Datatrolleri · internal platform · briefing for 2026-08-10

Find out
in a day

Ventures Garden takes a business idea from “someone had a hunch” to “strangers are giving us their email address” in about half a day of one person’s time — then does it again, across a team, so that what is learned compounds.

10 stages5 human gates 3 turns per person, maximum27 documents 0 completed ventures

The bet

Cheaper to find out than to build and hope

A venture never starts with code. It starts with evidence a market exists and ends with strangers handing over an email address, before a line of product is written. Most ventures are then killed — that is the design working, not a failure.

Success is not a launched venture. Success is cost per signup falling week over week, and a ledger that makes venture #40 start further along than venture #1.

What a competitor could not copy

The accumulated ledger of kills. Any single venture is disposable; knowing which categories, positions and creative approaches convert for us is not. Most portfolio tools delete their failures. This one is built so failure is the asset.

How work moves

The turn loop

Work is claimed under an expiring lease, never assigned. You are one claimant among several, and anything you hold returns to the board when you stop holding it.

boardWhat needs a person right now. * means nobody is holding it.
claimTake one turn. Writes a briefing: thesis, chosen position, rejected positions and why.
attachThe heartbeat. Not a status — it is what keeps the turn yours.
workThe stage prompt, resolved for you into the venture folder.
reportRelease it. Requires a manifest — a turn that produced nothing shared is refused.
The scarce resource is attention, not access

Three turns at once, maximum. That cap is not a rate limit — it is what stops one person claiming six things and blocking five of them. Reviewer attention, not money or compute, is what caps how many ventures launch in a day.

Track 01 — app pre-sell · the only track today

Ten stages

Each stage has a prompt in tracks/01-app-presell/prompts/, kept in two forms: the original verbatim source, and the hardened version we actually run. Amber marks a stage that cannot advance without a person.

00

Market scan

Replace guessing with evidence — where is money already moving.

AppMagica person in a browser
01

Blue ocean

Enter the hot category through a door nobody is standing in.

Gate 1 — which ideamodel returns five, you pick
02

Product spec

The one document every later stage reads from.

Gate 2 — the spec
03

Product screenshots

Make the product look real enough to sell before it exists.

Gate 3 — the assetsHiggsfield
04

Landing page

The instrument that measures demand. Everything before this was preparation.

Gate 4 — honestyleadd → Postgresusually needs a second person
05

Conversion tracking

Teach Meta’s AI what a good customer looks like.

Meta AdsChrome DevTools
06

Generate ads

Many shots on goal, cheaply. 42 formats, 11 banned by construction.

Higgsfield
07

Deploy

A URL a stranger can open. Our own box, behind Caddy.

CaddySimply.com DNS
08

Create Meta campaigns

Put the offer in front of strangers. Left in draft — a person publishes.

Gate 5 — before publishMeta Adsspends money
09

Scale winning ads

Make the system self-improving.

Gate 5 also covers thisMeta AdsHiggsfield

Six gated stages against five platform gates: gate 5 covers both stage 8 and stage 9, because both spend money.

Not advisory

The five gates

Ventures Garden is fast because the machine does the work. It is good because a human stops it at five points. A track may add a gate; nothing may remove one. A waiver changes who clears a gate, never whether it exists.

GATE 1 · STAGE 1

Which idea

The model returns five positions. You pick one, and the four you rejected are recorded with the reason — they travel into every later briefing.

GATE 2 · STAGE 2

The spec

Read it end to end. Push back until it describes something you would want to exist.

GATE 3 · STAGE 3

The assets

Anything hallucinated, off-brand or fake-looking gets regenerated.

GATE 4 · STAGE 4

Honesty

Models will happily write “loved by 12,000 future plant parents” on day zero. Delete it. Invented social proof does not ship, ever. Normally needs a second person.

GATE 5 · STAGES 8 & 9

Before publish

Ads are drafted, never auto-published. This is the gate that stands between a draft and real money. Normally needs a second person.

Working alone

When there genuinely is no second person, the producer clears their own gate under a recorded, expiring waiver — after a cooling-off period timed from when the work was put down, with notes, marked in the ledger forever.

