TODO for AI
vs 
Make
By Marcell Havlik, founder of TODO for AI · Updated
Visual scenario builder with credit-metered runs and AI agents on every plan. Here is where each one wins, with numbers, and who should pick which.
| Fact | Make | TODO for AI |
|---|---|---|
| Interface | Web | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Vendor managed, or bring your own LLM key | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Closed | Edge + CLI public |
| Starts at | Free | Free |
Key takeaways
- Models. Make model choice: Vendor managed, or bring your own LLM key. 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 95.1% on Terminal-Bench 2.1 with Opus 5.5 (own harness, 77/81 tasks, refused tasks excluded, 2026-09-30; not an official leaderboard submission).
- Price. Make pricing: Free 1,000 credits/month with 2 active scenarios, Core $9, Pro $16, Teams $29 per month at 10,000 credits, Enterprise custom. 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. Make gets one task done inside the scenario you drew. 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 Make if the process repeats and is worth drawing once. Pick TODO for AI if Tasks are one-offs you would rather describe than diagram.
Make
TODO for AI
Any providerWe are not competing for the same job
Make gets the task done.
TODO for AI organises the whole company’s work.
Make answers one question: how do I get this task done, inside the scenario you drew? 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 Make is, and where it stops
Make is what you pick when Zapier's linear steps stop being enough. The canvas shows branching, iteration and error handling as a diagram, the per-run cost is lower, and AI agents come on every plan including Free. Being able to attach your own LLM key is a genuinely unusual bit of openness in this category.
It is still a builder. Value starts after you have drawn the scenario, which makes it excellent for work that repeats and pointless for the task you would rather describe once. Credits meter each module action, so the elaborate scenarios you were encouraged to build are also the expensive ones, and unused credits expire with the term.
Teams who want Zapier-style automation with more control and a lower per-run cost.
Three reasons Make users look elsewhere
A scenario has to exist before anything runs. For a one-off task, building the diagram costs more than doing the work by hand.
Roughly a credit per module action means the branching, iterating scenarios Make is good at are the ones that drain the pool fastest.
Modules and connectors only. No shell, no file system, no session in your Chrome, so anything without a decent API is out of reach.
Six dimensions that decide it
Make 15/30TODO for AI 29/30How does Make compare to TODO for AI, feature by feature?
| Feature | Make | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | No | Yes |
Model choice | Vendor or your own key | Any provider |
Cross-vendor review Review GPT output with Claude, or the other way around. | No | Yes |
Drives your real browser Chrome extension plus cloud browsers. | No | Yes |
Business tasks, not only code SEO, email, ads, social, CRM via CLI tools. | Whatever a module exposes | Yes |
Any CLI as an integration | MCP + HTTP module | 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. | AI agents, all plans | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Scenarios and folders | Unlimited, shared |
Team roles, pooled usage | Seats + credit pool | Roles + pooled |
Tool permissions | Basic | Allow, approve, block |
Open runtime | No | Edge + CLI public |
Same ladder, different meter
Credits, roughly one per module action, so a long scenario costs more per run than a short one. Credits expire at the end of the term and scenarios stop when they run out. AI agents are on every plan and draw from the same pool, or you supply your own LLM key.
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.