> For the complete documentation index, see [llms.txt](https://help.brieftech.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.brieftech.ai/get-started/readme.md). # Brief Tech Overview BriefTech is an AI production infrastructure for dispute lawyers. It processes raw evidentiary files: PDFs, emails, spreadsheets — into court-ready work product: indexes, court bundles. ## The four-step pipeline Every matter in BriefTech follows the same pipeline: | Step | Tab | What happens | | -------------- | -------------- | ------------------------------------------------------------------------------------------------ | | **1 — Upload** | Files | Documents are converted to PDF, OCR'd where needed, and added to the search index automatically. | | **2 — Review** | Review | You correct document metadata: dates and descriptions. | | **3 — Index** | Index | You build the Document Index — ordered, structured, numbered. | | **4 — Export** | Index → Export | You generate a paginated PDF court bundle, or export the Document Index as DOCX/Excel. | BriefTech runs two workstreams in parallel throughout your matter: **AI analysis** — Agents extract key facts, classify documents, and organise the files automatically. The output is a structured, reviewable layer of work your team didn't have to do manually. **Human review** — Your team works directly on the AI output: accepting, correcting, and refining until the work product is court-ready. Invite colleagues to a shared matter, assign permissions, and collaborate in real time. {% hint style="info" %} The AI handles the extraction and classification. The lawyers own the judgment calls. {% endhint %} ## Key concepts | Concept | What it is | | ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Matter** | A single case. All documents, annotations, and exports for that case live here. | | **Document Index** | The structured, ordered index that becomes the spine of your court bundle. | | **Credits** | The unit BriefTech uses for billing, based on a document's page count. A document is charged once — the first time you export it, add it to a court bundle, or run Force OCR on it — at 1 credit per 50 pages (minimum 1). Uploading, processing, and running AI agents do not cost credits. | | **Collection** | A named subset of documents within a matter, used to segment the document set. | | **Preset** | A saved Document Index configuration (columns, serial numbers, bundle settings) applied in one click. | ## How this help centre is organised The help centre is split into three sections — pick the one that matches what you need right now: * **How-To Guides** — short, goal-oriented steps for getting a specific job done. Grouped into nine sections that follow the flow of a matter: Upload Files, Process Files, Extract Data, Organise Documents, Review Documents, Index Documents, Build Bundles, Export Files, Manage Account. * **Reference** — exact fields, limits, settings, and formats, as a single flat list. * **Concepts** — background reading about how and why BriefTech works the way it does. {% hint style="success" %} **New to BriefTech?** Start with the [tutorial](/get-started/your-first-matter.md) — about fifteen minutes, using sample files, no real case data needed. {% endhint %} The structure follows the [Diátaxis](https://diataxis.fr) framework: each page is written as exactly one kind of content (how-to, reference, or concept), so you always know what you're getting. *** ## Need more help? Contact the BriefTech support team at . *** ## Where to go next
Your first matterA guided, end-to-end first run — take a practice matter from sample files to a downloaded court bundle./pages/JElpS8iDIgC3KPHk5auM
How a matter moves through BriefTechThe staged pipeline and the two workstreams that run alongside it./pages/p87rZDZKq7GzvEb7cREo
How AI analysis worksWhat the agents extract, classify, and organise — and where your judgment comes in./pages/pLl4zmTHql9gsVVTXlhP
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://help.brieftech.ai/get-started/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.