Think inside your AI world.
Google Sheets through Unl
A spreadsheet updates silently. Whether the live cells still match the assumptions you settled on is a question the sheet won’t raise on its own.
Google Sheets through Unl reads your live sheet — cell values by range, formulas, tabs, metadata — against the model assumptions you have ratified, so drift from the numbers you settled on is surfaced with the assumption it breaks.
What Google Sheets holds
Google Sheets’ MCP server exposes the spreadsheet surface:
- Cell values by A1 range
- Formulas
- Tabs and sheet metadata
What the naked read gives you
A naked read returns the cell values. Accurate, and it can’t tell you the churn assumption has crept from 3% to 5% since you ratified the model, because the sheet doesn’t know which numbers were settled.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when Google Sheets is read measured
Say you've ratified the load-bearing assumptions behind the forecast: churn at 3%, CAC at £40, gross margin at 70% — the numbers the plan was signed off on.
“Does the model still hold?” returns, measured: two assumptions have drifted — the churn cell now reads 5% and CAC reads £52, both past the values you ratified the plan on, which is enough to move the runway you were protecting. Sheets supplied the live cells; your ratified assumptions supplied the drift and why it matters.
And back again
If you decide 5% churn is the new baseline and re-ratify it, the model’s settled assumptions move on your word — and the next read measures against the plan you now hold, not the old one.
The answer comes back measured against what you already decided, and why.
The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Questions people ask
Can AI check my spreadsheet against assumptions I set?
Yes, through Unl. You ratify the model’s load-bearing assumptions, and the live Sheets cells are measured against them — drift is surfaced with the assumption it breaks and why it matters, rather than left to notice by eye.
How do I connect Google Sheets to Claude?
Google Sheets offers an MCP server for cell values, formulas and tabs. Through Unl the same cells arrive measured against your ratified assumptions, so the model reads as holds-or-drifted.
Does Unl edit my spreadsheet?
Unl reads through Sheets, and can write back on your explicit gesture — it never acts as a side effect of a read.
What if the sheet has been updated with new assumptions and nobody re-signed them?
Then the forecast is running on numbers that were never ratified, and the read names the drift rather than recomputing quietly. The point of settling churn, acquisition cost and margin was that the plan rests on them; a cell edited afterwards changes the plan without anyone changing the decision. The read shows the ratified figure beside the current one and leaves the reconciliation with you.
What this is
Think inside your AI world — you stay in command
Save the thoughts, decisions and targets worth keeping, each with its reasoning, carried into every AI session the moment they matter. A new unit of exchange between you and your AI: the Settled Why with standing that travels. Unprompted.
Your whole AI world. What you decided at the epicentre. It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector — quick to connect, in a couple of steps.
MCP native·Human settled·Model agnostic·Your data
Measured Context
Connect Unl to bring the right information into the moment.
Your sources, read against the criteria you set.
The full product, open. Free at launch.