AI workforce on monday service

Who can use this feature
gray-cloud.svgAvailable on monday service

AI workforce is part of service AI in monday service. It lets you build AI teams that can answer requests, route conversations to the right AI agent, and hand them over to a human expert when needed.

In this article, you’ll learn how to create an AI workforce team, configure agents, connect channels and portals, test the experience, and monitor performance.

 

Note: service AI is currently in gradual release. To request early access, fill out this form.

 

What is AI workforce?

AI workforce is the area where you create and manage service AI teams across your organization.

Instead of relying on a single general agent, service AI uses multiple specialized agent teams. Each agent is set up for a specific type of request, such as benefits, payroll, onboarding, or IT support. This helps improve routing accuracy and makes the setup easier to maintain over time.

When a request comes in, the Service AI Supervisor reviews the request and routes it to the most relevant AI agent based on that agent’s configured scope. If AI cannot confidently handle the request, the conversation is routed to a human expert.

Keep reading for the steps to configure the workforce.

 

Open AI workforce

1Open monday service.

2Click the Service AI icon on the left side of the screen.

 

From there, you can access AI workforce, the Service AI Supervisor, Test, AI workforce performance, Channels, Portals, and Incoming requests.

 

Create an AI workforce team

Start by creating a team. Open Service AI workforce and click New team:

 

Choose the team type that best fits the requests you want the team to handle, enter a team name, and create the team:

 

When you create a team, monday service also creates a workspace for it. You can change the connected workspace if needed.

 

Set up your workforce team

After you create a team, you land on the team page. This page shows the team type, the connected workspace, the incoming request channels, and team-level metrics such as Team requests and Autonomy rate. Autonomy rate is the percentage of involved requests that the team's AI agents resolved without routing them to a human.

 

Further down the page, you will see Your team's agents. If you choose one of the suggested department types when creating the team, monday service automatically creates preset agents for that department. For example, an HR team may include agents such as Benefits, People Operations, and Payroll & Compensation. You can open these preset agents, update their scope, add knowledge, and activate them. You can also create completely new agents from the New agent card.

Tip: Human agents can use AI Co-pilot and other AI capabilities in monday service while working tickets, including Sidekick and AI-powered columns on your Tickets board. For more details, see Using AI in monday service.

 

Configure an agent

Each agent has its own setup panel with five tabs: Activity, Profile, Knowledge, Playbook & Skills, and Test. You can also activate or deactivate, or delete the agent from the top of the panel. An agent must be active in order to answer requests. To active an agent, it must have both scope and knowledge. 

 

In the Profile tab, define the agent's mission and scope, tone of voice (natural, professional, or friendly), and answer length. The Mission & Scope field is the main thing that affects routing. The Service AI Supervisor uses it to decide which requests should be routed to that AI agent. It does not use the knowledge base to make that routing decision, so your scope should be as specific as possible.

 

A narrow scope like vacation requests, PTO, and leave policies is more reliable than a broad scope like HR questions. In the same way, hardware, software, and connectivity requests is more useful than IT stuff. Be careful not to include capabilities your team does not actually support. For example, if you do not use device-management tools, avoid promising asset or device-management help in the agent's scope.

In the Activity tab, once the agent is up and running, you'll be able to review the agent's involved requests, resolved requests, autonomy rate, and activity feed:

 

In the Knowledge tab, add the information the agent uses to answer requests. Use Reference Knowledge for content you want requesters to see, such as policies, FAQs, and help guides. When the agent answers using reference knowledge, it can cite the source and include a link to the doc. Use Background Context for internal instructions the agent should follow without sharing them with the requester, such as team-specific policies. 

 

A good rule of thumb is simple: reference knowledge is the evidence the agent shows, and background context is the internal guidance the agent uses behind the scenes.

