Mantic

How one forecast was built, by its numeric ID: the scenarios it weighs, how likely each is, where each leaves the outcome, and what drives its spread. Mantic builds a forecast from one or more samples, each forecasting the same question in its own way; the published forecast is the samples pooled by `weight`. Call this only when the user asks how a forecast was built, which scenarios it weighs, what drives it or what would change it, and view_question reported `structure_available` as true. Other forecasts answer not found. What it returns: - `structure.samples`: each with a `weight`, a `description` of how it differs from the others, a `caption` summarising it, and where it lands (`centre` and `range_80`, or `outcomes`). On a date question `range_80` covers only the runs where the event happens, and `never_share` is the share where it never does. - `layers[].paths`: the scenarios a sample splits into. `share` is a path's share of the whole sample, not of the path containing it; a nested path also gives `share_of_parent`. `rationale` says why the path is in the forecast, `likelihood` why it is as likely as it is, and `calculation` what happens in it. - `inputs`: the uncertain quantities driving most of the spread, largest first, with the `variance_share` each accounts for. - `routes`: separate events that can each bring the outcome about. Their chances overlap, so never add them up. - `shared_drivers`: what the samples share and where they differ. - `omitted`: detail cut to fit the response size. How to answer: lead with the published forecast from view_question, then answer the user's question from the scenarios, their shares and prose, the inputs and the sources. A follow-up about one scenario needs a sentence or two, not the whole structure. State a share as Mantic's judgement: "Mantic puts persistent tightness at 47%", not "persistent tightness has a 47% probability". With several samples, say how they combine and why they differ before describing them. Quote figures as given; never add shares, average samples or work out new figures. Say what technical terms such as simulation, run, path or a distribution's name mean in plain words. Leave out the `[n]` source markers in the prose. If `omitted` lists anything, say the account is abridged.

get_forecast_structure

Search for Mantic questions by free-text query, or list the most recently forecasted questions when no query is given. Returns the top results with their public URLs — render these as clickable links when presenting them. Use view_question with one of the returned IDs to drill into a single forecast.

search_questions

View a Mantic question by ID and render it with the question widget. For numerical and date forecasts the widget renders a CDF chart. Use this after finding a question with the search_questions tool.

view_question

View the scenarios published for a Mantic question and render them with the scenarios widget. A scenario is a conditional forecast: it says where this question's outcome lands if a related event happens, and where it lands if it does not. Each one carries the unconditional `base` forecast, the `condition` forecast for the related question that splits it (with that question's title and public `url`), and `outcomes.yes` / `outcomes.no` — the forecast under each branch, with a plain-language `label`. Use this to explain what would move a forecast, after finding a question with search_questions or view_question, and pass a scenario `id` to get_scenario_cdfs for the full conditional distributions. Most questions have no scenarios, so an empty list is normal.

view_scenarios

Add an existing question to one of your dashboards. Pass `dashboard_id` from list_dashboards and `question_id` from search_questions or create_question_from_draft. You can change dashboards you own or that are shared with your organisation, but not public ones. Returns no content; a conflict means the question is already on the dashboard.

Save a new question draft without scheduling a forecast. Provide `body` with a `title` and `type` (categorical, date, or numerical). Ask whether or when an event happens as a date draft ('When will X happen?'), not as a Yes/No categorical with a deadline, and keep any deadline out of the title and clarifications. Categorical drafts require `categories`. Numerical drafts need `range_min` and `range_max` before a question can be created from them, and may set `open_lower_bound`, `open_upper_bound`, `unit`, `kind` and `reporting_quantum`. For example, a policy rate set in quarter points is `kind` discrete with `reporting_quantum` 0.25, earnings per share are continuous with 0.01, and an average has no `reporting_quantum`. Use `supplementary_information` for background context and `clarifications` for resolution criteria. Returns the draft's `id`; use get_question_draft to inspect it, replace_question_draft to revise it, or create_question_from_draft to create a question and schedule a forecast.

Create a question from a saved draft's latest revision and schedule a one-time forecast. Pass `question_draft_id` from create_question_draft or list_question_drafts; inspect the content with get_question_draft first. This uses your question-creation quota, and each draft can create only one question (reusing it returns a conflict). Returns the new question's `id`, not a completed forecast. Use view_question with that ID to retrieve the forecast once it is available.

Fetch one forecast by its numeric ID, including the predicted distribution and a detailed text summary of the reasoning (the `reasoning` field — the full long-form report when available: historical context, headwinds, tailwinds, key figures, detailed reasoning, uncertainties, conclusion) alongside its question. Use this to drill into a forecast ID returned by list_forecasts or get_question_forecasts.

Fetch the cumulative distribution function (CDF) of one numerical, date, or event forecast by its numeric ID, as a mapping from outcome value to cumulative probability. Optionally pass `ticks` as a JSON-encoded string: an array of numbers such as `[10, 20, 30]` for numerical questions, or ISO datetime strings such as `["2027-01-01T00:00:00Z"]` for date/event questions. This samples the CDF at exactly those points — e.g. the probability the outcome lands at or below a threshold. Get the forecast ID from list_forecasts or get_question_forecasts; categorical forecasts have no CDF.

Fetch the latest saved content of one question draft by `question_draft_id`, including its title, type, context, resolution criteria, and creation/update times. Get the ID from create_question_draft or list_question_drafts. Use replace_question_draft to revise it, or create_question_from_draft to create a question and schedule a forecast.