Harness, the AI Software Delivery Platform™ company, has announced the general availability of Autonomous Worker Agents, a new platform that enables enterprises to build, customize, and securely operate AI agents across the software delivery lifecycle. The launch introduces reasoning-based AI agents that automate tasks between code development and production deployment while leveraging existing enterprise governance, security, and compliance controls.
Harness is extending software delivery automation beyond traditional scripts and pipelines by introducing reasoning-based AI agents that execute workflow tasks autonomously.
Rather than relying on fixed automation, Autonomous Worker Agents operate as pipeline-native components capable of interpreting context, making decisions, and executing tasks while remaining subject to enterprise governance policies. The approach enables organizations to automate activities across software build, testing, security, deployment, and operations.
A key differentiator of Harness’ platform is its focus on enterprise-grade governance for AI operations. Worker Agents inherit the same controls already used for human-driven software deployments, ensuring AI actions remain secure, traceable, and policy compliant.
Key governance capabilities include:
This architecture enables organizations to safely deploy AI agents within production environments without compromising existing security frameworks.
Harness Worker Agents leverage the Harness Software Delivery Knowledge Graph, which provides contextual understanding of services, infrastructure, deployments, incidents, dependencies, and security findings.
Instead of generating generic responses, agents use enterprise-specific operational knowledge to troubleshoot issues, assess vulnerabilities, coordinate deployments, and recommend remediation based on an organization’s software ecosystem.
The platform also integrates with external developer environments through the Harness MCP Server, allowing developers to invoke Worker Agents directly from coding tools while maintaining centralized governance.
Harness is launching several managed AI agents designed to automate repetitive engineering tasks, including:
Organizations can use these agents immediately, customize them, or build their own using the standard agent-file format.
Alongside the Worker Agents, Harness has introduced the Harness Agent Marketplace, a centralized catalog where organizations can discover, publish, customize, and reuse AI agents.
The marketplace includes three categories:
Teams can fork existing agents, modify prompts or behaviors, and share enhancements across their organizations.
Harness supports multiple large language model providers, including Anthropic through AWS Bedrock, direct Anthropic integrations, and OpenAI. Organizations can select different AI models based on agent, pipeline, or deployment environment without modifying agent logic.
This flexibility allows enterprises to adapt AI strategies while maintaining consistent governance across software delivery workflows.
Jyoti Bansal, Co-founder and CEO, Harness
"AI now writes the code. Harness ships it. Autonomous Worker Agents are how enterprises build and safely run AI for everything after code: building, testing, securing, deploying, operating. All of it runs on the same pipelines that already ship our customers' software, inside their own network boundary. The governance, the audit trail, and the security posture are already there. Worker Agents inherit it all from day one."
John Jones, Director of Cloud Infrastructure, Verint Systems
"We built a Kubernetes troubleshooting agent that evolved from simply reading logs to actually troubleshooting issues very quickly. This agent will be rolled out at the org level. Having the agents inside the pipelines without needing to finagle calls out to other tools is extremely helpful. The agent will benefit more than 200 members of our operations team and ~1,000 developers. It only took us four days to learn and build a production-ready AI agent that will help us with our most common and time-consuming task of troubleshooting pipeline failures."
Ratna Devarapalli, Director IT, United Airlines
"We built RiskSentinel, a Harness Autonomous Worker Agent, to demonstrate that governed AI can move beyond identifying security issues to safely remediate them while maintaining enterprise controls, auditability, and compliance. When building with Harness, what stood out most was how intuitive the experience was — it enabled our team to move from an initial idea to a production-ready agent in just four days, allowing us to focus on solving a real enterprise challenge rather than the underlying platform. That combination of developer experience and enterprise-ready capabilities is what will enable organizations to confidently scale AI across software delivery."
Harness’ latest platform release reflects the growing adoption of agentic AI across enterprise software engineering. By combining autonomous reasoning with established DevOps governance, the company aims to help organizations accelerate software delivery while maintaining security, compliance, and operational control.
Harness is the AI Software Delivery Platform™ company, enabling engineering teams to build, test, and deliver software faster and more securely. Powered by Harness AI and the Software Delivery Knowledge Graph, the platform brings intelligent automation to every stage of the software delivery lifecycle after code — removing toil and freeing developers from manual, repetitive work. Companies like United Airlines, Morningstar, and Choice Hotels use Harness to accelerate releases by up to 75%, cut cloud costs by 60%, and achieve 10x efficiency across DevOps. Based in San Francisco, Harness is backed by Goldman Sachs, Menlo Ventures, IVP, Unusual Ventures, and Citi Ventures.
