TODO for AI
vs 
Airtable
By Marcell Havlik, founder of TODO for AI · Updated
Database-shaped workspace whose Omni agents build apps and act on records, metered in AI credits. Here is where each one wins, with numbers, and who should pick which.
| Fact | Airtable | TODO for AI |
|---|---|---|
| Interface | Web, desktop, mobile | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Vendor managed | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Closed | Edge + CLI public |
| Starts at | Free | Free |
Key takeaways
- Models. Airtable model choice: Vendor managed. 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. Airtable pricing: Free, Team $20, Business $45 per seat per month billed annually, Enterprise Scale custom. AI credits are pooled: 15,000 per billable collaborator on Team, 20,000 on Business; extra packs from $20 for 10,000. 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. Airtable gets one task done inside the base. 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 Airtable if your work is naturally records, tables and fields. Pick TODO for AI if you do not want to model the work before doing it.
Airtable
TODO for AI
Any providerWe are not competing for the same job
Airtable gets the task done.
TODO for AI organises the whole company’s work.
Airtable answers one question: how do I get this task done, inside the base? 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 Airtable is, and where it stops
Airtable made the smartest structural bet in this category: agents work far better against typed records than against a wall of documents, and Omni turns a description into a working internal app or agent over that data. Building costs nothing, credits pool across the workspace rather than stranding per seat, and for record-shaped work it delivers.
The cost is the modelling. Work has to become a base, tables and fields before an agent can touch it, which is real effort for anything that is not naturally tabular. Business seats are $45, well above the other work platforms in this list, and running agents draws on a credit pool that a document-heavy month empties quickly at roughly 200 credits per ten-page analysis.
Teams whose work is structured records and who want internal apps and agents on top of them.
Three reasons Airtable users look elsewhere
An agent acts on records, so the work first has to be a base with the right tables and fields. Tasks that are not tabular never get there.
$45 per seat on Business, against $19 on monday Pro and $10 on Trello Premium, plus a credit pool that stops the agents when it empties. Extra packs start at $20 for 10,000.
No shell, no machine, no session in your Chrome. Reach ends at records and connected integrations.
Six dimensions that decide it
Airtable 13/30TODO for AI 29/30How does Airtable compare to TODO for AI, feature by feature?
| Feature | Airtable | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | No | Yes |
Model choice | Vendor managed | 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. | Records + connected apps | Yes |
Any CLI as an integration | Scripting extension + MCP | 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. | Yes, agents on bases | Yes |
Many agents, each configured Each agent gets its own model, prompt, tools and permissions. Pick which one takes an item. | Omni agents and apps | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Bases and workspaces | Unlimited, shared |
Team roles, pooled usage | Seat + pooled credits | Roles + pooled |
Tool permissions | Base and field level | Allow, approve, block |
Open runtime | No | Edge + CLI public |
Same ladder, different meter
Seats plus a pooled AI credit allowance, 15,000 per collaborator on Team and 20,000 on Business. Building with Omni is free; running costs credits that scale with input, model and output, roughly 10 for a question and 200 for a 10-page document. Work stops when the pool empties.
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.