---
title: "Review AI security group changes — Kiweely"
description: "Before you activate an AI-suggested Workday security change, compare the domain, Available To, and View Security for Agent Skill status."
url: https://kiweely.com/guides/review-ai-workday-security-group-changes
---

# 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.

-   **Checked** against Workday on November 19
-   Applies to **Workday Extend**
-   6 min read
-   Published November 16
-   By Kiweely

Treat an AI security recommendation as a list of objects to open, not as a change that is already safe. Workday’s Ask-skill example asks Deployment Agent which domain controls the Bonus Plan Override field, which groups have View, and how to update the policy. The sample answer names **Worker Data: Compensation Explicit** and a missing Payroll Specialist (role-based) group, then points you at editing domain permissions and activating pending changes. As documented, you do those tasks and the chat does not activate them. With [Configuration Cloud](https://blog.workday.com/en-us/configuration-cloud.html), in opt-in early access for Workday partners since 18 Nov 2026, Deployment Agent can carry out changes once approved.

Review in a non-production tenant. Deployment Agent is not a Production assistant. Agent System of Record (ASOR) security is configured per tenant and does not migrate.

## Sort the suggestion before you edit anything

| The reply tells you to change | Legal target | Reject or redirect |
| --- | --- | --- |
| A domain’s report/task permissions (View or Modify) |  **Edit Security Policy Permissions** on that domain, then **Activate Pending Security Policy Changes** | A group that does not exist. A domain you cannot find. |
| Who may open Deployment Agent | The group must be on **Deployment Agent Users** and on the skill’s **Available To**. Workday validates this and blocks groups that are not on the domain. | Putting only **Available To** and skipping the domain. |
| Who may administer agents |  **Maintain Permissions for Security Group** on ASOR policies. **Unconstrained groups only.** | A constrained HR Partner role as the ASOR admin group. The setup topic does not allow it. |
| Who may use a Self-Service skill |  **Available To** on that skill. Guide must stay enabled or the agent does not run. | A tool-level security group. Tools inherit the skill’s groups. You cannot assign a tool to one group. |
| Integration Get or Put | Only if you are looking at a web service policy and you meant to grant it. The Ask example’s result is View on a worker data domain, not an integration permission. | Adding Modify because the reply said “access.” View and Modify are different. Modify includes what View includes. |

**View Security for Agent Skill** is how you review the third case when the change is about an agent. You need **Manage: Agents**. Prompts: **Registered Agent**, **Agent Skills**.

| Status | Review rule |
| --- | --- |
| Full Match | The **Available To** group has every required policy for the tool. Still ask whether that group should. |
| Review Required | Partial required policies. Do not activate the agent on this status. |
| Config Required | A required policy has no groups. Fix these first. |
| Not Evaluated |  **Available To** is empty. Nobody has been tested. |

**Required Permissions** show View or Modify. **Additional Security (Optional)** is extra field access, not the minimum for the tool. **Test My Setup** (Security Administration) shows whether a group can reach the tool and which other policies also grant it.

Self-Service Agent evaluates both access to the agent and access to the tools’ APIs. Align **Available To** with the groups that can run the tools. They do not have to be an identical list, but a person needs to pass both checks. The setup topic tells you to compare them.

## The review sequence

1.  Paste the suggestion into the change ticket with the tenant name and the prompt you used. Include “in my tenant” prompts only if that phrase was actually sent. Without it, the answer may be generic.
2.  Open the named domain. If the domain name does not exist, stop. Do not pick a similarly named domain.
3.  Read current View and Modify rows. Note groups the reply did not mention. You are adding, not replacing, unless the reply explicitly says to remove a group and you agree.
4.  For a Deployment Agent chat group, confirm the group is on **Deployment Agent Users** before you put it on **Available To**.
5.  For an ASOR admin change, confirm the group is unconstrained. Grant View and Modify only on the policies you intend: Agent Compliance, Agent Management Hub, Manage Agents, Reports: Agent Reporting, Reports: AI Agent Security, Setup: Agents.
6.  For an agent skill, run **View Security for Agent Skill**. Clear Config Required. Record Review Required groups you refuse to widen.
7.  Edit the policy. Prefer a new row when the new group needs View and the existing row is Modify, so you do not copy the stronger permission by accident.
8.  **Activate Pending Security Policy Changes**, with a comment that names the domain and the group.
9.  **Test My Setup** or a proxy session as a user in the group and as a user outside it. Pending changes that you forgot to activate will fail this test. That failure is real.
10.  Thumbs up or thumbs down on the Deployment Agent answer after you know whether the domain was right. The rating does not roll back security.

Customer Central can be asked how the same change would affect another tenant. The published follow-up names the other tenant. Do not assume impl2 was inspected because you typed “downstream.”

## Self-Service tool messages are not security

If the suggestion says “restrict bonus history with a message,” that is not a domain change. The configure-tools topic lets you disable a tool (unless the Enabled toggle is unavailable) and supply a disabled message. The agent writes its own sentence from that message. Skill and tool changes can take up to 10 minutes to cache, and the tools topic says a person already in a conversation may not see the change until a new conversation. Security groups on the skill are unchanged when you only edit the message.

