Think inside your AI world.

A filing, against the thesis you settled

EDGAR is the whole market’s paperwork, in public, all day: 10-Ks, 10-Qs, 8-Ks, S-1s, thousands a day across every issuer you will never hold. What you actually need is the one line in the one filing that bears on a thesis you wrote down — the metric you said would confirm or break the case — and that is a line the feed cannot hold, because the thesis is yours.

Read EDGAR through Unl and the whole public stream arrives measured against the thesis you ratified — so instead of a filings stream to skim, you get the single disclosure that touches the number your case turns on, with the reason it crosses. The one, not the thousand.

What SEC EDGAR publishes

EDGAR is a genuine public good, and there is a lot of it:

  • Thousands of filings a day across every public issuer — 10-Ks, 10-Qs, 8-Ks, proxies, registrations
  • Every disclosure at once, the material buried beside the boilerplate
  • Thousands of companies, almost none of which are in your book
  • No idea which line bears on a case you hold — that context is not in the filing

The line the feed can't hold

Say you settled a thesis on a company and wrote the line that would test it: my case rests on the margin holding above the level I set; the day a filing shows it breaking that line, the thesis is in question. That trigger is a decision you made; it is not a field the feed models.

The reason the line is yours is the whole point. A filings feed can alert on a new 8-K; it cannot know the number your case turns on, or that you already decided what reading of it changes your mind, or that a headline beat is noise to you when the one line you watch quietly moved the other way.

The frame judges the data it is given; it does not verify the source’s accuracy.

The one that crosses

So when a filing lands and the metric your thesis rests on has crossed the line you set, it crosses — and the other four hundred filings that day do not. Through Unl the answer arrives as a verdict: this quarter’s filing puts the number your case depends on through the line you drew, so the thesis you settled is now in question — here is the passage, read against what you concluded. Same public record; a decision instead of a digest.

You didn't ask — it was already there

You did not ask for it. The thesis was already ratified, so the next time you open Claude on that name the crossing is already in the window — read against the line your case turns on, with the reason it cleared it — rather than waiting for you to remember to pull the filing. You author the thesis once; the read applies it every time the company files.

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

How is this different from a filing alert or an EDGAR watch?

An alert fires on the source’s rule — a new filing, a form type, a keyword someone else chose. This fires on YOUR rule: the specific line your thesis rests on, the reading of it you decided changes the case, with the reasoning attached. The feed shows you every filing; the measured read shows you the one that moves a number you are actually invested in, and why.

Do I get pinged the moment a company files?

The capability is that the crossing arrives measured against your thesis the next time you are working — it is already in the window, read against the line you set, rather than a stream you monitor. A scheduled push is a separate delivery; what the read guarantees is that when a filing bears on the case you settled, it surfaces as a verdict against your reasoning, not as one more filing to open.

Does Unl change anything at EDGAR or in my portfolio?

Unl reads through EDGAR’s public filings, and can write back on your explicit gesture — it never acts as a side effect of a read. The filing is a public record; your thesis lives in Unl; the read joins them and returns a verdict, altering neither.

What this is

Think inside your AI world — you stay in command

Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.

It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.

Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:

Alpha is invite-only · free at launch.