---
title: "Stop or audit a Workday AI agent — Kiweely"
description: "Deactivate a Workday agent, including Production copies that refresh back into Sandbox, and review View AI Agent User Audit Trail and skill security."
url: https://kiweely.com/guides/stop-audit-workday-ai-agent-admin-runbook
---

# 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.

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

Stopping a Workday-built agent is a per-tenant action in **Agent Management Hub**. Deactivate hides the agent from users and leaves it in the hub so you can activate it later. For Deployment Agent, Workday also says Flex Credit consumption stops in that tenant. If you configured the agent in Production so Sandbox refreshes keep the setup, you must deactivate Production too. Otherwise the next refresh turns the Sandbox agent back on.

You need **Manage: Agents** and **Setup: Agents** to deactivate Deployment Agent. Those domains are part of Agent System of Record. **View AI Agent User Audit Trail** is the report the ASOR setup topic names under **Reports: AI Agent Security**.

This runbook is the operational sequence. It does not invent a kill switch beyond deactivate, skill and tool configuration, and security activation.

## Decide what “stop” means

| Goal | Do this | What remains |
| --- | --- | --- |
| Nobody can chat with Deployment Agent in this tenant |  **Deactivate Agent** on that tenant’s registry row | The agent stays in the hub. Chat history already stored follows the 14-day retention. Histories are per tenant. |
| Stop Flex Credits for Deployment Agent everywhere | Deactivate every tenant you configured, including Production if it exists only for refresh | A later activation starts a new period of use. |
| Stop one Self-Service action, keep the agent | Configure tools on that skill. Some tools cannot be disabled. The Enabled toggle is unavailable for those. | The skill’s other tools still run. Skill-level billing for tools you leave enabled does not drop just because you disabled one tool. |
| Stop a population from using a skill | Remove that security group from **Available To** | Other groups on the skill still can. Users need a new conversation before tool changes apply. The skills topic says skill and tool changes can take up to 10 minutes because of caching. The configure-tools topic says up to 5 minutes for new conversations, and an open conversation might not change until a new one starts. Plan on the longer window. |
| See what it already did |  **View AI Agent User Audit Trail** | Deactivate does not delete the report. |

Disabling a tool does not make the agent read your sentence verbatim. You can set a **Tool Disabled Message**, a **Supplemental Message**, or a **Fallback Message**. The agent uses that text to write its own reply. The configure-tools topic’s example: you disable a bonus-history tool and write that people should use the Bonus Management Portal, including a link. The user sees a generated reply based on that message, not the message itself.

## Deactivate Deployment Agent

1.  Confirm you are in the tenant you mean to stop. Production and Sandbox are different stops.
2.  Open **Agent Management Hub**.
3.  Open **Agent Registry**.
4.  Open **Deployment Agent**.
5.  Choose **Deactivate Agent**.
6.  Confirm if prompted.

Result, in Workday’s words: the ASOR-enabled Deployment Agent is no longer available in that tenant, and Flex Credit consumption stops there.

Repeat for each tenant in the table. Customer Central is its own tenant. A connected Implementation tenant is another.

| Tenant | Why it might still be on | Stop action |
| --- | --- | --- |
| Implementation | You tested setup here | Deactivate here |
| Preview | Separate ASOR configuration | Deactivate here |
| Sandbox | Active for implementers | Deactivate here |
| Production | Configured so refresh copies the agent into Sandbox. Not usable as Production chat, but still a configuration that reactivates Sandbox | Deactivate here or the next refresh undoes the Sandbox stop |
| Customer Central | Separate setup | Deactivate here if it was registered |

Write down the comment or the change ticket, the tenant, and who confirmed. The hub keeps the agent for a later activation. “Removed” is the wrong status word.

## Audit after the stop

ASOR permissions for the audit report are **View** and **Modify** on **Reports: AI Agent Security** for an unconstrained group, plus the domain enabled in the System functional area. If the report is missing, fix that security before you conclude there is no history. The setup topic’s example report is **View AI Agent User Audit Trail**.

While you are in the registry, open the agent profile if your process includes the passport and stamps. A related walkthrough of passport stamps and the audit trail is in the Agent Passport guide. This runbook only depends on the tasks the admin guide names.

