---
title: "ASOR setup for HRIS admins — Kiweely"
description: "Enable Agent System of Record, turn on its domains, and grant an unconstrained group View and Modify before you register any Workday-built agent."
url: https://kiweely.com/guides/workday-asor-setup-for-hris-admins
---

# Set up Workday Agent System of Record for HRIS admins

ASOR is the tenant control plane for agents. HRIS admins enable the functional area, activate security twice, and permission an unconstrained group. The configuration does not migrate, so Production, Sandbox, Preview, and Implementation each need the same setup.

-   **Checked** against Workday on November 16
-   Applies to **Workday Extend**
-   6 min read
-   Published November 16
-   By Kiweely

Agent System of Record (ASOR) is how Workday says you manage the organization’s agents inside a tenant. You enable the **Agent System of Record** functional area, enable its domain security policies, and grant an unconstrained security group access to the hub, setup, and audit reports. There is no migration. A Sandbox that was refreshed before you did this work does not inherit a setup you only clicked in Production later, and a setup that exists only in Implementation does not appear in Production.

You need the **Security Configuration** domain in the System functional area. Do this once per tenant before anyone registers Deployment Agent, Self-Service Agent, or another Workday-built agent. Registration itself is limited to agents in SKUs you have. For Workday-built agents, the Self-Service Agent setup topic says UMSA is required in non-production and in Production. Self-built agents do not require UMSA in non-production. Check Subscription Service Agreement on your Workday Community organization profile before you promise a go-live.

## The sequence

Workday splits setup into enablement, a first activation, domain enablement, permissions, and a second activation. Skipping either activation leaves the hub tasks missing or the new permissions pending.

### 1\. Enable the functional area

Run **Maintain Functional Areas**. Select **Enabled** for **Agent System of Record**. Click OK, then Done.

### 2\. Activate, the first time

Run **Activate Pending Security Policy Changes**. Enter a comment, select Confirm, and finish. This activation is for the functional area itself.

### 3\. Enable the domains

Open **Domain Security Policies for Functional Area**. Select functional area **Agent System of Record**. From each domain’s related actions, choose **Domain Security Policy > Enable**.

The setup page names these in the enable list: **Agent Compliance**, **Agent Management Hub**, and **Manage: Agents**. It then tells you to repeat the enable for **Reports: AI Agent Security** in the System functional area.

### 4\. Grant View and Modify to one unconstrained group

Run **Maintain Permissions for Security Group**. Operation: **Maintain**. Source security group: the group that will administer agents.

Workday’s current limitation: you can only configure **unconstrained** groups on ASOR security policies. A role-based HR Partner group that is constrained by supervisory organization cannot be the group you put on these policies. Use an unconstrained admin group, and keep day-to-day HR roles off this list.

On **Domain Security Policy Permissions**, grant **View** and **Modify** for:

| Policy | What Workday says it unlocks |
| --- | --- |
| Agent Compliance | Reports and data for agent compliance. |
| Agent Management Hub | The hub for viewing and managing all agents. |
| Manage Agents | Tasks to configure, activate, and deactivate agents in ASOR. |
| Reports: Agent Reporting | Agent analytics, report data sources, and filters. |
| Reports: AI Agent Security | Reports about agent security. The example is **View AI Agent User Audit Trail**. |
| Setup: Agents | Setup tasks and activities for agents in ASOR. |

**View Security for Agent Skill** is secured to **Manage: Agents** (and the report also cites **Security Administration** in the System functional area for the test action). If your admin group lacks Manage: Agents, you cannot review skill security after registration.

### 5\. Activate, the second time

Run **Activate Pending Security Policy Changes** again, with a comment that names the group and the tenant. Permissions stay pending until this step. Testing “as the new admin” before activation proves nothing.

