fletchbuilds

03 / The system

How this was actually made.

The brief said "tell us how you used AI." Here's the honest answer: not as an autocomplete, but as an operating system for the work — parallel research teams, a local video-intelligence lab, and a build partner, all directed from one conversation. Every stage below ran inside the four-hour window.

01The pipeline

Recon — three agents in parallel

my time: ~15 min · agents: 3, concurrent

Before touching the demo, three research agents fanned out across the public web: a site & messaging teardown of every kodexglobal.com page (voice, template anatomy, feature inventory, gaps), a buyer and market pass (the PMM job posting decoded, funding history, the Coinbase case study, the fake-EDR fraud wave), and a competitive landscape (four real competitors, the manual status quo, the e-Evidence regulatory clock). Everything source-cited, inferences labeled.

research corpus: 3 documents, every claim linked to a URL

Video intelligence — locally, in confidence

my time: ~10 min · the recording never left the machine

I watched the full demo end to end first — the AI pass came after, not instead of, my own viewing. Then the 34-minute raw recording (720MB, unedited, repeat takes and all) was processed entirely on-device: ffmpeg extracted audio and 135 frames; Whisper large-v3-turbo transcribed locally; three vision agents walked the frames and produced a timestamped, screen-by-screen map of the product. Result: a 21-feature inventory cross-referenced against the site teardown — including sales-motion context that ended up deciding the feature pick.

feature inventory + transcript analysis + 3 frame maps

The pick — evidence over instinct

my time: ~30 min · the judgment call

Shortlist of three, argued on the evidence: Transparency Reporting won because it's a provable site gap, undersold by the structure of the sales motion itself, backed by a page-ready automation claim, and riding a live regulatory clock. The runner-up (the API layer) and the case against the winner are both preserved in the working doc.

§1 of the thinking doc, counterargument included

Messaging — the framework before the pixels

my time: ~20 min · positioning, message house, voice rules

Buyer archetype (grounded in years working with compliance teams), the cost-center-to-trust-asset flip, a three-pillar message house, hero line chosen from four candidates, and an assumptions register that says exactly what I'd verify on day one. The page was built on top of this — not the other way around.

the thinking doc, evidence classes on every claim

The page — your system, done carefully

my time: ~45 min across three versions · design QA by screenshot

Design tokens pulled from your production CSS. Your newest page template decoded from live screenshots. Your licensed typeface matched by rendering six candidate fonts against your real headlines and comparing letterforms. Three review rounds of my notes — typography, contrast bugs, label precision — each verified with headless-browser screenshots in both themes before committing. Plus one addition your site doesn't have: a proper light/dark mode.

/page — one file, no framework, both themes, reduced-motion safe

This site — the submission as a product

my time: ~20 min · packaging is positioning

A page tells you what I decided. The working doc tells you how. This site exists so one link carries both — plus the part that usually stays invisible.

fletchbuilds.com

02The time ledger

PhaseMy timeWhat ran in parallel
Setup — project scaffold, working rules~15 min
Recon — direction + review of findings~15 min3 research agents, ~35 min wall
Video — drop file, review inventory~10 mintranscription + 3 vision agents, ~25 min wall
Pick + messaging — the judgment work~50 min
Page — direction, notes, three review rounds~45 minbuilds + screenshot QA between rounds
Hub + deploy~20 min
Total, as of deploy~2 h 35 minwithin the 4-hour cap

Times are honest estimates from the session log, rounded. The ledger includes ~15 minutes of project setup that isn't a pipeline stage; stage times cover direction plus review of what came back.

03Who did what

Me — every call that shapes meaning
  • Watched the full 34-minute demo end to end — before any AI touched it
  • The feature pick, argued and owned
  • The positioning angle and the buyer read (lived experience with compliance teams)
  • The hero line, from four candidates
  • Every design veto: typography, color, the cards, the labels, dark mode
  • The ground rules: what stays local, what gets labeled, what never ships
Claude Code — scale, speed, and receipts
  • Parallel web research with cited sources
  • Local video processing: ffmpeg, Whisper, frame analysis
  • Design-system extraction from production CSS
  • Font matching by rendered specimen comparison
  • Build + screenshot QA loops; session memory across the project

04Ground rules that held

Anyone can ask AI for a landing page. The job is knowing what to build, why this one, and what not to ship — and having the system to do all of it before the clock runs out.