For “what could it still do if we turn it back on,” run **View Security for Agent Skill**. You need **Manage: Agents**. The report prompts are **Registered Agent** and **Agent Skills**.

| Functional status | Meaning | What you do before any reactivation |
| --- | --- | --- |
| Full Match | The **Available To** group has all required policies for the tool. | Accept only if that group should have the tool. |
| Review Required | The group has some required policies, not all. | Review the group before you activate. |
| Config Required | A required policy has no security groups. | Configure those policies first. Workday says to prioritize these. |
| Not Evaluated |  **Available To** is empty, so there is no group to test. | Do not treat an empty skill as “safe and ready.” It is unevaluated. |

**Required Permissions** are View or Modify. **Recommended Security Policies** and **Assigned Security Group** show how the tool is supposed to be reached. **Additional Security (Optional)** is field-level access that is not required for the tool to run. **Test My Setup** checks a security group and shows other policy paths. It needs **Security Administration**.

Clear **Config Required** rows before you activate again. Then **Test My Setup** for a real user in each **Available To** group.

## Self-Service Agent: narrow it before you deactivate it

Deactivate is the full stop. If the problem is one action:

1.  Open **Agent Management Hub**, **Agent Registry**, **Self-Service Agent**.
2.  Configure the skill’s tools.
3.  Turn off only the tools whose Enabled control is available.
4.  Set a disabled message, and a fallback message for failures.
5.  Wait out the caching window and start a new conversation as a test user.
6.  If the skill itself should not exist for that population, clear **Available To** rather than hoping a disabled tool covers every action in the skill.

The Guide skill has to stay on for Self-Service Agent to operate. Turning off Guide is not a partial stop. It stops the agent from running. Policy Intelligence no longer requires the Workday Help SKU, so do not assume that skill is absent because you did not buy Help.

Runtime still checks the person’s access to the agent and their access to the tools’ domain or business process policies. Removing someone from **Available To** does not remove them from a domain. Do both if the domain was opened only for the experiment.

## Reactivate only with a written reason

Activation is the same hub. Workday isolates Deployment Agent chat histories by tenant and deletes them after 14 days, so a thread from before the stop may already be gone. Reactivating does not restore that chat. It does make the agent available to the **Available To** groups again, and for Deployment Agent it is again a tenant that can consume Flex Credits until you deactivate it.

If Production was reactivated “for the next Sandbox refresh,” say that in the ticket. Otherwise the next incident will look like Sandbox turned itself back on.

## Frequently asked questions

### Does deactivate delete the agent?

No. The deactivate topic says Workday hides it from users and keeps it in Agent Management Hub for a later activation.

### Will a Sandbox refresh turn it off?

A refresh copies configuration from the tenant you refresh from. If Production still has the agent active, Sandbox comes back active. Deactivate Production when the goal is a full stop.

### Is the audit trail the same as thumbs up and thumbs down?

No. Thumbs rate a Deployment Agent or Self-Service answer. **View AI Agent User Audit Trail** is the security report named on the ASOR setup topic. Use the report for “what ran.” Use thumbs for “the guidance was wrong.”

### Can I disable a single tool for one security group?

No. The configure-tools topic says you cannot assign tools to specific security groups. Tools inherit the skill’s groups. To split populations, use separate **Available To** lists at the skill level, or do not enable the skill for that group.

## Sources checked

Frontmatter pages, fetched 2026-11-16.

## Sources checked

-   [Deactivate the Deployment Agent in the Agent Management Hub](https://doc.workday.com/admin-guide/en-us/workday-ai/agents/workday-built-agents/deployment-agent-in-implementation-environments-an/deactivate-the-deployment-agent-in-the-agent-manag.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)
-   [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 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)
-   [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)

-   [### 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)
-   [### 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)
-   [### What Is Workday Agent Passport and How Do Admins Audit or Stop an AI Agent? Workday Agent Passport shows verified security stamps, assessors, and grant dates on each agent profile in Agent Management Hub. To audit or stop an AI agent, inspect View AI Agent User Audit Trail and click Deactivate Agent or disable its Agent System User OAuth 2.0 client.](https://kiweely.com/guides/workday-agent-passport-governance-explained)
-   [### 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)

-   [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)
-   [Is there an AI agent that can do Workday configuration, business processes and security changes in a tenant for me?](https://kiweely.com/guides/ai-agent-for-workday-configuration-business-process-security)
-   [Our Workday consulting firm wants an AI tool that does tenant work for our consultants: what are the options and costs?](https://kiweely.com/guides/ai-tools-for-workday-consulting-firms-options-costs)

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

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

-   [Insurance and MSA Language for AI Agents That Touch Workday](https://kiweely.com/blog/insurance-msa-language-ai-agents-workday)
-   [Load and Concurrency: When AI UI Agents Are the Wrong Tool for Workday](https://kiweely.com/blog/when-ai-ui-agents-wrong-tool-workday-load-concurrency)
-   [Migrating a Workday Extend App from Hand-Edited JSON to an Agent-Maintained Repo](https://kiweely.com/blog/migrate-extend-app-to-agent-maintained-repo)

## 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.
