SAN FRANCISCO – Harness, the AI Software program Supply Platform firm, at present introduced it’s extending its platform to cowl the total AI Agent Growth Lifecycle (DLC), giving enterprises a single set of pipelines and controls to construct, take a look at, deploy, and run brokers the identical approach they already ship the whole lot else.
Each enterprise is constructing AI brokers, however most can’t get them previous inner pilots or proofs of idea. Based on Gartner®, “Solely 8% of organizations have agentic AI in manufacturing.” The software program supply lifecycle enterprises’ belief for delivery utility code hasn’t prolonged to brokers but, trapping the ROI of inner AI investments. Actual innovation arrives as soon as an organization can run an agent dwell with the identical belief and confidence it has in the remainder of its software program.
“After we began Harness, the imaginative and prescient was a security harness for code,” stated Jyoti Bansal, co-founder and CEO of Harness. “Till not too long ago, that meant utility code. Immediately it additionally means agentic code, written throughout engineering, product, gross sales, and assist groups alike, every constructing brokers for their very own workflows. The whole lot you’ve finished for software program supply during the last decade — governance, orchestration, safety, testing — now you can do for brokers in the identical platform.”
Why AI brokers break the standard software program supply lifecycle
Conventional software program works as a result of it’s predictable. Utility code is deterministic. Run the identical take a look at towards the identical code twice, and it produces the identical outcome each instances.
Brokers don’t work that approach: an agent’s underlying language mannequin decides how you can full a job, and the identical agent, given the identical enter, can select a unique device or take a unique motion from one run to the following. A take a look at that passes as soon as affords no assure it should cross the following time. Incidents cease being reproducible on demand, which implies the usual playbook for catching and fixing bugs doesn’t switch both.
The stakes rise with the dimensions of the enterprise. A rogue agent can expose buyer information, violate a compliance coverage, or take an motion no person accepted. Enterprises want a option to reply for what their brokers are doing, and the standard software program supply lifecycle was by no means constructed to present them one.
New Harness Agent DLC merchandise and capabilities
Agent DLC closes the hole between constructing an agent and delivering it safely to manufacturing. Immediately’s launch consists of 5 new merchandise and capabilities spanning testing, deployment, operations, and governance:
-
Harness AI Evals makes agent high quality measurable, letting groups outline eval datasets, wire up scoring features, and set high quality gates that routinely catch regressions every time an agent or mannequin adjustments.
-
Agent Deployments lengthen the canary releases, approvals, and OPA guardrails that Harness already applies to Kubernetes deployments to managed agent runtimes like Amazon Bedrock AgentCore and Google’s Agent Runtime. Brokers now ship by way of present pipelines as a substitute of a separate cloud-specific workflow.
-
AI Configs assist the discharge and administration of prompts and mannequin adjustments at runtime, backed by the identical function flagging infrastructure that already manages code releases. Groups can take a look at what performs finest and roll again immediately, with out redeploying.
-
AI Asset Catalog routinely discovers each agent, talent, and plugin constructed throughout a corporation’s repositories and hyperlinks every to an proprietor, so nothing ships or runs unaccounted for.
-
Harness AgentTrace data what occurs throughout a single agent run and throughout a full multi-step session, displaying which path an agent took, the place it slowed down, and the way totally different fashions or prompts have an effect on the result. Harness can also be open-sourcing the foundational elements behind AgentTrace, together with harness-sdk and harness-evals, so builders can carry the identical tracing primitives into their very own AI functions.
As well as, present Harness merchandise already lengthen to brokers with out requiring any adjustments: Steady Integration builds them like another service, Artifact Registry tracks their variations and dependencies, AI Take a look at Automation validates their responses in plain English standards, and AI Price Administration extends spend visibility to each agent and mannequin.
Securing the Agent DLC
Brokers select their very own strategy and path to get there, so their habits is difficult to foretell and simply as laborious to safe. They broaden their very own assault floor by connecting to instruments and APIs, spawning sub-agents, and inheriting belief from each mannequin they contact. Static scans have been by no means designed for this type of threat. Harness is launching new safety capabilities to shut that hole.
Shift-left: constrain what brokers can do earlier than they ship.
-
Primitive Scanning flags misconfigurations in agent expertise, prompts, and fashions.
-
AIBOM captures each mannequin, device, and dependency an agent was constructed with.
-
AI Testing runs brokers towards adversarial inputs and the OWASP High 10 LLM and Agentic AI dangers.
Defend-right: implement coverage and keep visibility as soon as they’re dwell.
-
Agent Discovery and Posture Administration constantly maps brokers as they spin up and the way they join throughout the group.
-
AI Firewall enforces coverage in actual time towards immediate injection, device misuse, and information exfiltration.
Collectively, these capabilities give Agent DLC a single audit path from improvement to manufacturing.
Constructed on the Harness platform
Harness constructed context and intelligence straight into the platform with the Software program Supply Information Graph, which captures and connects information from each stage of the supply lifecycle, now spanning each functions and brokers. Organizations counting on siloed instruments don’t have that very same related view.
In June 2026, Harness launched Autonomous Employee Brokers, a platform for constructing and safely operating AI brokers inside software program supply pipelines. Employee Brokers run as ruled steps inside these pipelines, lined by the identical controls Harness already applies to each deployment.
Agent DLC extends that very same context and governance throughout the total agent lifecycle. The pipelines, insurance policies, approvals, and proof that already apply to a corporation’s code now apply to its brokers too, so eval gates, deployment approvals, and safety checks run as levels inside a single pipeline, from the second an agent is created by way of the whole lot it does afterward.
Availability
Harness Agent DLC capabilities are rolling out now to Harness clients. For a full breakdown of what’s included at every stage of the lifecycle, go to [blog page].
How does Harness AI Evals work for testing AI brokers?
Harness AI Evals lets groups outline analysis datasets, configure scoring features, and set high quality gates that routinely detect regressions when an agent or underlying mannequin adjustments. It addresses the non-deterministic nature of LLM-based brokers, the place the identical enter can produce totally different outputs throughout runs.
Can Harness Agent DLC deploy brokers to Amazon Bedrock AgentCore and Google Agent Runtime?
Sure. The Agent Deployments functionality extends Harness canary releases, approval workflows, and OPA coverage guardrails to managed agent runtimes together with Amazon Bedrock AgentCore and Google’s Agent Runtime, so brokers ship by way of present Harness pipelines reasonably than cloud-provider-specific workflows.
How does Harness safe AI brokers towards immediate injection and LLM vulnerabilities?
Harness introduces each shift-left and shield-right safety capabilities. Shift-left instruments embody Primitive Scanning for misconfigurations, AIBOM for dependency monitoring, and AI Testing towards OWASP High 10 LLM and Agentic AI dangers. Defend-right capabilities embody Agent Discovery and Posture Administration for runtime visibility and an AI Firewall that enforces coverage towards immediate injection, device misuse, and information exfiltration in actual time.
