The Trusted Agent Platform is now offering headless capability, making it possible for organizations to generate and run AI agents that will handle HR and finance tasks within the defined governance framework. With this capability, organizations can work with whatever tools and AI they want while maintaining their current security infrastructure. This was unveiled at the company’s Rising 2026 event. With this, AI agents can function independently of the user interface of the company. Every agent needs to conform to the guidelines of the platform.
Governance for AI Agents without Heads
The Trusted Agent Platform comprises Data Cloud, Agent-Ready Tools, Developer Agent, Custom Agents, and Agent Harness. The above features assist in building AI agents adhering to the known business rules. Workday warns that headless access creates threats if the agents make use of ungoverned data and system-level logins. Headless access may reveal confidential compensation details or perform unwanted activities. As such, Workday uses its security and governance controls for agent communications.
“Headless can’t mean lawless,” said Gabe Monroy, chief technology officer, Workday. “The rules for HR and finance already live in Workday, so customers don’t have to rebuild them for every agent they create. This is what lets companies move fast with agents without losing control.”
Using Agent-Ready Tools and Live Data Query, agents can be provided access to Workday data with pre-set permissions. The use of Model Context Protocol (MCP) ensures that the activities undertaken using the tools are appropriate for data access. On the other hand, Live Data Query allows users to get real-time data via SQL.
“MCP gives agents a standard way to connect with the systems where work happens,” said Ankur Sinha, head of enterprise and verticals, Anthropic. “Workday’s Agent-Ready Tools bring that model to HR and finance, helping customers give agents access to critical workflows while preserving the permissions and approvals their businesses already trust.”
Agent Harness Adds Context and Business Controls
Workday Agent Harness gives agents pertinent employee details, their roles within the organization, their permissions, and related policies. In turn, agents can undertake tasks in the right business context, not just from standalone data. Workday is scheduled to release Agent Context Service and Grounded Reasoning in early 2027. The technologies will help agents determine what context applies to their tasks and check whether the request aligns with company policies before executing them. For instance, an agent can deny any role modification beyond the manager’s jurisdiction.
More Freedom for Developers
Developer Agent is now generally available, enabling developers to build agents and applications using plain-language requests. Developers may utilize several developer-related tools such as Claude Code, Codex, Cursor, and the Workday Developer Site.
Deployment is also possible using Custom Agents through Agent Harness. The developer can choose from various frameworks like Google ADK and LangChain. There are several supported models including Anthropic’s Claude, Google’s Gemini, Meta’s Llama, Mistral, OpenAI’s GPT, and NVIDIA’s Nemotron open models.
“Efficient agents require a system of both open and proprietary models,” said Pat Lee, vice president, strategic enterprise partnerships, NVIDIA. “Workday’s Trusted Agent Platform gives developers the ability to work with the right model for the job – including NVIDIA Nemotron open models – so they can build optimized workflows they can adapt, govern, and trust.”
In conclusion, Workday seeks to enable companies to incorporate AI in their operations without sacrificing the security, transparency, or existing business processes.
Explore HR Tech News for the latest advancements in Human Resources Technologies and insightful updates from industry experts!
News Source: PRNewswire.com
