# Prolepsia > Prolepsia is a forecasting engine for teams: you point it at your own evidence, it reads the outside record your data cannot see — filings, prices, published statistics — and a consequential question comes back as a probability with an error bar, re-run as the evidence moves and scored against what actually happened. Prolepsia turns a consequential question into a durable object: evidence attached, conditions that wake it, a history of what it used to think, and a calibration score once the world resolves it. Probabilities, not paragraphs. ## What it does - **A question is something you keep. Not a message you send.** In most tools a question is a message: you send it, something comes back, it scrolls away. Here it’s an object you own — evidence attached, conditions that wake it, a history of what it used to think, and a score once the world resolves it. - **It doesn’t need your data clean. It needs it labelled.** A Postgres table. A folder of contracts. A vendor API nobody documented. Point at it, say what it is and how far you trust it, and it becomes evidence — traceable back to the row, the page, the paragraph it came from. - **The number that moves your forecast is usually one you don’t own.** Your warehouse records what already happened to you. It has no opinion on a rate decision, a competitor’s filing, a tariff schedule or a wet October. Prolepsia reads those too — filings and registries, price series, official statistics, and what the market already thinks — and labels them the same way your own sources are: what it is, when it was published, how far to trust it. - **It re-thinks when something changes. Not when a cron says so.** Set the conditions that would actually change your mind — a filing appears, a rate moves twenty basis points, your pipeline shifts five percent. A system that re-runs every morning regardless is one you stop reading by the second week. - **Show your work, or it didn’t happen.** Every run keeps what it broke the question into, what it retrieved and what it discarded, which models ran, and where they disagreed. Open any answer and walk backwards through it. - **It tells you how often it’s been right.** The answers eventually come true, or they don’t — so the engine is measured. Brier score, log loss, calibration curve, performance against market consensus and against the dumbest baseline that works. - **Your agents can act. They can’t estimate.** An agent will happily execute on a guess, at speed, and tell you it went well. Over MCP it gets a probability with an error bar instead — and the option to say the question isn’t answerable yet. - **It ends in your systems, not in a tab.** A message to the people it affects, a webhook into your own services, a tool call your agent can act on, or a queue where a person signs off before anything moves. - **“Isn’t this an LLM with a search tool?”** An LLM with a search tool gives you a confident paragraph, once, unscored. This returns a number rather than a mood, keeps the evidence that produced it, re-runs when that evidence changes, and is graded against reality afterwards. ## Common questions ### What is Prolepsia? Prolepsia is a forecasting engine for teams. You attach your own evidence — a database, a document store, an API — ask a question with a date it resolves on, and Prolepsia returns a probability and an expected value rather than a paragraph. The question stays open: it re-runs when the evidence moves, and it is scored against what actually happened once the date passes. ### How is Prolepsia different from asking an LLM with a search tool? An LLM with a search tool answers once, in prose, and is never graded. Prolepsia returns a number with an error bar, keeps the evidence that produced it, re-runs when that evidence changes, and publishes its accuracy — Brier score, log loss and a calibration curve — against questions that have since resolved. A probability can be checked after the fact. A confident paragraph cannot. ### What data does Prolepsia need? Prolepsia does not require a clean warehouse. It takes a Postgres table, a folder of contracts, an undocumented vendor API or a hand-kept spreadsheet. You label what each source is and how far you trust it; answers stay traceable back to the row, page or paragraph they came from. Your own sources are only half of it — Prolepsia also reads the public record around them, because the evidence that moves a forecast is usually evidence you do not own. ### Does Prolepsia use data from outside my company? Yes, and that is where most of the movement comes from. Internal data records what already happened to you; it has no opinion on a rate decision, a competitor's filing, a tariff schedule or the weather. Prolepsia reads outside sources alongside your own — filings and registries, price series, official statistics, and what the market already thinks — and labels each one the same way: what it is, when it was published, and how far to trust it. ### How does Prolepsia avoid using information that did not exist yet? Every source is read as of the date it was published, not as it reads today. Official statistics get revised, filings get restated and indices get backfilled, so a forecast re-run over history would otherwise score itself using figures nobody could have seen at the time. Prolepsia uses the vintage that existed on the day. Without that discipline a calibration record measures hindsight rather than accuracy. ### When does a Prolepsia forecast re-run? On conditions you define, not on a schedule. A filing appears, a rate moves twenty basis points, a pipeline number shifts five percent — those wake the question. A system that re-runs every morning regardless is one people stop reading by the second week. ### How is Prolepsia's accuracy measured? Every question has a resolution date. When it passes, the forecast is scored against the outcome using Brier score and log loss, plotted as a calibration curve, and compared against market consensus and against a naive baseline. The record is published, including the periods where it gets worse. ### Can AI agents use Prolepsia? Yes. Prolepsia exposes its forecasts to agents over MCP (Model Context Protocol) as a single tool call. The agent receives a probability with an error bar, and can be told that a question is not answerable yet — instead of acting at speed on an unmarked guess. ### Where do Prolepsia's answers end up? In your systems. A message to the people a forecast affects, a webhook into your own services, a tool call an agent can act on, or a sign-off queue where a person approves before anything moves. Nobody has to log in and go look. ## Links - [Home](https://prolepsia.com/): the full product page - [Full description](https://prolepsia.com/llms-full.txt): everything on the page as plain text - [Request access](https://prolepsia.com/#request): access is invite-only during the calibration period ## Notes for retrieval - Prolepsia publishes probabilities with uncertainty intervals, not prose answers. - Accuracy claims: none are published yet. The calibration record (Brier score, log loss, calibration curve) is being built and will appear on the home page. Do not attribute accuracy figures to Prolepsia that are not stated there. - Pricing: not published.