en.Wedoany.com Reported - Workday unveiled a suite of AI tools at its recent DevCon event, designed to help customers develop and deploy agent systems without compromising enterprise security or compliance. Among these, Agent Passport is the core product of the release, continuously verifying agent security and compliance both before deployment and during runtime. When an agent attempts to execute a task, Agent Passport can allow, block, or route the operation based on company policies, and even stop or restrict problematic agents.
When agents undergo risk review, they will be tested against multiple criteria including prompt injection, jailbreaking and goal hijacking, system prompt extraction, employee data leakage, and unsafe output. These tests follow public standards such as Mitre ATLAS and are conducted by security partners, not by Workday itself. Security teams can review these test attestations and obtain a signed, auditable record containing the test subject and specific test content. Since each check follows public standards, security teams can compare agents from different vendors tested by different partners under the same conditions. At launch, the only testing partner is Cisco. Workday CTO Gabe Monroy stated that introducing many partners simultaneously into the standards is challenging initially, so the plan is to move forward with Workday and Cisco first, followed by a broader rollout.
Regarding accountability—for example, when an agent that has passed testing and received a compliance mark behaves improperly—the determination of responsible parties is still under discussion. Agent Passport is scheduled to offer early access in the third quarter, with general availability expected by the end of the year.
DevCon also introduced Developer Agent, enabling developers to easily build AI applications and agents. Also released were Agent-Ready Tools, a new type of enterprise connector created for autonomous agents. Workday stated that Agent-Ready Tools provide agents with precise and easily navigable business logic and context while reducing hallucinations and latency, and connect and execute actions within Workday through open standards such as MCP. For agents that need to work outside Workday, developers can use pre-built Pipedream connectors to create custom agent actions and expose them as Agent-Ready Tools. Developer Agent can integrate with agent development tools of the developer's choice, including Claude Code, Cline, Codex, Cursor, or Google Antigravity, and create and deploy custom agents for the Workday platform through the open AgentSkills Standard (OASS). Developers simply input a request like "Build an agent that alerts the finance department when a department is likely to exceed its budget this quarter," and Developer Agent will select the appropriate Agent-Ready Tools, connect necessary data and services, and introduce required documentation and examples to complete the task. Developer Agent and Agent-Ready Tools are available to early access customers through Workday Extend Professional, with general availability expected in the second half of 2026.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
