Workday announced that its Trusted Agent Platform now supports headless operation, letting customers build, deploy, and manage AI agents for HR and finance using their preferred development tools and AI models.
“Headless can’t mean lawless,” said Gabe Monroy, Workday’s chief technology officer. “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.”
Headless, not lawless
The platform features Workday Data Cloud, Agent-Ready Tools, Developer Agent, Custom Agents, and Agent Harness. Agent-Ready Tools use the Model Context Protocol (MCP) to let compatible AI agents securely access Workday data and perform approved actions. Live Data Query enables users and agents to query real-time data using SQL, eliminating the need for custom reports or duplicate datasets.
Agent Harness provides agents with organisational context, including employee roles, reporting structures, permissions, policies, and business processes. It governs actions and directs tasks to the appropriate AI models. Planned enhancements, including Agent Context Service and Grounded Reasoning, will further improve contextual accuracy and policy compliance.
Developer Agent enables teams to create custom agents and applications using natural language instructions and their preferred development tools. Custom Agents support deployment through Agent Harness and frameworks such as LangChain, with models including Anthropic Claude, Google Gemini, Meta Llama, Mistral, OpenAI GPT, and NVIDIA Nemotron.
“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 optimised workflows they can adapt, govern, and trust.”
