SYSTEM ARCHITECTURE
Built in the lab·Verified against the live system·For vetted investors only

The system behind the research,
not just the research itself.

Data lineage, validation gates, operating cadence, and the architecture that keeps one wrong number from compounding into a bad decision. Built to be inspected, not taken on faith.

// Data

Every figure traces to a filing, not a vendor's summary of one.

The filing is the data — the 10-K, the transcript, the footnote. Nothing is trusted from a single source.

Price works the same way. Only the close matters, captured within minutes of it — not the noise in between.

External Landscape 70+ exchanges · 150,000+ listed securities · multiple independent data providers Primary Filings & Market Data indices chosen for filing-standard consistency, not size alone Verified Universe 1,804 COMPANIES Mechanical Filter margin, return-on-equity and debt thresholds, re-run nightly Composite Q·G·V Filter quality, growth and valuation scored together, not in isolation Shortlist ranked, and re-ranked every night Per-Thesis Pipeline
MARKET DATA EDGAR FILINGS TRANSCRIPTS 10-Ks 8-Ks
VERIFIED FILING CORPUS 5–10 YRS
The filing itself, not a restatement of it

U.S. fundamentals come straight from the primary regulatory filing. Markets without an equivalent filing regime use a general-purpose market-data provider — but only for screening. That data is never the basis for a thesis: fresh figures are sourced directly from the company itself before any thesis is written, so a screening-stage gap never reaches a decision unchecked. Where a figure can't be reached from the automated sources — insider ownership, for U.S. tickers — it's excluded from scoring rather than estimated, then sourced directly from the proxy filing at research stage. A known gap is worth more than a convenient guess.

// Quality

Errors are treated as a system problem, not a one-off mistake.

A wrong number caught once and fixed once will happen again somewhere else. Every correction here is traced to its root cause, checked for every other place the same mistake could occur, and closed off with a rule that prevents the whole class of error — not just the instance that got noticed.

01 · DIAGNOSE

Root Cause

Not just what was wrong, but why the system produced it — traced to the specific step, rule, or assumption responsible.

02 · SWEEP

System-Wide Sweep

Every other record that could carry the same error is checked, not just the one a person happened to notice.

03 · CLOSE

Permanent Rule

The fix is written back into the process itself, so the same class of error can't recur silently.

Applied the same way whether the error is a mispriced trigger, a mislabelled metric, or a process that stalled and should have resumed on its own.

PRE-PUBLICATION

Sourced Before It Ships

Every numeric claim is checked against the source document it's attributed to before a report is finalized — not spot-checked after the fact.

CROSS-EXAMINATION

Disagreement Is Signal

Disagreements between independent functions are surfaced, not smoothed over. A quiet, immediate consensus is a reason to look closer, not a green light.

CONTINUITY

Nothing Silently Drops

A process that stalls partway through resumes automatically from where it left off, rather than quietly failing and going unnoticed.

// Systems

A real operations stack behind the research — not a script calling an API.

The parts that don't show up in a report are what make the reports possible: a system of record for every decision, a workflow layer that gives every task and correction a durable history, and infrastructure that's encrypted and monitored the way any production system should be.

SYSTEM OF RECORD

Structured, Not Scattered

A queryable record of every company's current status, decision history, and pricing data — not a folder of documents that drifts out of sync with reality.

WORKFLOW & AUDIT

Every Task Has a History

Every research task, correction, and incident has an auditable lifecycle — opened, worked, resolved, and traceable afterward, the same discipline a real engineering team runs on.

CONTINUOUS MONITORING

Watches Its Own Health

The system monitors its own health as closely as it monitors the market — a stalled or silently failing process is visible immediately, not discovered days later.

ENCRYPTED AT REST & IN TRANSIT

Not an Afterthought

Data is encrypted at rest, and every external connection runs over TLS with certificates that rotate automatically well before they expire. Internal traffic never leaves the machine.

EACH MARKET'S OWN CLOSE

Not One Global Batch

Prices update as each exchange closes in its own timezone — the Australian close is captured while London is still trading, and London's while New York runs. Every position's trigger is re-evaluated that same night, against every market's most recent close.

