[ monday.com / WorkOS ]

AI agents for monday.com, across every board

monday.com recipes are single rules: when this, do that. engini lets an AI agent read what came in, decide what it means, and act on several boards and systems at once: move the item, create subitems, assign the team, attach the file, post the update, tell Slack. Teams can also ask Claude or ChatGPT to make changes on boards in plain words.

monday.comOutlook or GmailSlackGoogle DriveClaude
Read the monday.com guide →
A client email changes the plan
  1. Client emails a scope change"add two locations, launch moves to May"
  2. Agent reads and decidesproject: Northwind rollout
  3. monday.com logo
    Board changeddate updated; 2 subitems added; team assigned
  4. monday.com logo
    Update postedsummary and the email on the item
  5. Slack logo
    Team told#northwind with what changed
Illustration of the flow on this page, not a product screen.
What it does
Agents that read, decide and act across boards and other systems
Systems
monday.com, Outlook or Gmail, Slack or Teams, Google Drive, your CRM and ERP
Built with
Workflows on monday triggers with an AI agent step; MCP for chat
Your control
Which boards and tools each agent may use
[ 01 / The problem ]

Recipes are rules. Most work needs judgment.

monday.com automations are a great fit for simple rules: when status changes, notify someone. They are a poor fit for the work that fills a project manager’s day, which starts with something unstructured: an email, a form answer, a file. Someone has to read it, decide which project it belongs to, and then make five changes across two or three boards. Recipes also have usage limits by plan, as monday’s own support pages explain.

What recipes cannot do

  • Read an email or a document and decide what it means.
  • Find the right item across boards when nobody gave you its id.
  • Make several related changes in one go: dates, subitems, owners, files.
  • Act in the systems around monday.com, such as your CRM, ERP or Drive.

What an engini agent adds

engini triggers on monday.com changes: items and subitems created, updated or deleted, and updates created or edited. It can also start from an email, a schedule or another system. An AI agent step reads the input, finds the right items, and acts: moves items, creates subitems, assigns users and teams, uploads files, writes column values and posts updates, plus whatever needs to happen in Slack, Drive, your CRM or ERP.

For everyday questions and edits, teams add an engini MCP server to Claude or ChatGPT and ask in plain words: "what is late on the Northwind board", "move these three items to next sprint". The server exposes only the boards’ tools you choose, and every call is recorded.

[ 02 / How it works ]

Read, decide, act everywhere it matters

01 / Start

Any signal

A monday.com change, an email, a schedule or a change in another system starts the workflow.

02 / Decide

An AI agent step

The agent reads the input with your instructions and decides what it means and which items it touches.

03 / Act

Across boards

It moves items, creates subitems, assigns users and teams, uploads files, sets columns and posts updates.

04 / Extend

Beyond monday.com

The same workflow updates Slack, Drive, your CRM or ERP. For chat, teams use Claude or ChatGPT through an engini MCP server.

[ 03 / What the agent reads and writes ]

What the agent reads and writes

SystemRecordsAccess
monday.comBoards, items, subitems, column values, updatesReadCreateUpdate
monday.comFiles, users and teams, connect-board columnsReadUpdate
Outlook or GmailIncoming requestsRead
Slack, Teams or Google DriveNotifications and documentsWrite
[ 04 / Build it with the engini skill ]

Describe it in plain words. The engini skill builds the workflow.

engini skills is engini’s plugin for Claude Code and Codex. Its workflow agent, Flo, turns a plain-language request into an engini workflow: it designs the steps, dry-runs them against your own engini account, shows you a proposal, and creates the workflow only after you approve it, always turned off. You check it in the engini designer and turn it on.

Blurred landscape photo with the monday.com logo, the engini mark and a frosted tile joined by a thin line, labeled across boards: email, decide, updates

Editorial image: one signal, several boards.

Claude Code: install once
/plugin marketplace add engini/skills
/plugin install skills@engini
Then ask for this solution
Build a workflow in my engini account: when an email arrives in pm@ in Outlook, use an AI agent to find the matching project on my monday.com "Projects" board by client name, post the email as an update on that item, and if the email asks for a date change or new work, create a subitem describing it and assign it to the item's owner.
  1. You need an engini account, the engini CLI (npm i -g @engini/cli) and a workspace-scoped API key, ideally a dedicated least-privilege one.
  2. Connect the systems this flow uses in engini first. Flo never creates or changes a connection and never handles your key; it tells you which command to run.
  3. Flo checks your login and workspace, searches the tool catalog, compiles the plan and shows a proposal table with every step. It creates the workflow only when you approve that proposal, and it creates it turned off.
  4. Open it in the engini designer, fill anything it left for you, and turn it on.
engini skills for Claude Code and Codex →
What the skill will never do on its own →
[ 05 / Agent Policy ]

The agent does only what you allow. Every run is on the record.

Agent Policy is how you govern agents in engini: the tools each agent may call, the account each tool uses, and a record of every call.

Toolsets

Scope every call

Hand the agent a toolset: only the tools it needs, each on the connection you choose, for example read only. engini enforces it on the server for CLI, SDK and REST API calls; a call outside the toolset is refused. An MCP server exposes only the connections and tools chosen when you set it up.

Identity

Acts with the account you connect

engini acts with the permissions of the connected account. Connect a person’s own account and it acts as that person; use a shared integration account and it acts as that account. Every run is recorded under the user who triggered it.

Audit

History and audit log

Each tool call and workflow run is recorded in History and the audit log, which supports export and streaming to your SIEM. Your agent never needs your credentials: engini stores them and adds them when it runs each call.

SOC 2 Type IIISO 27001GDPRHIPAA compliant
[ 06 / Try it now ]

Build it on your own data today

Start free, connect monday.com, and build this flow with the engini skill, in Workflow Studio, or from your own agent.

  • 01Workflow Studio. Build the flow on a visual canvas, with an AI agent step where judgment is needed. Start free →
  • 02Your own agent. Give Claude, ChatGPT or Cursor an engini MCP server with only these tools. MCP client setup →
  • 03The engini skill. Ask Flo in Claude Code or Codex and review its proposal. Install the skill →
[ 07 / Questions ]

Questions buyers ask before they start

Can an AI agent work across several monday.com boards?

Yes. An engini workflow with an AI agent step can read and change items on any board the connection can reach, in one run.

Can Claude or ChatGPT update monday.com items?

Yes, through an engini MCP server that exposes only the monday.com tools you choose. People sign in through engini and ask in plain words.

What can start an agent?

Items and subitems created, updated or deleted, updates created or edited, an email, a schedule, a webhook or a change in another connected system.

Does it replace monday.com automations?

No. Keep recipes for simple rules. Use engini where the work needs reading, judgment, several boards or other systems.

How is this different from monday AI and monday agents?

monday’s AI works inside monday.com. engini agents work across monday.com and your inbox, CRM, ERP and chat tools under one set of controls, and you can use the assistants your teams already have.