Note: Agents currently use monday docs and public single web pages as knowledge sources. They do not use board data as a knowledge source, cannot access pages that require login, and do not use embedded board or widget content inside docs as agent knowledge. When you add a public web page, the content is imported at that point in time, so later changes to the original page are not synced automatically. A good setup pattern is to start with one or two strong docs per agent, test with sample questions, and then add more knowledge for topics that still route to a human.

 

In the Playbook & Skills tab, review the built-in playbooks that shape agent behavior. If you need to add extra instructions today, use Background Context as a workaround for simple playbook-like behavior. In the future, you will also be able to add new playbooks.

 

In the Test tab, review generated sample requests based on the agent's scope, knowledge, and skills. This helps you understand whether the agent is likely to resolve the request, partially cover it, or route it to a human.

 

Use the Service AI Supervisor

The Service AI Supervisor helps you understand how requests are matched and routed across your workforce teams.

When a request comes in, the supervisor recognizes the request intent and checks whether there is a matching AI agent based on that agent’s configured scope. If the supervisor finds a match, the conversation is assigned to that AI agent. If no matching AI agent is found, the outcome depends on the channel. In portal chat (we'll cover it later in this section), the supervisor can first try to help using the portal’s resources before routing the request to a human expert. In other channels, the request is routed directly to a human.

 

Before an AI agent answers, the system checks whether the agent has enough knowledge coverage for the request. If knowledge coverage is too low, the request is routed to a human instead of being answered by AI.

Note: AI agents do not hand conversations off to other AI agents. If a conversation goes beyond the assigned agent's scope, if the request does not have enough knowledge coverage, or if the requester asks for a human, the conversation is routed to a human expert.

 

You can review this logic directly in the Service AI Supervisor page. The Activity tab helps you track how requests are being matched by showing matched requests, unmatched requests, match rate, and recent supervisor actions, and you can filter the view by workforce team:

 

The Routing tab helps you see how the supervisor is connected to your workforce teams and how requests are routed across them:

 

Connect channels

The Channels page brings all your channels into one place so you can manage how requests enter your service workflows.

From this page, you can add a new channel, search existing channels, and filter the list to find the setup you need. Each channel card shows whether the channel is connected, the email address or channel name, which Tickets board it creates tickets in, and which workspace it belongs to.

 

Each channel is connected to a Tickets board and linked to a workspace. Once a channel is connected to a board inside the team's workspace, the AI workforce team can work on requests from that channel, including email channels. If there is no matching AI agent, the request is routed to a human.

Note: If you need the same AI setup across boards in different workspaces, you currently need to recreate the team in each relevant workspace.

 

Who can edit channels

On the Channels tab, anyone can view existing channel connections and create a new connection, whether the workspace is open or closed. However, only the team member who created a connection can edit that specific connection.

This means workspace type does not affect who can view or create channel connections. Editing permissions stay with the original creator of each connection.

 

Manage portals

The Portals page brings all your portals into one place.

 

If your account has one portal, this page shows that portal:

 

If you are on the Enterprise plan and use multiple portals, this page shows your main portal as well as your additional portals. To create another portal in a multi-portal setup, click Create portal.

From the Portals page, you can open a portal in two ways:

  • Click the portal itself to open its settings.
  • Click the three-dot menu, then choose Edit portal to open settings or Go to portal to open the live portal.

 

In the portal settings, you can manage areas such as Customize, Content, AI Chat, Access, and Users.

 

Who can edit portals

On the Portals tab, permissions depend on whether you are working with the main portal or a workspace portal.

For the main portal, anyone can view and edit the Customize, Content, and AI chat tabs. Only account admins can edit the Access and Users tabs.

For workspace portals, permissions depend on the workspace type, whether the portal is open or private, and whether the person is a workspace member or not.

If someone is a workspace member, an open portal can be seen by anyone, and anyone can access its settings. A private portal can only be seen by portal subscribers and admins, and only they can access its settings.

If someone is not a workspace member in a Closed workspace, both open and private portals can only be seen by portal subscribers and admins, and only they can access portal settings.