Disabling one tool does not change subscription or skill-level billing for the tools that stay on.

## Failure modes

| Result | Likely miss |
| --- | --- |
| Validation error on Deployment Agent **Available To** | Group is not on Deployment Agent Users. |
| Cannot select the security group on an ASOR policy | Group is constrained. |
| User still cannot see the field | Activation did not run, the group membership is wrong, or the field is secured by more than one domain. |
| User can see the field but the agent tool fails |  **Available To** passed and the tool policy did not, or the status was Review Required. |
| A whole organization gained Modify | The new group was added to an existing Modify row, or you used an unconstrained group for a worker-facing skill. |
| Sandbox review does not match Production | ASOR and domain edits do not migrate by themselves. |

## Frequently asked questions

### Should we accept the domain name in the example as our domain?

Only if your tenant uses that field and the policy you open is **Worker Data: Compensation Explicit**. The example is a sample result for Bonus Plan Override. Your field may be a different domain. The prompt is what you reuse. The sample domain is what you verify.

### Do interaction groups and API groups have to match person for person?

The Self-Service setup says to evaluate alignment. A person must be allowed on the skill and allowed on the tool’s domain or business process policy. The lists can differ. **View Security for Agent Skill** is the check, not a spreadsheet comparison done from memory.

### Can the AI remove a group?

As documented for Ask, only if you remove it in **Edit Security Policy Permissions** and activate. Configuration Cloud, in partner early access, can carry out approved changes. Read the remaining rows before you confirm. There is no published undo inside the chat.

### What do we file if Test My Setup disagrees with the reply?

The report status, the tool name, the **Available To** group, and whether you had already activated. That packet is the review. The chat is the proposal.

## Sources checked

Frontmatter pages, fetched 2026-11-16.

## Sources checked

-   [Example: Troubleshoot Security Policy and Access Configuration with the Ask Skill](https://doc.workday.com/admin-guide/en-us/workday-ai/agents/workday-built-agents/deployment-agent-in-implementation-environments-an/example--troubleshoot-security-policy-and-access-c.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)
-   [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)
-   [Configure Self-Service Agent Tools](https://doc.workday.com/admin-guide/en-us/workday-ai/agents/workday-built-agents/self-service-agent/disable-individual-self-service-agent-tools.html)

## Related guides

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

-   [### Start a proxy test after an AI-suggested Workday change Workday’s Adaptive Planning proxy procedure uses a proxy policy, Start Proxy, and Stop Proxy in non-production, and records the proxy user. After an AI-suggested security or rule change, add the tester that matches the object you edited.](https://kiweely.com/guides/workday-start-proxy-testing-after-ai-changes)
-   [### 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.](https://kiweely.com/guides/workday-asor-setup-for-hris-admins)
-   [### 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)
-   [### CRAFT prompts for the Workday Deployment Agent Workday’s Deployment Agent sample-prompts topic, updated 2026-11-06, says accurate answers come from five CRAFT elements. This guide restates that method, shows which elements you can omit, and rewrites the published samples so an administrator can see what each word is doing.](https://kiweely.com/guides/workday-deployment-agent-admin-prompt-patterns)
-   [### 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 Business processes and security

[All 27 guides](https://kiweely.com/guides#business-processes)

-   [Explain a Workday business process in plain language, then configure the rule](https://kiweely.com/guides/ai-workday-business-process-design-plain-language)
-   [Turn a requirements note into a Workday business process](https://kiweely.com/guides/ai-brd-to-workday-business-process-design)
-   [Benefits Life-Event Intake That Starts the Right Workday Process](https://kiweely.com/guides/benefits-life-event-intake-workday-business-process)
-   [How do I document Workday configuration and business processes from a live tenant?](https://kiweely.com/guides/document-workday-configuration-and-business-processes)
-   [How to Run Role-Boundary Security Tests Across Employee, Manager, and HR Partner Personas](https://kiweely.com/guides/workday-role-boundary-testing-employee-manager-hr-partner)
-   [Aligning Workday Session Timeouts with External OAuth Access Token Lifetimes](https://kiweely.com/guides/workday-anonymous-vs-authenticated-session-timeout-oauth)
-   [How Workday Terminations and Job Transfers Affect Active OAuth Grants](https://kiweely.com/guides/workday-revoke-oauth-tokens-terminated-transferred-workers)
-   [Configuring Workday Pre-Hire Security So New Employees Can Complete Tasks Before Day One](https://kiweely.com/guides/workday-pre-hire-onboarding-access-before-day-one-security)

### From the blog on Business processes and security

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

-   [Keeping External Workday Screens in Sync When You Change Absence Plans or Approval Rules](https://kiweely.com/blog/updating-custom-workday-screens-when-business-processes-change)
-   [Two Phone Apps, Two Jobs: Kiweely Companion for Admins vs. Kiweely Leaf for Employees](https://kiweely.com/blog/kiweely-phone-app-vs-kiweely-leaf-phone-app-explained)
-   [The CISO Checklist for Connecting Claude, ChatGPT, or Gemini to Workday](https://kiweely.com/blog/ciso-security-review-checklist-connecting-llms-to-workday)

## 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.
