needs changing. These are the technologies that make automatic optimization a reality.”