Think inside your AI world.
A competitor feature, against a gap you flagged
A competitor changelog is busy by design: fixes, tweaks and launches every week, almost none of which change anything for you. What you actually need is the one release you had already flagged — the capability you decided would turn a rival you watch into a real threat — and that is a line no changelog can hold, because the line is a call only you have made.
Read a competitor’s public changelog through Unl and the stream of releases arrives measured against the gap you flagged — so instead of a log to skim, you get the single feature you had already named as the one that would matter, with the reason it crosses. The one, not the thousand.
What a competitor's public changelog publishes
A competitor you track ships in public, and the changelog is busy:
- A steady stream of releases — fixes, polish, minor features, the occasional launch
- Every area of their product at once, most of it irrelevant to where you actually compete
- No sense of which release changes the threat and which is routine
- The bearing on your position is a judgement — it is nowhere in the release note
The line the feed can't hold
Say you took a position on a rival you watch, and named the one thing that would change it: they are not a real threat until they close this specific gap; the day they ship it, that is the release I need to know about — everything else is noise. That call is yours: you decided which capability is load-bearing and which is cosmetic. It is not a field the changelog exposes.
The reason the line is yours is the whole point. A changelog reader can list every release; it cannot know which one you had flagged as the gap that makes a rival a genuine threat, or that a flashy launch you do not care about is noise to you while a quiet line-item closing the gap you named is not. The judgement of what matters is a position you took, not a category the feed models.
The frame judges the data it is given; it does not verify the source’s accuracy.
The one that crosses
So when their changelog announces the exact feature you flagged, it crosses — and the rest of the stream does not. Through Unl the answer arrives as a verdict: the gap you named as the one that would make them a real threat just closed — this release is the thing you told yourself to watch for, above the rest of the log, which was routine. Same public changelog; a position confirmed instead of a digest scanned.
You didn't ask — it was already there
You did not ask for it. The gap was already flagged in your own words, so the next time you open Claude on that work the crossing is already in the window — held against the position you took, with the reason it matters — rather than waiting for you to remember to read the rival’s log. You name the gap once; the read watches for it every time they ship.
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.
Read further
Questions people ask
How is this different from following a competitor’s changelog or a changelog-tracker feed?
A tracker forwards every release; you still have to decide, each time, whether it matters. This decides against a line you already drew: the specific gap you flagged as the one that would make them a real threat, applied only to that release, with the reasoning attached. The feed shows you the thousand routine ships; the measured read shows you the one that closes a gap you named, and why.
Do I get pinged the moment they ship something?
The capability is that the crossing arrives measured against your flagged gap the next time you are working — it is already in the window, held against your line, rather than a stream you monitor. A scheduled push is a separate delivery; what the read guarantees is that when the release you were watching for lands, it surfaces as a verdict against your position, not as one more changelog entry.
Does Unl change anything on the competitor’s site or in my notes?
Unl reads through the competitor’s public changelog, and can write back on your explicit gesture — it never acts as a side effect of a read. The changelog is a public GET; the gap you flagged lives in Unl; the read joins them and returns a verdict, altering neither.
What if they ship something adjacent rather than the exact gap I named?
It does not cross, and that is the point of naming the gap precisely: near-misses stop consuming your attention. The risk is real and worth stating — a line drawn too narrowly can miss a genuine move made a different way. That is why the criterion is written in your words and revisable in your words. If the adjacent release changes your read of them, you restate what you now believe would make them a threat, and the record holds both what you thought before and what moved 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
Frontier Frame
Connect Unl to watch the world against what you decided.
A crossing arrives when the world bears on your position.
The full product, open. Free at launch.