Two rules that never bend

Honesty, and the draft rule

Never fabricate

No invented counts, testimonials, ratings, press logos or urgency. The instruction goes in every generation prompt, every time, because models re-add it on regeneration. A linter greps for the patterns; a person still reads the page as a stranger would.

Never publish ads

Stages 8 and 9 leave campaigns in draft. A person publishes. This is enforced by a hook on the Meta mutations that can start live spend — it asks, every time, rather than relying on a model having read the rule.

What you operate

Tools & skills

Every capability the track needs, and what provides it. Health is measured by ./scripts/doctor.sh and recorded — the platform knows its own state rather than assuming it.

ProvidesToolStagesState
App revenue dataAppMagic0a person in a browser
Image & video generationHiggsfield (hf CLI)3, 6, 9healthy
Campaign managementMeta Ads MCP5, 8, 9healthy
Network observationChrome DevTools MCP5healthy
Static hostingCaddy on app-017not observed
DNS record writeSimply.com API7not observed
Lead captureventuresgarden-leadd4live
Lead storagePostgres on data-014, 7live

Skills — callable procedures

SkillWhat it doesState
/gate-honestyRuns the fabrication linter, reads the page as a stranger, writes findings into VENTURE.md, then opens the gate for a second personshipped
/venture-domainRegisters a domain, points a venture hostname at the box, diagnoses a deploy that failed at DNSshipped
/gate-reviewThe four gates that have no skill — position, spec, assets, pre-publishto write
/standupSteward digest: spend, what is stalling, blocked on whomto write
/kill-reviewFriday pass over every live venture, default killto write

A skill never writes what the ledger records — it calls venturesgarden. Gates, reviews, claims and decisions are rows; written into markdown they become a second version that disagrees.

Read this part twice

Where it is real, and where it is not

The platform’s own voice rule is to state its gaps out loud. Every number here was measured on 2026-08-08, not estimated.

0
completed ventures. The ledger holds three, all killed at stage 0 — plumbing tests, not attempts.
0–7
stages ready to run today, end to end.
cost per signup. Signups are measured; spend is not. The sync from Meta is not built.
1
track. A second one is written only after a first has been run manually end to end.
The method’s own metric has no instrument

Success is defined as cost per signup falling week over week. Signups reach the ledger; spend does not, because the Meta performance sync is not built. The ledger renders those columns as visibly unmeasured rather than as zero — a column nothing feeds shows , never 0.

A venture cannot be ended

There is no command that records a kill. The venture.decision table exists and is empty; none of the 30 CLI subcommands or 24 service routes writes it. The three killed ventures were killed with raw SQL. This sits exactly where the method claims its value — the accumulated ledger of kills — and it is the largest hole in the platform today.

The ad account reports on Stockholm time

Every venture targets the US, but the ad account’s day boundary is Europe/Stockholm and Meta refuses to change it after creation. A replacement cannot be created either — the portfolio’s ad-account limit is 1. Accepted deliberately: cost per signup is a ratio and is unaffected, so this is a reporting offset. Any surface showing a date must say which clock it is on.

Monday

Where to start

  • Run the tutorial. docs/first-venture.md — a throwaway venture, start to kill, about an hour. It costs nothing and touches no advertising. Do this before the first real one, so that the first time you meet a lease expiring is not on a venture that matters.
  • Then the manual. docs/running-a-venture.md — the whole flow from having no account to killing or scaling.
  • Then the playbook. tracks/01-app-presell/playbook.md — the ten stages in detail.
  • Before you generate a line of copy: docs/honesty.md.
Orient from a terminal, without reading anything
  • ./scripts/doctor.sh — is this machine set up? Fails loudly.
  • venturesgarden board — what needs a person, and the command that takes it.
  • venturesgarden guide list — every document: kind, slug, path, summary.
  • venturesgarden guide due — manual work the platform cannot do itself.
  • venturesgarden tools — what provides each capability, and whether it works.
One thing a fresh clone will not have

impeccable, which the design linter shells out to, is a personal skill in ~/.claude/skills/ and is not committed. The design surfaces depend on it, so a second operator gets its output on git pull without the tool that produced it. You do not need it to run a venture.