TODO for AI
vs 
Linear
The issue tracker engineering teams like, now with agents you can assign issues to. Here is where each one wins, with numbers, and who should pick which.
Linear
Whatever the delegated agent runs
TODO for AI
Every providerWho should pick which
- Your work is engineering issues and cycles, and you want the best tracker for them
- You are happy for the doing to happen in another vendor's agent
- You need the maturity: triage, projects, roadmaps, integrations
- The work on your board is not only code
- You want the agent to have a shell on your machines and a session in your Chrome
- You want to pick the model per item instead of inheriting the delegated agent's
- You want one bill instead of a tracker plus an agent subscription
We are not competing for the same job
Linear gets the task done.
TODO for AI organises the whole company’s work.
Linear answers one question: how do I get this task done, by handing it to somebody else's coding agent? So do the others — Cursor inside the editor, Claude Code in one person's session, Lindy by asking its assistant.
We answer a different one: where does the work live? One board per project, and a project for each part of the company — engineering, marketing, ops, finance, one per client. Your colleagues work on it. So do your agents, as many as you want to run, each with its own model, tools and permissions. Items carry the people who worked them and the agent that ran them, and the board filters by person, so what the company has in flight is one screen instead of a Slack thread.
That is not a team plan bolted onto an AI tool. It is the product. The agents are how items get closed; the board is what the company runs on.
What Linear is, and where it stops
Linear is the closest thing to what we are building, from the opposite direction. It already has the thing the agent vendors do not: a real shared board, where a teammate and an agent can hold the same item, where state is queued, started, blocked and done, and where everyone can see it. Since the agent platform shipped you can assign an issue to Claude Code, Codex, Cursor, Copilot, Devin or twenty others, and Linear Agent runs Claude Code or Codex in Linear's own managed sandbox.
What it will not do is leave engineering. An issue is a thing that ends in a diff. There is no shell on your laptop, no logged-in browser, no inbox, no ad account, and the model is whatever the agent you delegated to happens to run. Linear is mostly the dispatcher, and Linear Agent only narrows the worker to Claude Code or Codex in Linear's sandbox.
Engineering teams who want issues, cycles and coding agents on one board.
Three reasons Linear users look elsewhere
Invoices, outreach, ad accounts and support triage have no shape in Linear. The agent integrations are coding agents, every one of them.
Assigning an issue to Devin or Cursor means another subscription, another vendor's models and another permission model. Linear Agent avoids the second bill by running Claude Code or Codex in Linear's own sandbox, which is still not a machine you control.
Linear never gets a shell on your box or a session in your Chrome. Anything that needs your logins goes back to a human.
Six dimensions that decide it
Linear 15/30TODO for AI 29/30What each one ships
LinearTODO for AISame ladder, different meter
Seats, plus AI credits for coding sessions and Loops. Delegated agents bill on their own vendor plan, so a Devin or Cursor subscription sits on top.
One pool priced in dollars of model cost, spendable on any vendor. Session and weekly windows pace it, and a 1.3-1.5x plan multiplier applies, so a $20 plan is about $15 of list-price API. Team seat prices go into one shared pool.