TODO for AI
vs
Copilot Cowork
By Marcell Havlik, founder of TODO for AI · Updated
Microsoft 365 Copilot's agent: describe a task and it does the work across Outlook, Teams, Word, Excel, PowerPoint and SharePoint. Here is where each one wins, with numbers, and who should pick which.
| Fact | Copilot Cowork | TODO for AI |
|---|---|---|
| Interface | Web, Copilot desktop app, mobile | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Anthropic and OpenAI, picked by Microsoft | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Closed | Edge + CLI public |
| Starts at | $18/mo + usage | Free |
Key takeaways
- Models. Copilot Cowork model choice: Anthropic and OpenAI, picked by Microsoft. TODO for AI runs any provider, Claude, GPT, Gemini, Grok or a local Ollama model, on one plan, and one model can review another's work.
- Benchmark. TODO for AI scored 89.9% on Terminal-Bench 2.1 with Opus 5.5 (high) (own harness, 80/89 tasks, 2026-10-08; not an official leaderboard submission).
- Price. Copilot Cowork pricing: Needs a Microsoft 365 Copilot license (Copilot Business $18 per user per month yearly, promotional to end of 2026), then Cowork is metered in Copilot Credits at $0.01 each, or prepaid at a discount. TODO for AI has a free plan (Claude Sonnet only), then Starter $20, Pro $100 or Ultra $200 a month with any provider included.
- Where the work happens. Copilot Cowork gets one task done inside Microsoft 365. TODO for AI is one board your team and agents work through together, on your own PC, a cloud VM and your logged-in Chrome.
- Who should pick which. Pick Copilot Cowork if your work lives in Outlook, Teams, Word, Excel and SharePoint. Pick TODO for AI if your work spans tools outside Microsoft 365: CRM, ads, shop, website, servers.
TODO for AIWe are not competing for the same job
Copilot Cowork gets the task done.
TODO for AI organises the whole company’s work.
Copilot Cowork answers one question: how do I get this task done, inside Microsoft 365? 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 Copilot Cowork is, and where it stops
Copilot Cowork is Microsoft's answer to Claude Cowork, generally available since 16 June 2026. You describe a task and it carries it out across your Microsoft 365 environment: drafts and sends mail, schedules meetings, builds the deck and the spreadsheet, posts in Teams, files it in SharePoint. It runs in Microsoft's cloud under your identity and permissions, and at launch it runs on Anthropic models, with OpenAI in the Frontier program.
The perimeter is Microsoft 365. Work that lives in your CRM, your ad account, your shop admin, your servers or your codebase is outside it, and there is no shell on your own machine. Pricing is a Copilot license and then credits per task, so the bill follows usage. Like every agent here except ours, it waits for someone to describe the task.
Companies already standardised on Microsoft 365 who want an agent inside Outlook, Teams and Office.
Three reasons Copilot Cowork users look elsewhere
Cowork is excellent inside Outlook, Teams and Office. The CRM, the ad account, the shop admin, the vendor portal and the server are outside it.
You need a Microsoft 365 Copilot license per user, then every Cowork task spends credits priced by model, context, tool calls and runtime.
Cowork executes what you describe. It does not look at your business and put the next piece of work on the list.
Six dimensions that decide it
How does Copilot Cowork compare to TODO for AI, feature by feature?
| Feature | ||
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | Microsoft cloud | Yes |
Model choice | Anthropic, OpenAI (Frontier) | Any provider |
Cross-vendor review Review GPT output with Claude, or the other way around. | No | Yes |
Drives your real browser Browser extension (Chrome, Firefox) plus cloud browsers. | Edge, Frontier preview | Yes |
Business tasks, not only code SEO, email, ads, social, CRM via CLI tools. | Microsoft 365 apps | Yes |
Any CLI as an integration | Microsoft 365 connectors | Any binary |
Voice control | No | Yes |
People and agents on one board Colleagues and agents work the same list. Items show who contributed and which agent ran them; filter the board by person. | No | Yes |
Many agents, each configured Each agent gets its own model, prompt, tools and permissions. Pick which one takes an item. | Cowork plus Copilot agents | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Microsoft 365 workspace | Unlimited, shared |
Team roles, pooled usage | License + credits | Roles + pooled |
Tool permissions | Tenant and admin controls | Allow, approve, block |
Open runtime | No | Edge + CLI public |
Same ladder, different meter
Copilot Credits at $0.01 each. Cost depends on the model, context retrieval, tool calls and runtime, so a heavy task can cost dollars on top of the license.
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.