Foretex lets the expert work directly with a model of their own business's future. No consultants in the middle, no six-month project. The first iteration takes 30 to 40 minutes.
Demand forecasting, assortment planning
S&OP, line utilisation, output planning
Safety stock, lead times, networks
Cash gaps, payment calendar
Probability of default, arrears, provisions
Elasticity, revenue management
Rates, FX, commodities and their impact on the business
Payback, launching what has never existed
Software and services have been sold against each of these for decades. The problem is still not solved.
Annual indicators give you 5 to 10 observations, and over those years everything changed. The numbers aren't even comparable with one another.
Terabytes from the plant describe one part of the process over and over. They say nothing about what happens outside the regimes you've already seen.
A new product. A new plant. A scenario that has never happened.
Missing data doesn't excuse you from making the decision.
The methods and the data science already existed. What was missing was a system that speaks the expert's language. An LLM is the first tool that speaks both.
The expert explains how the business works and what has to be decided. About twenty questions; "don't know" counts as an answer.
What exists, in what shape, and how much of it can be trusted. Every column gets a passport; defects are stated.
The system assembles the model. The expert checks the links and assumptions and corrects them.
Parameters and distributions are fitted to history wherever history exists.
The expert sees what happens to the business in every scenario.
The system finds the best set of decisions within the constraints.
Then a new iteration, by reframing the problem.
Revenue, cash flow, profit. Accounting identities, not guesses.
Policy rate, FX, commodity prices. Nobody forecasts these; you decide which worlds to test.
Demand, deliveries. Fitted to your data where there is data.usually 10–20% of the model
Customers, dealers, borrowers. Thousands of agents acting on rules the expert can read.
Price, stock, capacity. The levers the optimiser searches over.
or free cash flow, output, service level: one metric is the objective, the rest become constraints
A scenario is a world, not a forecast. Pick one and see how the cost of funding for the quarter spreads across 1,000 runs, and how often it stays within target.
Each dot is 5 runs. Dots right of the target line breach the limit. Illustrative figures on hypersynthetic data.
Every number is labelled: computed from the project's tables, taken as an assumption, carried over from a finding, or flagged as an open question.
| Parameter | Value | Source |
|---|---|---|
Inflow rate elasticityinflow_elasticitySet to 0 until an estimate from inflow and rate-grid history is available. | 0 1/pp range 0 … 0.15 | assumption |
Monthly inflow volatilityinflow_sigmaMonth-to-month scatter of new-money volume; to be recomputed from monthly openings. | 0.25 σ (log) | assumption |
Current rate gridbase_ratesThe grid in force before the committee meeting, read from the latest effective rows. | 91: 12.8 · 181: 13.2 · 367: 12.4 | from data |
Pass-through of a rate cutfollow_shareNeither in the data nor in the expert's words yet. Goes on the list of questions. | ? | open question |
Each option below solves part of the problem. Foretex is built for the expensive, uncertain decisions that fall between them.
| BI with AI forecasting | Planning platforms | Simulation tools | Consultants or in-house data science | Foretex | |
|---|---|---|---|---|---|
| Time to first result | Minutes | Months of implementation | Weeks | 6–12 months | 30–40 minutes |
| Cost | Licence | Licence plus implementation partner | Licence plus specialist time | $0.5–1.5M per project | Staged: demo, PoC, production |
| Works with little or no data | Needs long history | Partly | Yes, if a modeller builds it | Yes | Yes: scenarios and simulators fill the gaps |
| Who builds the model | The tool fits a trend | Implementation partner | Specialist modeller | Consultants and data scientists | The domain expert, with the system |
| Expert can check the logic | Black box | Partly | Only modellers can read it | Through reports | Every link and number is labelled |
| Scenarios and tail risk | A confidence band on a trend | What-if on the plan | Yes | Per project | Thousands of runs, probability of breaching each limit |
| Optimisation under constraints | No | In specific modules | Add-ons | Custom-built | Built in |
| Your data | In the vendor's platform | In the vendor's platform | On your machines | Shared with the team | Demo on hypersynthetic data. PoC inside your perimeter |
Funding cost, deposit pricing, credit risk, liquidity
Use case coming soonCapacity, S&OP, output planning, new plants
Use case coming soonDemand, assortment, pricing, safety stock
Use case coming soonPrice scenarios, production, investment payback
Use case coming soonLead times, network design, inventory
Use case coming soonThe more of these that apply, the more a model beats a forecast.
If an ordinary forecast solves the problem well, use an ordinary forecast.
Foretex is for the rest: the decisions no boxed product covers and no consulting budget reaches. Bring the problem, not the data. The first demo runs on hypersynthetic data and needs no access to your systems.
Check your problem with usIn BI the effect is indirect. Here every decision taken on the model moves a specific number, and you see it straight away.
Better pricing and assortment. More output from the same capacity.
Less inventory without losing service levels. Lower capital requirements.
Ready for rare scenarios. A smaller catastrophic downside.
Pricing follows the three stages. Details are coming soon; contact us for a quote.
Price on request
Price on request
Price on request
Hypersynthetic data is a generated dataset that matches your real data in structure, scale, dependencies and business context, but holds none of your confidential information.
An expensive decision, material uncertainty or scenario risk.
On hypersynthetic data, with no access to yours.
If the demo shows value, we launch inside your perimeter.
We read every problem ourselves. If it is a fit, the next message is a proposal for the custom demo.