## What this setup does not do

| Still separate | Why |
| --- | --- |
| Deployment Agent Users domain | Chat access to Deployment Agent. **Available To** groups must also be on that domain or Workday rejects them. |
| Self-Service Agent skills and **Available To** | Which employees or managers may use which skill. The Guide skill has to be enabled or the agent does not run. |
| Graph API Descriptor, with All Users | Named on the Self-Service Agent setup topic, not on the generic ASOR setup. |
| Tool security for the APIs a skill calls |  **View Security for Agent Skill**. Interaction groups and tool policies are both checked at runtime. |
| A constrained HR role as the ASOR admin | Not allowed on these policies while the unconstrained limitation stands. |

Register agents only after both activations. In **Agent Management Hub**, **Unregistered Workday Agent**, register the agent your SKU includes. It moves to **Agent Registry**. Then configure skills and activate that agent. ASOR setup alone does not turn any assistant on.

## One checklist per tenant

Copy this for Production, Sandbox, Sandbox Preview, Implementation, and Customer Central if you use it. Customer Central has its own Agent System of Record setup. Configuring Deployment Agent only there does not configure the connected non-production tenants.

| Check | Production | Sandbox | Preview | Implementation |
| --- | --- | --- | --- | --- |
| Functional area enabled |  |  |  |  |
| First security activation |  |  |  |  |
| ASOR domains enabled, plus Reports: AI Agent Security |  |  |  |  |
| Unconstrained group has View and Modify on the six policies |  |  |  |  |
| Second security activation |  |  |  |  |
| Agent Management Hub opens for that group |  |  |  |  |
| View AI Agent User Audit Trail opens |  |  |  |  |

For Sandbox refreshes, Workday’s Deployment Agent topic recommends also configuring that agent in Production so the refresh does not wipe it, even though people cannot use Deployment Agent in Production. That is agent configuration, not a substitute for doing ASOR in the Sandbox you are testing today. If you need the agent before the next refresh, configure Production and the current Sandbox.

## Failure modes

| Symptom | Where to look |
| --- | --- |
| Maintain Functional Areas has no Agent System of Record row you can enable | Security Configuration, or the agreement and SKU. |
| Hub is empty of tasks after you enabled the area | The first **Activate Pending Security Policy Changes** did not run. |
| You cannot pick the HR Partner role on the policy | The group is constrained. Pick an unconstrained group. |
| Admins still cannot open the hub | The second activation did not run, or View and Modify were granted on only some of the policies. |
| Audit report is missing |  **Reports: AI Agent Security** was not enabled in System, or the group has no permission on it. |
| Sandbox “lost” agents after refresh | ASOR and the agent were not established in the tenant that the refresh copies from. |
| A worker can administer agents and also sees every organization | You put a broad unconstrained group on ASOR. The setup topic does not offer a constrained alternative. Split membership: few people in the unconstrained admin group. |

## Frequently asked questions

### Is ASOR the same thing as turning on Self-Service Agent?

No. ASOR is the prerequisite control plane. Self-Service Agent is one Workday-built agent you register afterward, with its own skills, a required Guide skill, and **Available To** groups.

### Can we transport this with Object Transporter?

The ASOR setup topic says there is no current method to migrate the configuration. Object Transporter is documented for things like condition rules, not for this setup. Repeat the steps in each tenant.

### Who should be in the unconstrained group?

People who register, configure, activate, deactivate, and read agent audit reports. Not every HR business partner. Worker access to an assistant is **Available To** on that agent’s skills, plus the worker’s own domain and business process security for the tools.

### What do we do about Flex Credits?

The Self-Service Agent setup topic points usage impact to Workday’s Flex Credits material. The Deployment Agent deactivate topic says deactivating that agent stops Flex Credit consumption in that tenant. ASOR setup itself is not the usage switch. Activation of a specific agent is.

## Sources checked

Frontmatter pages, fetched 2026-11-16.

## Sources checked

-   [Set Up Agent System of Record](https://doc.workday.com/admin-guide/en-us/workday-ai/agents/set-up-agent-system-of-record.html)
-   [Set Up Deployment Agent in Implementation Environments and Customer Central](https://doc.workday.com/admin-guide/en-us/workday-ai/agents/workday-built-agents/deployment-agent-in-implementation-environments-an/set-up-deployment-agent-on-implementation-environm.html)
-   [Set Up Self-Service Agent](https://doc.workday.com/admin-guide/en-us/workday-ai/agents/workday-built-agents/self-service-agent/set-up-self-service-agent.html)
-   [View Security for Agent Skills and Tools](https://doc.workday.com/admin-guide/en-us/workday-ai/agent-security/view-security-for-agent-skills-and-tools.html)
-   [Workday-Built Agents](https://doc.workday.com/admin-guide/en-us/workday-ai/agents/workday-built-agents/reference--workday-built-agents.html)

