Comparison

Unl vs the docs method — an honest comparison

Point your AI at the README, the docs/ folder, the Notion workspace — writing it down is the obvious way to hand over project context. For a large part of the job it’s the right move. The question this page answers is which part, and where a written record stops keeping up.

A fair comparison: documentation earns real credit here — including the reference role Unl’s own setup leans on — and Unl’s own trade-offs are on the page too.

  The docs methodREADME · docs/ · wiki · Notion Unla layer that inherits
SetupYou already write themAdd the connector — about five minutes
CostFree, part of how you workFree at launch; paid tiers later for heavy use
Reference material and how-it-worksStrong — the right home for the stable how~Keep the docs; they carry the reference
Holds the why behind a decisionRecords the what; the reasoning dates fastEvery decision with its reasoning
Shows which decision is currentOld and new sit side by side until someone editsSuperseded on your word
Stays current as the work movesDrifts from reality between editsUpdates as you settle decisions
Surfaces on point, mid-sessionRead when you point at itArrives in the reasoning when it bears
One source across your AI tools~Scattered across repos, wikis and appsOne connection over MCP — inherited everywhere

The docs method

Pros

  • Free, and part of how you already work
  • The right home for reference and the stable how-it-works
  • In-repo or in-workspace, and searchable
  • Excellent for onboarding and shared reference

Cons

  • Records the what; the reasoning behind a call dates fast
  • No marker for which of several pages holds the current decision
  • Drifts from reality between edits
  • Read when you point at it, not when a decision bears

Unl

Pros

  • Holds decisions as you settle them — no grooming
  • Every decision with its reasoning
  • Retires the superseded call so the current one is unambiguous
  • Surfaces the relevant decision when it bears, mid-session
  • One connection over MCP, inherited across tools

Cons

  • It’s a connector you add — one more thing in your stack
  • Newest in the category; earliest days
  • Free at launch, with paid tiers later for heavy use

Nothing here is a versus. Documentation and Unl do different jobs and sit happily side by side. Let the docs own the durable material — architecture, how to run things, the reasoning that doesn’t move. Let Unl own the live layer: the decision you settled today, the option you rejected, the state the work is actually in, delivered the moment it bears. Reference that holds still belongs in a document; judgement that keeps moving belongs somewhere that moves with it.

Where a written record stops keeping up

A document is read on demand; a decision has to arrive on its own.

Open a doc and it tells you what someone last wrote there. That’s ideal for the parts of a project that don’t move — the layout, the run commands, why the architecture is what it is — and useless as a signal that a call has changed, because a page never announces its own staleness.

The decisions are the moving part: which approach won this week, what you dropped, where things actually stand. Nobody edits the wiki the second a decision flips, so between the flip and the edit the model reads whatever the page still says. Unl carries that moving part as structure and puts the piece that bears into the model’s reasoning before it acts — you settle a call, and the work runs inside it without a document in the loop. Tuned for Claude, Claude Code, ChatGPT & Cursor at launch, extending across the AI ecosystem. Connects anywhere MCP does.

Docs are the right home for what stays true — the reference and the how; Unl carries what moves — the decisions, the why, and what you ruled out — so the answer comes back measured against what you already decided, and why.

Reads through Unl arrive with measured context — in the presence of the decisions you’ve already settled. The reach lane is live: 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

Is Unl a replacement for my docs?

No — they compose. Docs are the right home for reference material and the stable how-it-works; Unl adds the half a document can't keep: decisions with their reasoning, the dead-ends, and which call is current — surfaced when they bear.

Why do docs go out of date?

Because they're hand-written and read on demand: a doc holds what someone last typed, and nobody edits it the moment a decision changes. Reference that rarely moves survives; anything with a present-tense truth-value drifts from reality between edits.

Isn't a Notion workspace enough?

A workspace is excellent for reference and process, and worth keeping. What it can't tell you is which of four pages holds the decision that still stands, or the reasoning that carried it — and it waits to be opened rather than arriving when the work needs it.

Which AI tools does this work with?

Unl is one connection over MCP, so the decisions you settle are inherited by Claude, Claude Code, ChatGPT and Cursor alike. The call you settle on one surface is inherited on the others.

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.