OPERATIONS
One screen·Fifteen seconds·Then you decide

You don't arrive and start looking.
You arrive and start deciding.

The desk has already done the looking before you sit down. This is how a working day actually runs — the automated backbone, the handoffs, and the moments that genuinely need a person.

// Concept

09:00. Coffee down. One screen, and it has already done the looking.

Not an inbox. Not a folder of PDFs. What's waiting is specific rather than generic — each item there because a condition was met overnight, not because a report ran on a timetable.

A thesis on a regional bank holding is sitting in review — written overnight, 22:04 to 22:48, while nobody was here. You approved it yesterday; it ran on its own. Beside it, the book: seven BUY, eighteen WATCH, twenty-five active positions — the whole thing, not a sample.

Then the part that actually gets read first.

Watch Triggers23:37 close
██.██ A$1.33 vs A$1.20–A$1.54 🔔
███ $1,805.82 vs $1,700–$1,900 🔔
██.█ £3.41 vs £1.90–£3.43 🔔
████ $289.15 vs $248–$270
██.██ A$5.84 vs A$4.00–A$5.37
Three positions crossed into range overnight. Two sit above their range, doing nothing, correctly quiet. Tickers redacted for this page — the prices and ranges are real.

Underneath, what changed at the companies actually held or watched: thirteen real filings, not headlines — a director departure, a material agreement, a couple of routine regulatory filings, a leadership change. Categorised, dated, scoped to positions that exist. Not the whole market's news.

And a research pack dated this morning, on a company the mechanical screen originally rejected — it came back through the near-miss route and produced a complete four-document pack overnight.

That's roughly fifteen seconds of reading. In that time: what's being worked on, what's come into range, what changed at the companies held, and what finished overnight. Now comes the only part that needed a person — open the position that matters, read where the analysts disagreed and who gave ground, check the conditions written down before the price moved, and decide.

// Handoffs

Every handoff has a name. Nothing passes silently.

The desk is a chain of specific handoffs, not a black box — each one a named node passing a specific artifact to the next.

Screen
Shortlist
Review
Approval
Research
Valuation
Challenge
Recommendation
Sideways, not downstream: Trigger Monitor → Signal Ticket → Desk. Watchdog → Alert.
The only node that requires a person is Approval — everything either side of it runs on its own.
// Activities

Nothing runs because it's Tuesday.

Every activity below has a stated trigger — a market close, a completed scan, a changed shortlist, a crossed price, or a person's decision. None run on a bare timetable.

TRIGGER: MARKET CLOSE

Per-Market Price Refresh

Each exchange's prices update within minutes of its own close, staggered through the day and night — not one global batch run regardless of whether a market has actually closed.

Fresh Trigger Data
TRIGGER: SCAN COMPLETE

Shortlist Review

Fires only when membership actually changed — a name entered or left the Core Watchlist, the top five moved, a near-miss appeared. A quiet night creates no work.

Scoped Review, With Its Reason Stated
TRIGGER: JOB COMPLETION

Integrity Check

Before anything else happens, something checks that every job that should have run, ran — a completion record, not a health guess. A failure is known before anything else is.

Verified Overnight State
TRIGGER: STALL OR LOCK

Self-Healing Sweeps

A stalled-job sweep, a stuck-lock monitor, and a capacity watchdog run continuously underneath. Blocked work is marked with its exact unblock condition and picked up automatically — nothing sits silently stuck.

Recovered Work, Not a Silent Stall
TRIGGER: PERSON'S DECISION

Approval

A thesis cannot start without a person's approval, and the approval itself is recorded — a timestamped trail of every decision to begin research, not just the conclusions it reached.

Authorised, Auditable Start
TRIGGER: AD HOC REQUEST

Off-Menu Work

An investigation into one company. A management-quality report. A competitive-intelligence report. Or a workshop — one question put to independent functions at once, disagreements preserved, one document at the end.

Scoped, On-Demand Output
// Rules in Action

Every rule below exists because something real happened once.

Not policy for its own sake — each one is a governing rule paired with the dated event that caused it, or a live case of it firing.

One thesis at a time

Contention-Aware Scheduling

Thesis cycles are queued and released one at a time rather than run concurrently — because concurrency once exhausted a shared capacity limit mid-thesis and lost the work. Research now queues rather than collides, and a cycle that starts, finishes.

Approval before research

Pre-Approval & Initiation Trail

Research doesn't start because someone felt like it. Every decision to begin coverage on a company carries an approval record and a timestamped log — an audit trail of intent, not just outcome.

A screened-out name isn't necessarily wrong

The Near-Miss Tier

A genuinely good business was once screened out on a single-year metric distorted by an accounting artefact. Rather than special-case that one name, it was workshopped across every independent function, spec'd, signed off five times — one sign-off catching a real error and forcing a revision — and shipped as an additive tier that changed no existing threshold. It carries its own guardrails: a hard ceiling on how many names it can carry, mandatory filing citation at intake, and an automatic drop if a name fails to normalise by the next cycle. That tier is still running: it's what produced this morning's research pack, and near-miss names now carry a higher burden of proof — adversarial review happens before valuation, not after.

Every job proves it ran

Self-Healing Infrastructure

A stalled-job sweep, a stuck-lock monitor, and a nightly freshness check that reports what it repaired — because work once sat blocked for fourteen hours before a person noticed. Now blocked work names its own unblock condition and resumes on its own.

Signals get checked before anyone reasons about them

Signal Triage, Person-First

A real "Board Attention" ticket, two flagged filings, both tagged with the same generic regulatory label. One turned out to be a routine buyback expansion — checked against the actual filing, closed inline, no action. The other had genuinely crossed its trigger — so rather than reasoning it through inline, a narrowly-scoped child task was opened for further work, with an explicit note that a full thesis cycle still needed separate approval. Hold-or-delegate, decided by checking the primary source first — never by the label a scanner attached.

// Standard

Judgement is the scarce resource. Everything else is built to protect it.

A desk that makes you go looking for what matters has already failed you before you've made a single decision. So the system takes the looking away from the person entirely — the screening, the checking, the routine review — and leaves only the part that actually needs judgement: does this change what I believe, and what do I do about it.

That's not a convenience feature. It's the whole point of running research operationally instead of manually — the fifteen seconds of reading exists because a great deal of unseen work happened first, on a stated trigger, with a stated reason, and a record of what it found.

The desk does the looking. You do the deciding. Everything in between is built to make sure that division never blurs.
15s
To know what's being worked on, what's in range, and what changed
1
Node in the whole chain that requires a person: Approval
0
Activities that run on a bare timetable — every one has a stated trigger