Who can use this feature

Available on monday AI platform, availability on all products coming soon

AI agents are built into monday.com and act within the context of your work. They monitor activity, make decisions based on your defined rules and priorities, and execute tasks end to end on your boards and workflows.

Once your agent is up and running, this article walks you through how to use it on boards and in docs, monitor its activity, manage its memory, share it with your team, and stay in control through governance settings.

For a full overview of AI agents and how to build them, see the AI Agents on monday.com article.

Using your agent on a board

Once your agent is active, there are several ways to interact with it directly from a board:

• Assign the agent to items to trigger it.
   
• Open an existing agent for editing, or create a new agent from the agent button at the top-right pane:
  
   
• Use monday Sidekick to interact with and improve the agent.
   
• View the agent's actions and undo them from the activity log:
  
   
• Follow your agent's activity on the board in real time. While the agent works on your board, you can see it happen live, with the agent's avatar moving between cells like a collaborator. To enable this, turn on the Live agent mode toggle in the Agents button at the top right of your board:
  

Using your agent in a monday doc

Your agent can also work inside a monday doc. It can:

• Pull context or reference information from the doc when generating status updates
• Use the doc as a knowledge base for project standards or guidelines
• Include relevant sections in the agent's reports
• Write to the doc (like adding status updates directly to it) by updating its permissions to read-write

Monitoring your agent's activity

Your agent is active as soon as it's created; there is no manual activation step. Once the triggers and rules you configured are met, your agent will run.

In the Activity tab, you can see all of the runs your agent has completed, all in one place. You can monitor the status of each run and stay on top of what may require your attention. You can see the date of the run, which apps it used, and how many AI credits were consumed, if any.

Click on a particular run to view more details of what has been done or what else needs to be added in order for the agent to complete the work:

If a run fails, you will receive a bell notification, even if you are not viewing the agent at the time. When you open a failed or partial run, a What Went Wrong panel shows what happened, why, and a suggested fix. The run summary also includes details about what the agent was attempting when a tool failed, providing context beyond a simple failure message.

Agent memory

Agents retain memory across runs and can reference past work and outputs, persisting across conversations. Your agent can remember facts about you, such as your preferences and working style, as well as behavioral rules you set, like "always ask before sending an email".

You can access the agent's memory by clicking on Manage memory located in the top right three-button menu of the Agent builder. The memory functionality can also be fully switched off if you prefer a fresh start each session.

You can also ask your agent to remember or forget anything at any time.

Artifacts

The Artifacts tab centralizes everything your agent has produced, including images, HTML outputs, monday docs, and monday boards. All outputs are stored as named, searchable artifacts accessible across conversations.

Meetings

Your agent can join live meetings alongside AI Notetaker. The agent listens to the conversation in real time and can be interacted with through the meeting chat, giving you access to the same tools and data it uses outside of meetings. For setup and privacy details, see the monday.com AI Notetaker article.

Duplicating an agent

You can duplicate any agent you own or any shared agent you have access to. To duplicate, open the three-dot menu at the top right of the Agent builder (next to Share) and select Duplicate.

If you own the agent, the duplicate includes all connected resources. If you are a member with access to a shared agent, the duplicate is created without private resources or credentials. You become the owner of the duplicate and can reconnect your own resources as needed.

Sharing your agent

Once your agent is created, you can share it with other members so they can interact with it directly, without needing to build or configure anything themselves.

To share your agent, click the Share button at the top right of the Agent builder. Search for and select the members you'd like to invite, and they will be added to the agent.

Shared members can trigger the agent, chat with it, and view its settings in the Brain tab. They cannot edit the agent's instructions, tools, permissions, or any other configuration.

Admins control which roles can share agents through the AI permissions page, under AI governance in the Administration section. Open User agents to see the Share user agents permission, where you can select which account roles are allowed to share agents with other members.

How sharing works

When you share an agent, it retains its existing context and permissions. Shared members interact with the agent using the full context it already has access to, if they have the same access.

• The owner grants context and permissions to the agent during setup.
• When the agent is shared, authorized members can invoke it with that full context.
• If the agent has access to private boards or docs, a Review private content step appears during the sharing flow. This step lists all private content the agent has access to. By clicking Share agent, you grant the invited members access to that content.
  

Sharing an agent with tools connected

If an agent uses tools such as Slack or Gmail linked to your own account, each tool includes an Allow people you share this agent with to use this account toggle. Turn this on for a tool to let shared members trigger it using your connection.

• If a personal tool doesn't have this toggle turned on, sharing the agent is blocked until you either enable it or remove the tool.
  
• If you add a personal tool to an agent that's already shared, the same toggle applies. It needs to be turned on for the new tool to work for shared members as well.

Control, permissions, and governance

AI agents are designed with enterprise-grade controls in mind. This ensures agents operate predictably and in alignment with your organization's structure and policies.

• Agents only access what you are allowed to access. You can narrow this access to the minimum that's necessary for the agent to run. For example, you can grant the agent permission to read only particular boards, or the same viewing permissions as a particular member is allowed to see.
• Creators control where agents can act (specific boards, spaces, teams). Creators are also able to decide what the agent is allowed to do within a specific scope. For example, the agent can only view a particular board, or can edit only a specific board.
• You can review a transparent log of actions and reasoning in the Activity tab.
• Agents can be paused at any time. In a Paused state, you can continue building and editing your agent, but it cannot run. To resume, take your agent live again.
• Agent owners can assign editors and viewers, but currently, ownership cannot be transferred.

To learn more about agent governance, see the AI permissions and governance article.

FAQs

How does credit consumption work when I share my agent with other members?

AI credits are consumed from your account's shared credit pool. When members you've invited through the Share button chat with, trigger, or mention your agent, the credit consumption is attributed to the agent owner. This applies whether the agent is shared or not. Consumption is always tracked on behalf of the agent owner. Admins can monitor all credit usage from the AI governance section in the Administration section.

Can agents edit columns with restricted edit permissions?

Yes. An agent can edit a restricted column in two ways: by setting the agent as the board's owner, which grants access to all restricted columns on that board, or by assigning the agent to a specific column through the column's settings under permissions. If the agent is not granted access through either method, it cannot edit the restricted column.

Can I duplicate a shared agent?

Yes. You can duplicate any agent you own or any shared agent you have access to. If you own the agent, the duplicate includes all connected resources. If you are a member with access to a shared agent, the duplicate is created without private resources or credentials. You become the owner of the duplicate and can reconnect your own resources as needed.