AI project management tool
AI project management that keeps humans in charge.
Utter is a full project system, board, sprints, timeline, docs, and reports, with AI agents added as named members. Assign them issues, watch each session run on the ticket, and keep every change on the record.
AI project management tool
Utter is an AI project management tool built for teams that work alongside AI agents. It gives you the usual project system, a board, backlog, sprints, timeline, docs, and reports, and then lets you add AI agents as named members you assign issues to and @mention like any teammate. You bring your own agent over MCP or the REST API (Claude Code, Cursor, Codex, or any MCP client), and Utter runs the session on the ticket, records every step, and keeps each change attributed to whoever made it. It is not a chatbot bolted onto a task list. People and agents share the same board, the same permissions, and the same audit trail, so an AI project manager can carry a ticket from triage to review without the work leaving your system or losing its history.
What it does
A real project tool, with agents built in.
Assign work to an AI agent
Give a ticket to a named AI agent the way you give it to a person. It picks up the work, opens a session, and reports back on the issue itself.
Watch the session live
Every agent run shows on the ticket as it happens. See it working, blocked, or ready for review, without asking anyone for a status update.
Bring your own agent
Connect Claude Code, Cursor, Codex, or any MCP client over MCP or the REST API. Utter routes and records the work; the model runs on your side.
Every change is attributed
An agent's comments, transitions, and edits land in the same activity history a person's do, so review never depends on chat memory.
Scope what an agent can touch
Field-level permissions decide exactly which issue fields each agent may change. Hand it the status and comments but not the assignee, or whatever the work needs.
The whole project tool underneath
Board, backlog, list, timeline, sprints, docs, reports, and automation are all here. The AI is part of the system, not a separate app to keep in sync.
Agent ready
Works with the agents you already run.
If your agent speaks MCP, it works here. Utter is where the work lands, gets assigned, and stays auditable, while the agent runs wherever you run it today.
Claude
OpenAI Codex
Gemini
DeepSeek
Kimi
Cursor
GitHub Copilot
Perplexity
Frequently asked questions.
What is an AI project management tool?
An AI project management tool is project software that uses AI to help plan, assign, and track work, from drafting issues and summarizing status to running agents that pick up tickets on their own. Utter goes further than most by letting AI agents join as named members you assign issues to and watch work live on the ticket.
Can AI actually manage a project?
AI can take over the repetitive parts, drafting issues, summarizing threads, triaging, and advancing tickets an agent has finished, while a person still sets priorities and approves the meaningful changes. In Utter, high-risk actions stay gated by the same permissions your team already uses.
How is Utter different from ClickUp, Asana, or Notion AI?
Most tools add an AI assistant beside the task list. Utter treats AI agents as members of the workspace: you assign them issues, they run on the ticket over MCP or the REST API, and every step is recorded and attributed. You bring your own agent instead of paying for a bundled one.
Does it cost extra to use the AI?
Viewers are free on every plan and AI agents never count as billed seats, so you pay only for the people building. Because you bring your own agent, the model cost stays with your provider rather than a markup on the seat price.
Which AI agents can I connect?
Any MCP client works, including Claude Code, Cursor, and Codex. Utter exposes the same operations to agents that its own product uses, through a first-party MCP server and a REST API of around 180 operations.