--- name: prescient-ai-docs description: Find and read the Prescient AI documentation. Use when a task needs guides, reference, or methodology for the Prescient AI marketing mix modeling (MMM) platform. --- # Prescient AI Docs Prescient AI is a marketing mix modeling (MMM) platform. Its documentation is at https://docs.prescientai.com. This skill tells an agent what the documentation covers and how to read it. ## When to use this skill Use this skill when a user asks how a part of the Prescient AI platform works, how to do a task in the platform, or what a term or a number in the platform means. Do not answer these questions from memory. Read the documentation and cite the page. ## What the docs cover - [Get started](https://docs.prescientai.com/index.md) (5 pages): A starting page for the Prescient AI docs, with a path for new readers, a card for each product area, and the ways to read the docs with an AI tool. - [Prescient AI](https://docs.prescientai.com/prescient-ai.md) (6 pages): What the first screen of the product shows, what you can ask in the chat, and which guide to read for each task. - [Library](https://docs.prescientai.com/library.md) (7 pages): What the Library holds, who can read a saved item, and which guide to read to save, share, export, or track a conversation. - [Model Center](https://docs.prescientai.com/model-center.md) (8 pages): What Model Center shows about your marketing mix models, what you can and cannot do there, and which guide to read for each task. - [Data Center](https://docs.prescientai.com/data-center.md) (13 pages): What Data Center is for, what each of its three tabs holds, who can change a connection, and which guide to read for each task. - [Attribution](https://docs.prescientai.com/attribution.md) (8 pages): What the Attribution page reports, the four sections of the page, and which guide to read for each task. - [Media Forecaster](https://docs.prescientai.com/media-forecaster.md) (6 pages): What Media Forecaster does, what a plan contains, and which guide to read for each task. - [Account and settings](https://docs.prescientai.com/account.md) (11 pages): Where to find the settings of your workspace and of your own account, what each page holds, and which guide to read for each task. - [Use the API](https://docs.prescientai.com/api.md) (3 pages): What the Prescient GraphQL API returns, where to send a request, and which page to read for each task. - [API guides](https://docs.prescientai.com/api/pull-modeled-metrics.md) (3 pages): Steps and code that copy each modeled metric row of a date range from the Prescient GraphQL API, one page at a time. - [API concepts](https://docs.prescientai.com/api/pagination.md) (4 pages): How the after argument and the pageInfo object of the Prescient GraphQL API split a large result into pages of 5,000 rows. - [API queries](https://docs.prescientai.com/api/queries/channel-names.md) (4 pages): Reference for the channelNames query of the Prescient GraphQL API, with its return type and an example request. - [API schema](https://docs.prescientai.com/api/types.md) (1 page): Reference for each object, enum, and scalar in the schema of the Prescient GraphQL API, with the fields and the values of each one. - [Reference](https://docs.prescientai.com/reference.md) (1 page): Lookup pages for each screen, control, option, status, limit, and message of Prescient AI, in the order of the product, with a glossary of the terms. - [Prescient AI reference](https://docs.prescientai.com/reference/prescient-ai/chat.md) (3 pages): Reference for the Prescient AI chat, with the topics that an answer can read, the header buttons, the status lines, the messages, and each limit. - [Library reference](https://docs.prescientai.com/reference/library/library.md) (1 page): Reference for the Library, with the tabs, the menu of an item, the visibility options, the save messages, the goal badges, and each limit of a saved item and a tracked goal. - [Model Center reference](https://docs.prescientai.com/reference/model-center/overview.md) (3 pages): Reference for the Model Center overview, with each summary tile, each field of a model card, the periods, and the empty states. - [Data Center reference](https://docs.prescientai.com/reference/data-center/channels-and-integrations-tabs.md) (6 pages): Reference for the two connection tables of Data Center, with each filter, column, row action, and badge. - [Attribution reference](https://docs.prescientai.com/reference/attribution/page-controls.md) (6 pages): Reference for the Attribution filter bar, date range presets, and comparison periods, with each default and limit. - [Media Forecaster reference](https://docs.prescientai.com/reference/media-forecaster/plan-settings.md) (3 pages): Reference for the Timeline, Goal, and Budget steps of the Media Forecaster New plan wizard, with each option and limit. - [Account and settings reference](https://docs.prescientai.com/reference/account/settings.md) (4 pages): Reference for the tabs of the Settings page, the display currency options, the API key rules, the subscription statuses, and the cookie categories. - [Glossary](https://docs.prescientai.com/reference/glossary.md) (1 page): Short definitions of the terms that the Prescient AI docs and the product use, in alphabetical order, each with a link to the page that covers the term. - [What's New](https://docs.prescientai.com/whats-new.md) (1 page): A dated list of the changes to the Prescient AI product, the API, and the docs, with the newest change first and an RSS feed. The full page list, in navigation order, is at https://docs.prescientai.com/llms.txt. ## How to read the docs 1. Fetch `https://docs.prescientai.com/llms.txt`. It lists every page with a one-line description and a link to the Markdown version. 2. Fetch a page as Markdown. Add `.md` to the page URL, for example `https://docs.prescientai.com/index.md`. A request to the page URL with the header `Accept: text/markdown` returns the same Markdown. 3. To load all pages in one request, fetch `https://docs.prescientai.com/llms-full.txt`. 4. To search, connect to the MCP server at `https://docs.prescientai.com/mcp` (Streamable HTTP, no authentication). It has three tools: - `search`: find the page sections that match a query. - `read`: get one page as Markdown, or list the page paths. - `submit_feedback`: report a page that is incorrect, outdated, confusing, or incomplete. 5. To find what changed, read the What's New page at `https://docs.prescientai.com/whats-new.md`, or the RSS feed at `https://docs.prescientai.com/whats-new/rss.xml`. ## Rules - Use only what the documentation says. If the documentation does not answer the question, say so. - Cite the URL of each page you use. - Use the page URL without `.md` when you give a link to a person. - If a page is wrong or unclear, report it with `submit_feedback`.