 

Set up AI chat in your portal

Once you're in the portal settings, open the AI Chat tab.

In this tab, connect AI chat to a Tickets board. This step is required because tickets created through AI chat are added to the selected board, and that board connects the portal experience to the AI workforce team.

 

Once AI chat is connected, requesters can open the portal, type a question, and click Get assistance from AI:

 

As soon as the conversation starts, a ticket is created in the connected Tickets board. The Service AI Supervisor then reviews the request and checks whether there is a matching AI agent for that request type. If there is, the request is routed to that agent. If the agent has enough knowledge coverage, it responds in the portal. If it cannot handle the request, the conversation is routed to a human expert.

 

If no matching agent is found in portal chat, the supervisor can first try to help using the portal’s available resources before routing the request to a human. In that case, the supervisor uses the portal resource titles and descriptions, not the full content of those resources.

Note: AI chat can currently be connected to one Tickets board per portal. The selected board must belong to the same workspace as the connected AI workforce team. If the dropdown is empty or shows limited options, check that you have access to the relevant board and the permissions needed to manage the portal setup.

 

When a request is created through portal AI chat, it appears in the connected Tickets board.

The board includes a dedicated AI Status column that tracks where the request is in the AI flow. The current AI status values are In progress, Pending customer response, AI resolved, and Routed to human.

 

The AI Status column and your regular workflow Status column are separate. AI Status is system-set and cannot be edited manually. Your regular Status column controls your board workflow and automations.

Note: If you want requesters to see AI progress in the portal, create an automation that maps AI Status values to your main Status column. Otherwise, the requester may continue to see the ticket as open in the portal until the regular Status column is updated.

 

When AI resolves a request

A request is marked as AI resolved only after the system determines that AI handled it successfully without routing it to a human. This is not decided immediately.

The system waits 24 hours after the last AI response in portal conversations and 72 hours after the last AI response in email conversations before marking the request as resolved.

After a ticket is marked AI resolved, any new requester reply routes the ticket to a human expert. This applies in both portal and email. The AI Status changes to Routed to human, and you can use automations so your regular workflow status reflects that return as well.

What counts as AI resolved?

A request is considered AI resolved only when the conversation stayed with AI, the interaction was meaningful, the requester explicitly confirmed success or implicitly accepted the answer, and there were no negative signals such as dissatisfaction, looping behavior, vague deflection, or abandonment during troubleshooting.

 

Test the full workforce flow

The Test page in the left menu lets you simulate the requester experience for an entire workforce team.

Choose a workforce and start a test conversation to see how the supervisor routes the request and how the flow behaves end to end. Currently, you can test this flow through portal AI chat, while additional test channels are coming in the future.

Each test is saved as its own conversation, so you can return to previous tests, compare outcomes, and continue reviewing them over time. You can also create new tests and delete tests you no longer need.

This is different from the Test tab inside a single agent. The full Test page is designed for workforce-level testing, while the Test tab inside an agent is designed for agent-level testing.

 

Review AI workforce performance

The AI workforce performance page helps you monitor how your AI teams are performing over time.

This page includes AI Resolved tickets, AI Involvement rate, AI Resolution rate, and a performance funnel that shows total conversations, AI involvement, no match, AI resolved, and routed to human.

 

Use this page to understand how often AI is involved, how often it resolves requests successfully, and how often requests still need a human handoff.

 

Open the connected Tickets board quickly

The Incoming requests link at the bottom of the Service AI menu gives you a shortcut to the connected Tickets board.

 

You can use it to jump directly into the board where incoming AI-supported requests are being created and managed.

 

If you have any questions, please reach out to our team right here. We’re available 24/7 and happy to help.

Last modified on

Still have questions?
We can help.

Chat support

Get in touch with our support team through our chat for any questions, concerns, or inquiries.

Community forum

Learn, share ideas and connect with other monday.com customers.

Expert help

Hire a monday.com expert to optimize your workflows.

Is this article helpful?
Help us improve our articles.