Agent builders / Workday
Workday AI Agents
Workday-built, partner and custom agents under Agent System of Record; Flex Credits consumption
No public price. Flex Credits bought in bulk; each agent skill costs a set number of credits (for example 1 or 5 per action); no public dollar rate. Official page
Company app connectorsPartly · “Agent-Ready Tools”
Workday exposes its own data to agents; reading other company apps is not described here.
Connect Workday to any agent. Agent-Ready Tools are engineered for agents with the structure and context agents need to act accurately, every time.
MCP serversYes · “Agent-Ready Tools & MCP”
Workday connects to agents over open protocols including MCP and A2A.
This allows customers to connect through Teams, Gemini, and open protocols like MCP and A2A.
Models from several companiesYes · “Model Choice”
Agents on Workday's Agent Harness can run on models from six companies, including Anthropic, Google and OpenAI.
Run agents on foundation models from Anthropic, Google, and OpenAI, or open models from NVIDIA, Meta, and Mistral.
No-code agent builderYes · “Agent & App Builder”
Build custom agents in plain language, with governance built in.
Empowers your team to build custom agents in plain language, codes using your preferred tool, and ensures every agent deployed has built-in governance.
Agents call other agentsYes · “Agent-to-Agent (A2A)”
Workday agents and outside agents, such as Gemini Enterprise ones, can hand tasks to each other over A2A.
The partnership supports Agent-to-Agent (A2A), Agent-to-UI (A2UI) and Model Context Protocol (MCP) approaches so AI agents can share information and autonomously hand off tasks to each other in real time, all within a single workflow.
Starts on its ownPartly · “agent builder”
Scheduled and event-started custom agents need the Sana Enterprise SKU; autopilot Workday agents are early adopter only.
Users can trigger agents manually, on a schedule, or through third-party events.
Asks a person firstYes · “human-in-the-loop approval”
Sana asks a person to confirm actions that need approval; pending approvals wait in the Sana Inbox.
Prompts users to review and confirm actions that require human-in-the-loop approval before proceeding.
Test before launchYes · “Evals and Traces”
Agent Harness evals measure an agent's accuracy before deployment; generally available since October 2026.
Measure accuracy before deployment and give auditors a step-by-step trace of what the agent did.
Audit logsYes · “Agent System of Record”
Admins can view a record of everything agents do.
Quickly view a record of everything agents do, and prove the agents are actually working.
Data residencyNot documented
Searched Workday trust, privacy, compliance and AI pages; no statement letting customers choose a data region for agents.
No statement from Workday found.
Your own encryption keysPartly · “bring-your-own-key”
BYOK covers Workday platform data at rest; Workday says nothing specific about agent data or model calls.
Additionally, customers have the option to implement bring-your-own-key capability to retain full control of their root encryption keys.
Not used for trainingPartly · “Responsible AI”
Workday never shares customer data to train third-party public models; some ML features use opted-in tenant data.
We never share customer data to train third-party public models.
SOC 2 and ISO 27001Yes · “ISO 27001 and SOC 2 Type II”
ISO 27001 scope includes Sana Agents; Workday also publishes a SOC 2 Type II report.
Information Security Scope (ISO 27001, 27017, 27018): Adaptive Planning, Analytics and Reporting, Contract Lifecycle Management (CLM) and Contract & Document Intelligence, Financial Management, HiredScore, Human Capital Management, Payroll, Peakon, Platform and Product Extensions, Spend Management, Student, Talent Management, Workforce Management, and Sana (Core/Enterprise, Learn, Agents).
HIPAA BAAPartly · “HIPAA attestation”
A third-party HIPAA attestation for Workday Enterprise Products; no BAA or agent-specific statement found.
Workday has completed a Health Insurance Portability and Accountability Act (HIPAA) third-party attestation for the Workday Enterprise Products
FedRAMPPartly · “FedRAMP Moderate”
Workday Government Cloud is FedRAMP Moderate; Workday does not say its AI agents run in that boundary.
Workday is FedRAMP Authorized status at the Moderate security impact level for Workday Government Cloud.
Changes
featureWorkday AI Agents
Autopilot agents run HR, finance and IT tasks in the background
Talent Acquisition Agent is live for early adopters. Payroll, Accounting and Deployment Agents get autopilot next, within customer approval rules.
newsroom.workday.comfeatureWorkday AI Agents
Workday Custom Agents generally available
Customers can build their own agents, run them on Workday's Agent Harness, and choose the AI model behind each agent.
newsroom.workday.comfeatureWorkday AI Agents
Developer Agent and Agent-Ready Tools for building on Workday
Developers can build agents on Workday from tools like Claude Code and Cursor. Agent-Ready Tools expose HR and finance data over MCP.
newsroom.workday.com