## Related guides

[All guides](https://kiweely.com/guides)

-   [### Stop or audit a Workday AI agent: an admin runbook When an agent must stop, deactivate it in every tenant where it was set up. Hiding it is not enough if Production will refresh Sandbox. Use View AI Agent User Audit Trail and View Security for Agent Skill to see what it did and what it can still do.](https://kiweely.com/guides/stop-audit-workday-ai-agent-admin-runbook)
-   [### Review security group changes an AI assistant suggested in Workday Deployment Agent can name a domain and a missing View group. As documented, you still edit the policy (change-making is in partner early access), activate pending changes, and confirm View Security for Agent Skill is not Config Required. Constrained groups cannot administer Agent System of Record.](https://kiweely.com/guides/review-ai-workday-security-group-changes)
-   [### A Workday admin’s first week with Deployment Agent Deployment Agent is a non-production assistant for implementers and administrators. This week plan follows Workday’s setup: confirm UMSA, set up Agent System of Record per tenant, secure Deployment Agent Users, register skills, and prove one tenant-grounded prompt.](https://kiweely.com/guides/workday-admin-first-week-deployment-agent)
-   [### Workday-built AI agents catalog: what each agent is for Use Workday’s Workday-Built Agents reference as the configuration catalog. This guide restates each agent’s published purpose, notes SKU and UMSA gates, and separates marketing names from what Agent Management Hub can register.](https://kiweely.com/guides/workday-built-ai-agents-catalog)
-   [### Workday Agent System of Record (ASOR): An Admin’s Security and Setup Checklist Workday’s Agent System of Record (ASOR) governs both Workday-built and custom agents through the Agent Management Hub. Here is how ASUs differ from ISUs, how delegate and ambient execution evaluate security, and the exact steps an administrator takes to register, secure, and audit an agent.](https://kiweely.com/guides/workday-agent-system-of-record-security)

### More guides on Custom agents and Workday AI

[All 91 guides](https://kiweely.com/guides#custom-agents)

-   [Financials and payroll prompts for the Workday Deployment Agent](https://kiweely.com/guides/workday-ai-prompt-library-financials-payroll)
-   [HCM prompt library for Workday implementers using Deployment Agent](https://kiweely.com/guides/workday-ai-prompt-library-hcm-implementers)
-   [Workday Developer Agent Prompt Templates That Hold](https://kiweely.com/guides/workday-developer-agent-prompt-templates)
-   [A Learning Path on a Workday Build Personal Tenant](https://kiweely.com/guides/workday-build-personal-tenant-learning-path)
-   [Build Your First Workday Extend App with Developer Agent](https://kiweely.com/guides/first-workday-extend-app-developer-agent)
-   [What counts as Workday test evidence when an agent helped](https://kiweely.com/guides/workday-uat-evidence-pack-ai-agents)
-   [Security workshops that follow Workday’s own access model](https://kiweely.com/guides/security-design-workshops-deployment-agent)
-   [Pick a Workday integration tool before you prompt an agent](https://kiweely.com/guides/ai-workday-integration-design-workshop)

### From the blog on Custom agents and Workday AI

[All posts](https://kiweely.com/blog)

-   [How to Create Any Workday Calculated Field with an AI Agent](https://kiweely.com/blog/create-any-workday-calculated-field)
-   [Free AI help for Workday developers: Developer Agent, Claude Code, Cursor and Kiweely compared](https://kiweely.com/blog/free-ai-assistant-for-workday-developers)
-   [Workday Studio to Extend AI: What to Rebuild With Developer Agent](https://kiweely.com/blog/workday-studio-to-extend-ai-developer-agent)

## Let Workday check the work.

Kiweely writes WQL and builds orchestrations in your own tenant, and Workday, not Kiweely, says whether they passed.

[Start for free](https://kiweely.com/download) [See how it works](https://kiweely.com/vine/how-it-works)

## Get the next guide in your inbox.

One email a month with new guides and one Extend tip. Nothing else.
