Think inside your AI world.
Xero + Ramp through Unl
Bank transactions in Xero, card spend in Ramp — reconciling them by hand is a chore that still doesn’t tell you what breached a rule.
Xero + Ramp through Unl reads bank transactions and card spend together against the category caps you ratified, so reconciliation returns verdicts — which categories breached which caps, and why the cap is set — not a list of lines to tick off.
The criterion that binds them
You ratified category caps and the reasons behind them — the monthly ceilings that keep spend inside the plan. Reconciliation is then judged against those caps, not just matched line to line.
The two naked reads
Xero returns the bank side; Ramp returns the card side. Each accurate; matching them tells you the books agree, not whether the spend obeyed your rules — because the caps aren’t in either.
The one measured answer
Measured against your caps: the two sides reconcile, and two categories breached the caps you set — travel at 128% of its ceiling and tools at 115% — each named with the cap it broke and why that cap exists. Reconciliation becomes a verdict, not a tick-list.
And back again
When you lift the travel cap for a conference month, that exception is ratified in Unl — and next month’s reconciliation measures against the rule you actually hold.
The answer comes back measured against what you already decided, and why.
A router can match Xero and Ramp lines. It cannot judge them against your caps, because the caps — and the reasons for them — live in neither tool.
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.
Read further
Questions people ask
Can AI reconcile Xero and Ramp against my spending rules?
Yes, through Unl. You ratify your category caps and reasons, and Xero’s bank transactions and Ramp’s card spend are read together against them — reconciliation returns which caps were breached, not just whether the lines match.
How is this different from normal reconciliation?
Normal reconciliation checks the two sides agree. Measured through Unl, it also checks the spend against the caps you ratified — so the output is verdicts against your rules, with the reasoning.
Does Unl change my accounts?
Unl reads through your accounts, and can write back on your explicit gesture — it never acts as a side effect of a read.
What if a charge belongs to two categories at once?
Then it will be judged against whichever cap it was filed under, and the other cap will not see it. Category caps assume each charge has one home, which most do and some genuinely do not. The read reconciles what it is given rather than deciding where an ambiguous charge belongs, because that decision is a judgement about your own plan and it stays yours.
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.