Published: June 30th, 2026
SAN FRANCISCO — Harness, the AI Software Delivery Platform company, today launched Autonomous Worker Agents for software delivery: the platform for enterprises to build and safely run AI agents that handle the work between writing code and shipping it to production.
Software delivery has moved through phases. First, people did the work by hand. Then they wrote scripts for individual jobs like deployment. Most recently, they connected those jobs into automated pipelines that follow fixed instructions, which is what Harness has run for large enterprises for years. Worker Agents are the next phase. Every step in the pipeline can now run as a reasoning agent rather than a fixed script, with the context, governance, sandboxing, and audit trails that enterprises need to trust agents in production.
Dozens of Harness Managed Agents are available today, and any team can customize them or build their own. A new Harness Agent Marketplace makes it easy to find, use, and share them.
“AI now writes the code. Harness ships it,” said Jyoti Bansal, Founder and CEO of Harness. “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.”
Autonomous Worker Agents run on infrastructure that the customer controls. Code and data never leave the customer’s network, and agents are governed by the same controls enterprises already use for human deployments.
These controls make Autonomous Worker Agents safe to run in production:
- Sandboxing: Agents run in isolated containers with restricted file and network access.
- Scoped credentials: Each agent has its own identity and the specific set of permissions assigned to it.
- Policy enforcement: The same policies that gate human deployments gate agents.
- Audit trails: Every agent action is recorded under a distinct AI identity, with full provenance.
- Cost tracking: Token spend is surfaced per agent, per pipeline, with budget caps.
- Chaining: Agents compose into multi-step workflows, passing output from one to the next.
Harness pre-built dozens of Worker Agents including Autofix (reads build logs, identifies root cause, commits fix, re-triggers builds), Code Review, Code Coverage, Library Upgrade, Feature Flag Cleanup, Manifest Remediator, and Zero Day Mitigation.
The Harness Agent Marketplace has three tiers: Harness Managed (built and SLA-backed by Harness), Harness Certified (partner-built, reviewed by Harness), and Community (published by the broader community).
Autonomous Worker Agents work with any LLM provider through existing Harness connectors for Anthropic, AWS Bedrock, or Google Vertex AI.
Autonomous Worker Agents and the Harness Agent Marketplace are now generally available to all Harness customers.