The note is titled "Membership retention ideas" — but ask about "the subscription economy" and it still turns up

1,800 notes over five years, 12 folders, tags abandoned

He wrote nearly every week for five years, and wrote meetings up the same day they happened. Which means he covered the same ground more than once. Subscription models and repurchase cycles come up four separate times across three years — and none of those four notes link to each other, and each carries a different set of tags.

• 1,800 markdown notes. Five years' worth, all .md files on a local disk
• 12 folders. "00_inbox" alone holds 400 of them, and the other 11 each sort by a different logic
• Roughly 300 book summaries, 200 conference and talk notes, 700 meeting notes, and the rest loose ideas
• About 40 tags. Half of them sit on exactly one note, and #ideas is on 600 notes, which makes it useless as a filter
• No title convention. "Membership retention ideas," "0312 meeting," and "look at this again" all live in the same folder

Five search terms in, still nothing

Here's the current routine. Type whatever word comes to mind into the search box. "Subscription economy." "Subscriptions." "Subscription model." "SaaS." "Retention." Each one only catches notes where he happened to type that exact word. The note he actually wants, "Membership retention ideas," is written entirely in his own vocabulary — "repurchase cycle," "membership," "churn" — so it matches none of the five.

Next he opens folders. The 400 notes in "00_inbox" tell you nothing from their titles. Whether "0312 meeting" is the one is something you learn by opening it. He opens ten or so, gives up, creates a blank document, and rewrites it from memory. How many of those 1,800 notes are duplicates written this way, he couldn't tell you.

Drag all 12 folders in at once

Setup happens once. He doesn't rewrite notes or clean up tags. The original markdown files are left alone — they just go in.

Ask using words that aren't in the title

"what did I write up about the subscription economy last year?"
→ "Documents" section: 3 hits. All meeting notes that spell out the phrase.
   From here, ⌘↵ → "Ask your workspace". A new chat opens with the question
   pre-filled; nothing is sent until you press send.

(same question, in chat)
→ The answer arrives with a "Where this came from in your notes" card.
   2 glowing nodes = "Directly matched" (those meeting notes).
   Matte nodes = "Related". One of them is [[Membership retention ideas]] (2025-03),
   which never says "subscription economy" in its title or body.
   Each connecting line is labeled with the relation's name.

"retention"
→ A [[Retention]] row under "Concepts". Enter opens the entity page, where
   five years of notes mentioning the concept sit together in one place.
   "Open in graph" jumps to the full 3D view.

Here's why the first question works. Concepts like [[Subscription economy]] and [[Retention]] were pulled out of the sentences inside "Membership retention ideas," and the two are connected to each other. So asking about the subscription economy drags along a note that never once uses the phrase, as "Related." He doesn't have to remember which words he chose five years ago.

Why something matched is visible on the spot. The mini-graph card draws "Directly matched" — the query's direct hits — separately from "Related," reached by walking relations, and labels each connecting line with the relation's name. Click a node and its entity page opens. If it's material for his manager, he collects it into a case, and reopens it later with ⌘⇧K or by typing the case's name into the palette.

What changes