The archive.
Forty-nine million public documents, read as they appear, kept with their date, source and language.
1.6 million sources · Many languages · Read continuously
A language model remembers the world loosely and without dates. Noah keeps it precisely, so a question about next quarter is answered against what was known, and when.
The archive is not a search index. Every document is tagged on arrival: who, where, what kind of event, which market, which risk. That tagging is what lets the physics compare this week with the same week last year, or one country with its neighbours, in numbers rather than impressions.
- 01News and specialist media
- 02Company filings and results
- 03Regulators, courts, parliaments
- 04Markets, prices, prediction markets
- 05Public datasets and official series
- 06Fifteen months of instrumented history
The physics.
Deterministic Python runs before any language model writes a word. The model explains the numbers. It does not invent them.
Measured first · Written second
Tagging
Every document is classified on arrival: actors, places, event types, markets and risk areas, with its date kept.
Pressure
How much signal is building around a subject, compared with its own history and with its peers.
Regime
Whether a subject is in a calm, building or breaking state, and how long such states have lasted before.
Couplings
Which subjects move together, so a shock in one place can be read across to the others it drags.
Calibration
Probabilities are scored against resolved questions, so a 70 means something close to 70.
Evidence kept
Every number carries the documents it rests on, with dates, so the answer can be checked rather than believed.
Five shapes of answer.
You ask in plain words. Noah chooses the shape, runs the physics and hands the result to your AI with the evidence attached.
Risk · Probability · Outlook · Edge · Opportunity
How risky is it?
A place, a sector, a counterparty or a journey, read from the record, this quarter and next.
How likely is it?
A named event by a named date, as a probability with its range, drivers and counter-evidence.
Where is it heading?
A subject month by month, with the watchpoints that would change the path.
Is the market right?
Noah's reading beside the market price, so you can see where they disagree and why.
Where is it moving?
A scan across a sector for the subjects gaining signal before the price has noticed.
Back-test any of them as of a date in the past.
As of any past date.
Name a date. Noah limits itself to what was in the archive by then, runs the same physics, and gives you the forecast it would have given. Then compare it with what happened.
The same engine, limited to the cutoff
This is how you test a theory before you trust it, and how you test Noah before you pay for it.
Back-tests use the full engine, not a thinned one. The only thing that changes is the cutoff. Fifteen months of instrumented history means there is room to run the same question at several dates and watch the probability move.
The bigger the model, the better the forecast.
Noah supplies the evidence and the arithmetic. Your model reads it, argues with it and writes the answer in your voice. When the model improves, so does the result.
Read-only. Your questions stay with your AI.
Noah hands evidence out. It does not take your prompts, your files or your conclusions in. Nothing you ask becomes our content.
Connect ChatGPT →