SINGLE OWNER

Local hardware with LLM independence

The system was designed to keep data secure — local dedicated hardware, not cloud infrastructure. Each function's frontier LLM, and the provider behind it, can be swapped independently; nothing here depends on one vendor.

// Processes

The system runs on a fixed rhythm, not a request queue.

Coverage doesn't wait for someone to ask for it. Each layer runs on its own cadence, and a company only enters the slow, adversarial part of the cycle once the fast, mechanical part has already done its job.

NIGHTLY

Full Rescreen & Rank

Every company in the universe is re-evaluated and re-ranked against current filing and market data — every night, not on a slower cycle.

Re-Ranked Shortlist
ON CHANGE

Shortlist Review

When the shortlist's membership actually changes, the ranked list is reviewed and the candidates worth acting on are handed to the recommendation function. Unchanged nights don't manufacture a review.

Escalated Candidates
DAILY

Trigger Watch

Every open position carries a trigger price. Each market's close is captured within minutes of that close, and every position is re-evaluated against it the same night. We don't trade, so we don't watch ticks.

Standing Alerts
PER-THESIS

Independent Pipeline

A full four-function research cycle runs on demand for any company, on the same fixed sequence and standards every time.

Independent Recommendation
POST-DECISION

Calibration

Every closed decision updates the benchmarks the next one is measured against — the process gets stricter over time, not just busier.

Compounding Standards
// Functions

Four functions, and a chain that has to hold.

Research establishes the base, straight from the filings — there's nothing before it to read. Everything after it works differently: Valuation prices what Research found, Challenge is tasked with finding what's wrong in both, and Recommendation reads all three and is free to disagree, as long as it says why. Agreement isn't assumed anywhere in that chain; it has to hold up.

01 · RESEARCH FUNCTION

Research

Builds the case for what the business is and what it's worth owning, from the filings up — with no visibility into the valuation or challenge functions' output.

Research Analysis
02 · VALUATION FUNCTION

Valuation

Independently prices the business under bear, base, and bull assumptions before seeing any challenge to the research it's built on.

Investment Thesis
03 · CHALLENGE FUNCTION

Adversarial Review

Given the research and valuation together for the first time, and tasked with finding what's wrong with them — not confirming what's right.

Adversarial Challenge
04 · RECOMMENDATION FUNCTION

Independent Recommendation

Reads all three outputs and forms its own view, including where it disagrees — nothing here is an average of the others.

Final Recommendation
// Architecture

No single step is allowed to average away a disagreement.

The point where separate conclusions get folded into one is the single highest-risk step in any automated system — it's where an error is most likely to get laundered into something that looks like consensus. This architecture is built specifically to avoid needing that step.

01 · VERIFY

No Blind Acceptance

A function can read what came before, but a claim only survives by holding up against the same source material — not because an earlier stage already accepted it.

02 · PRESERVE

Disagreement Survives

Where two functions reach different conclusions, both are kept and shown — not blended into a single smoothed-over number.

03 · RE-CHECK

Errors Don't Compound

A wrong figure introduced at one stage is checked again, independently, at the next — rather than carried forward and trusted because an earlier stage already used it.

This is the same principle that governs data sourcing and error correction elsewhere on this page — independence isn't a feature of one part of the system, it's the design constraint the whole thing is built around.

// Standard

The standard doesn't stop at the research.

A recommendation is only as good as the system that produced it. So the system is held to the same standard as the research itself — every number traceable, every process auditable, and nothing accepted from a single source without a way to check it.

The rigor a vetted investor would expect from operational due diligence on any real research desk applies here by default, not by request. The data pipeline, the correction process, and the review architecture are all built to be examined — not just described.

If a claim about the system can't be traced to a specific process, log, or check, it doesn't belong on this page.
5
Independent operating cadences, from nightly to per-thesis
4
Independent functions in a chain that has to hold
1,804
Companies verified and re-ranked, every night