IC.
GITHUBGH ↗ LINKEDININ ↗
SYSTEM 002 · HIRING SIMULATION · PUBLIC + LIVE

Liveweek.

Desktop OS - a candidate's simulated first week, quietly scored on how they think, not what they claim.

TRY THE SIMULATION →ALL SYSTEMS

30 SECONDS INSIDE THE SIMULATION - FROM THE LAUNCH FILM, RENDERED IN CODE

01 · THE PROBLEMWHAT WAS BROKEN

Resumes don't show how someone works under a real week's pressure. Interviews reward performance; work reveals judgment. So the interview became a week of work.

02 · THE SYSTEMWHAT SHIPPED · WHO USES IT
The Liveweek desktop mid-fire: WhatsApp decision card, Metabase clone, Discord, dockThe in-sim Metabase clone running a real SQL query over the seeded warehouseThe login screen - the workday drifting behind frosted glass

REAL SIM SCREENS · THE DESKTOP MID-FIRE · THE SQL ENGINE RUNNING · THE LOGIN

A hidden evaluator scores prioritization and written thinking as they work.

The hire came from the simulation, not the resume.

173candidates ran it
31finished the week
1hire made

SOURCE: Hiring panel · July 2026

03 · UNDER THE HOODWHAT ACTUALLY HAPPENS

Pick a moment. Watch the calls the system makes that no one sees.

CODEA CHECKTHE CLEVER BIT00/07
THE THINKING BEHIND EACH STEP
01The login is the idea in one frame - the workday adrift before you sign in, so you know this is a week already alive, not a quiz waiting on you.
02Should reading up on last week count against you? No - preparation is free while the clock sits frozen at 9:45, because the test has not started until you press start.
03A hiring test has to be fair before it can be predictive, so every candidate's day starts at exactly 10:00 and runs the same length - same conditions, comparable scores.
04Why does the clock run? Because time has to be scarce for prioritizing to mean anything - it advances whether you act or not, so you cannot do everything and must choose.
05How do you tell someone who stepped away from someone who is working? Watch two signals - tab visible and network up. Lose either and you count as gone, not deciding.
06A dropped connection or a bathroom break is not a hiring signal, so the clock is held instead of drained - your week can never quietly burn down while you are gone.
07Should thinking cost you time? We decided care should not, but dithering should - so the clock freezes while you type, halves while you read, and a tooltip tells you exactly that.THE CLEVER BIT

EVERY STEP MINED FROM THE REAL BUILD · NOTHING INVENTED

04 · WHY NOT ONE PROMPTWHAT A ONE-SHOT WOULD HAVE GOT WRONG

One prompt did produce a version of this - and it is the reason the real one exists.

  1. The one-shot was built, and rejected. The first pass read as a toy - and a toy cannot measure how someone works.
  2. The realism came from a real dump. Mined from real office conversations, then fictionalized by design - role names, invented numbers, a stand-in product. No prompt contains that raw material.
  3. The scoring is an accreted rubric. Cold runs exposed false negatives - a diligent candidate pulled a number a day early. Every guard cites the run that broke it.
  4. The data layer was rebuilt on a taste call. Canned dashboard answers were replaced with a hand-written SQL interpreter over a seeded warehouse, purely because canned numbers felt fake. One prompt does not make that call.
05 · THE DIRECTIONWHERE THE HUMAN WAS
THE FORK · WHAT THE AI PITCHED VS WHAT I SENT

Two days in, the first playable build: one HTML file with invented app interfaces - a WhatsApp that looks nothing like WhatsApp.

WHAT THE MODEL HAD BUILT

Its default: approximate the apps, invent the icons, ship a stylized demo of an office instead of an office.

WHAT I SENT BACK · TYPOS KEPT

the UI of the apps should reflect real UI more accurately - whatsapp does not look like how you coded it. [...] This feels like a toy demo - nothing like a real website - feels really half baked really - dissapointed. [...] this is not a brand new concept - so let us not re-invent the wheel, let us use the current wheel and build on it

That message is why every app is a pixel-faithful clone in real brand hexes - the desktop a proven open-source OS pattern, not invented.

SESSION TRANSCRIPT · 2026-06-06 · QUOTED EXACTLY · [...] MARKS OMITTED SPEECH

The realism IS the test - you can only measure how someone works if the tools work like the real ones.

8 decision records8 app replicas, exact hexesfictionalized by designheadless sim-QA harnessHOW IT WAS RUN, NOT HOW IT WORKS
NEXT SYSTEM Shikho Intelligence →
▸