Think inside your AI world.
Cloudflare + GitHub through Unl
Some config a change can touch freely; some should never move without a second pair of eyes. Which is which is a bar you set — and it sits above both the edge and the repo.
Cloudflare + GitHub through Unl reads a config change against the code driving it, judged by the config-safety bar you set, so the change reads as “inside the bar” or “touches config that needs review.” The bar is held in Unl.
The criterion that binds them
Say you’ve ratified a config-safety bar: the Cloudflare settings that may change with a normal review, and the protected ones — routing, security rules, Workers bindings — that need explicit sign-off, because a quiet edit to a protected setting is how an outage ships as a routine deploy.
The two naked reads
Cloudflare returns the account config, Workers bindings and recent builds. GitHub returns the pull request and its diff. Both are exact and unaware of each other, so whether the change crosses a protected setting is left to you to catch in review.
The one measured answer
Held to your bar: the change is routine on the code side, but it edits a protected routing setting your bar rings-fences — so it needs explicit sign-off, not the normal review, and it’s the config it touches, not the code, that raises the flag.
And back again
If you reclassify that setting as safe to change routinely, Unl holds the revised bar — and the next change is measured against the protections as you’ve now drawn them.
The answer comes back measured against what you already decided, and why.
A router can put the Cloudflare config beside the GitHub diff. It can’t say the change needs sign-off, because the config-safety bar — which settings are protected and why — lives in neither the edge nor the repo.
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 flag an infra change that needs review?
Yes, through Unl. You ratify a config-safety bar — which Cloudflare settings may change routinely and which are protected — and Cloudflare and GitHub are read together against it, so a change reads as inside the bar or touching config that needs sign-off.
Isn’t a reviewed pull request enough?
A normal review can wave through a diff whose real risk is the protected config it touches. The bar that marks which settings need explicit sign-off lives in Unl, so the read raises the flag a routine review would miss.
Does Unl change my Cloudflare or GitHub state?
Unl reads through Cloudflare and GitHub, and can write back on your explicit gesture — it never acts as a side effect of a read.
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.