Who can use this feature

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

This article introduces AI agents on monday.com: what they are, what they can do, and where to go to build, run, and troubleshoot them.

What are AI agents?

AI agents are built inside 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, all directly inside your boards and workflows.

Unlike rule-based automations, agents can analyze information, apply judgment based on your defined priorities, and take the next best action, all within the boundaries you set. Agents operate within your permissions and guardrails, so you stay in control of what they do, where they act, and how they communicate.

AI agents include:

• Expert Agents - Pre-defined agents designed for common end-to-end use cases. These include the CRM AI Lead Agent and the CRM Sales Agent.
• AI agent builder - A flexible builder that allows you to create custom agents tailored to your workflows.

What can agents do?

Custom agents built with the AI agent builder can:

• Understand context - Use your boards, data, docs, workflows, and permissions to analyze and connect signals. Agents can also understand external context by connecting external files with specific knowledge.
• Make decisions - Apply rules, priorities, tone, and thresholds you define to triage, route, escalate, and prioritize work.
• Take action - Create and update items, assign owners, change statuses, draft messages, log outcomes, and execute follow-ups.
• Operate within governance controls - Act only where permissions allow and within defined access boundaries.
• Run based on triggers - Execute when specific events occur, at defined times, or on an ongoing cadence. Agents will keep working even when you are asleep, taking care of your work for you even when you are unavailable to do it yourself.

Agents can support work such as capturing and triaging incoming requests, researching and summarizing information, routing tasks to the right owner, drafting follow-ups, maintaining records, and coordinating work across teams.

Billing and credit consumption

Credit consumption depends on the complexity and depth of each task your agent performs. For full details, see the AI Models and Credits: understanding and optimizing consumption article.

Build your agent

You can build a custom agent using the AI agent builder. From the AI Agents tab in the left navigation pane, click + New agents to describe your ideal agent in plain text, choose a pre-defined starting prompt, or start from blank. You can also use pre-built templates from Agents made for you, personalized for your role and boards.

You can pause your agent at any time to stop it from running, and take it live again from the This agent is paused message at the top of the Agent builder.

Once your agent is created, you can customize it through the Agent builder. The agent chat on the left side panel walks you through the entire building experience, suggesting improvements, adding context, and helping you test the agent. Every configuration action includes an Undo option so you can revert changes safely.

Your agent's configuration lives across four tabs. The Brain tab is where you set the agent's instructions, grant access to boards and files, connect tools, add skills, and choose the AI model. The Jobs tab lets you break your agent's work into focused tasks, each with its own trigger and instructions. The Channels tab lets your agent communicate with people in external apps like WhatsApp and Telegram. The Activity tab is where you monitor every run.

For the full step-by-step guide to creating and configuring your agent, see the Build and configure your AI agent article.

Run and manage your agent

Once your agent is live, you can interact with it directly from boards and monday docs, monitor its runs, and manage its memory. You can share your agent with other members so they can interact with it directly, or duplicate any agent you own or have access to.

Your agent can also join live meetings alongside AI Notetaker. 

For everything you need to know about using, monitoring, sharing, and governing your agent, see the Run and manage your AI agents article.

Troubleshooting

Agents continuously evaluate and act based on the provided instructions. If your agent behaves unexpectedly, does not run when you expect it to, or produces results that need refining, you can investigate directly in the product by reviewing its configuration in the Brain tab and each run in the Activity tab.

For the full troubleshooting guide, including common issues and step-by-step fixes, see the Troubleshooting AI agents article.

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.
• Creators control where agents can act (specific boards, spaces, teams) and what the agent is allowed to do within a specific scope.
• 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.
• 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.

How are AI agents different from automations, monday sidekick, and Agent Factory?

AI agents vs. automations

Automations follow predefined "if this, then that" logic.

AI agents go further by generating content, evaluating context, and choosing actions dynamically, while still operating inside the structure and guardrails you define. This allows agents to handle more complex scenarios, ambiguity, and decision-making across multiple steps.

AI agents vs. monday sidekick

monday sidekick is designed for conversational support and on-demand assistance.

AI agents are built for execution inside monday.com. They run processes end to end at scale, monitor activity continuously, and take action based on triggers and defined workflows.

AI agents can run anytime, whether you are working or not. They can work even as you sleep, so you can maximize your workflow even when you're not actively working yourself.

AI agent builder vs. Agent Factory

AI agents are a capability built directly into monday.com.

Agent Factory is a standalone product outside of monday.com designed for independent agent creation.

Other resources

Agent templates

Use the AI Agent template center to jump start the agent building process by starting out with conveniently pre-made agent templates.

Agents in mobile

You can also use your agent on the go. For more information, check out the Get started with the AI agents app article.

FAQs

Do I need admin permissions to create or manage agents?

Yes. Admin permissions are required to create or manage AI agents.

Can I pause my agent?

Yes. You can pause your agent at any time. In a Paused state, you can continue building and editing, but the agent cannot run. To resume, take your agent live again.

Can agents work together in one flow?

Yes. With AI workflows, multiple agents can operate in a single flow, each handling a different stage of execution.

How are agents different from automations?

Automations follow fixed rules. Agents evaluate context, generate content, and choose actions dynamically within defined guardrails.

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.