# every: method

> how ai agents researched the every history, the evidence rules they followed, and what they could not verify.

## the lanes

the corpus was produced by four parallel agent research lanes — company history, the people and their writing, coverage and sentiment, and the media-house-ships-software idea — each writing a lane report against one shared scratch source catalog before synthesis. the pattern is the company-research formula proven on roam-research and obsidian: lane-prefixed source ids frozen upfront, per-claim confidence from the start, and a declared deduplication owner.

## the evidence rules

- every event, quote, and claim carries at least one source id.
- dates keep their precision; approximate dates are labeled, not sharpened.
- confirmed, reported, and inferred stay distinct.
- sources are typed by role: primary, interview, reporting, archive, community.
- sentiment describes the coverage, not the truth of it.

## known gaps

- subscriber and revenue figures are self-reported by the company and labeled as such.
- the pre-seed is reported as both $600k and ~$700k across every's own posts and the trade coverage; the discrepancy is preserved, not reconciled.
- the 2025 seed is a drawdown structure — ~$500k reported drawn by mid-2025; the current drawn figure is undisclosed.
- the terms of the lex spinout stake and any alumni equity claims are undisclosed.
- which apps are every-owned versus every-partnered is reported but not fully mapped — the boundary moves with each launch.
- bundle revenue-sharing terms between every and its columnists were never published; the economics are inferred from departures, not contracts.
- the x/twitter corpus is partial — native search failed, so tweet-level material came through archives and interviews.
- early newsletter-era metrics (open rates, churn) exist mostly in every's own retrospective essays.

## corrections

corrections and additional primary sources are welcome — cite the claim, the source, and what it changes.

389 cataloged sources. 39 timeline events. 27 writings. 24 coverage items.

AI-drafted at Ben Guo's direct request and credited to Hraness; every claim links to its cataloged source.

Canonical page: https://hraness.com/every/method


Published by @ben in profile revision 1.
Original document: https://hraness.com/every/method
Original credited author: Hraness
AI-drafted at Ben Guo's direct request and credited to Hraness; every claim links to its cataloged source.

## Structured source and record data

````json
{"anchors":[{"id":"lanes","originalUrl":"https://hraness.com/every/method#lanes","title":"the lanes"},{"id":"rules","originalUrl":"https://hraness.com/every/method#rules","title":"the evidence rules"},{"id":"gaps","originalUrl":"https://hraness.com/every/method#gaps","title":"known gaps"},{"id":"corrections","originalUrl":"https://hraness.com/every/method#corrections","title":"corrections"}],"provenance":{"draftingDisclosure":"AI-drafted at Ben Guo's direct request and credited to Hraness; every claim links to its cataloged source.","originalAuthor":"Hraness","originalRevision":"3eaff376dd9eda9784809cd63ed44f616049de4eb8f7395cdaede77af342da5c","originalUrl":"https://hraness.com/every/method","source":"hraness"},"records":[],"sources":[]}
````