Harness Introduces Autonomous Worker Agents for Software Delivery
Harness announced in a press release the launch of Autonomous Worker Agents, a system that enables enterprises to build and run AI agents for software delivery. The agents handle work across the build, test, deploy, and operations stages, operating inside existing pipelines with enterprise-level governance and security controls.
The agents function as governed steps within Harness pipelines, inheriting controls such as sandboxing, scoped credentials, policy enforcement, and audit trails. Each agent runs in isolation, with restricted access and defined permissions, ensuring safe execution in production environments. Token usage is tracked per agent and per pipeline.
Harness provides pre-built agents including Autofix, Code Review, Code Coverage, Feature Flag Cleanup, Manifest Remediator, and IaCM Remediation. These agents automate common software delivery tasks such as fixing build failures, reviewing code quality, and resolving configuration issues.
A new Harness Agent Marketplace offers Managed, Certified, and Community tiers for publishing and sharing Worker Agents. Teams can adopt, modify, or contribute agents within the marketplace. The platform supports multiple large language models, including Anthropic via AWS Bedrock and OpenAI, with flexible configuration per agent or pipeline.
Autonomous Worker Agents and the Harness Agent Marketplace are now generally available to all Harness customers.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.
Also, consider following us on social media:
AI Programming Weekly
Weekly news about AI tools for software engineers, AI enabled IDE's and much more.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Chainguard launches Harness for AI vulnerability testing
Josh Bersin Company Maps 151 AI Agents for HR Management
Loadsmart Launches AI Agents for Freight Workflows
Autoheal raises $7.9 million to improve software agents
The Conference Board Proposes Five Stage Framework for AI Agents
Daily AI Brief: the AI news that matters, in your inbox.