> 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/concepts/the-matter-pipeline.md). # How a matter moves through BriefTech The staged pipeline and the two workstreams that run alongside it. BriefTech organises everything around a single, repeatable pipeline for a matter. Almost every feature belongs to one stage of that pipeline or supports it, so once you have the shape of the pipeline in mind, the rest of the platform is much easier to place. *** ## Why the work is staged: Upload → Review → Index → Export A matter moves through four stages, each with a clear job: * **Upload** — you bring your documents in and BriefTech prepares them for use. * **Review** — you check and correct the details it has extracted — dates and descriptions. * **Index** — you build the Document Index: the ordered, structured spine of the matter. * **Export** — you turn that index into a deliverable — a paginated court bundle, or the Document Index as a Word or Excel file. Separating the work this way means each stage has a single focus. You are never asked to order documents before they are ready, or to export before the index reflects what you want. Organising your documents — into folders, with labels, or as collections — is not a stage of its own. You can do it from the Files or the Review tab at any point. Folders and collections also shape what your index and exports contain: you can group the index by folder and mirror that structure in a ZIP export, and a collection scopes both the index and the bundle built from it. If you have come from the BriefTech website, it presents this same journey as **six stages** — Files, Orientation, Review, Structuring, Index, and Production. That is the full arc from evidence to bundle, including the parts BriefTech handles for you automatically. They map onto the four steps shown across the top of a matter: * **Upload**, on the Files tab (Orientation — the automatic reading and mapping of your documents — happens here) * **Review**, on the Review tab * **Index**, on the Index tab (Structuring, ordering the evidence into the bundle, is part of building the index) * **Export** (Production — pagination, bookmarks and volumes), which you run from the **Create Bundle** and **Download Files** buttons on the Index tab's toolbar. Same pipeline, described at two levels: six stages of what happens to your evidence, four steps you drive. *** ## The two workstreams that run alongside: AI analysis and collaboration Not everything fits neatly into a stage. Two capabilities run alongside the whole pipeline, available at any point. AI analysis reads your documents and extracts structured information — document types, dates, and summaries. Collaboration lets you share the matter with colleagues and control who has access to it. These are workstreams rather than steps. AI analysis starts on its own: each document is read as soon as it is ready. The matter's owner can invite a colleague at any time. *** ## Why each stage builds on the one before The order of the pipeline reflects real dependencies. A document must finish processing before there's anything to review: only once it's **ready** does the AI extract its dates and descriptions, and reviewing is where you check and correct those. Review feeds the index, because the dates and descriptions you confirm become the content of your Document Index — except that a date the app reads from a document's file name takes precedence over the reviewed one. It looks at the first group of digits in the name shaped four-two-two (year, month, day) or two-two-four (day, month, year), separated by `-`, `.` or `_` — `2024-03-01` or `01.03.2024`, for example — and uses it if it reads as a date; only if the name has no such group is a run of eight digits tried instead, read year-first or day-first, whichever reading dates more of the eight-digit file names in the index being built (the collection you are viewing or exporting), this one included (year-first on a tie) (see [Serial numbers and date formats](/reference/serial-numbers-and-date-formats.md)). And the index drives export, because the bundle and the exported index are produced directly from the order and structure you set. Working with the pipeline rather than against it keeps each stage's output trustworthy for the next. > For what happens to each document between upload and the moment it can be used, see [The document lifecycle: from upload to ready](/concepts/the-document-lifecycle.md). *** ## What a matter holds A matter is the container for everything that belongs to a single case: the documents and their metadata, the folders, labels and collections you organise them into, the Document Index you build, the bundles you export, and the colleagues you have shared it with. Sharing a matter shares everything in it. Your credits and storage limits are set at the account level and apply across all your matters, not just this one. Uploading, AI analysis and building the index don't use credits. A document is charged at most once, usually the first time you include it in an export or a court bundle — see [How credits work](/concepts/how-credits-work.md) for everything that uses credits. *** ## Related
Get StartedWhat BriefTech is, how it works, and where to start.Brief Tech Overview
Your First MatterA guided, end-to-end first run — take a practice matter from sample files all the way to a downloaded court bundle.Your First Matter
The document lifecycle: from upload to readyWhat happens to a file between upload and the moment it can be used.The document lifecycle: from upload to ready
How AI analysis works: agents and playbooksWhat agents and playbooks are, and what they extract.How AI analysis works: agents and playbooks
From Document Index to court bundleHow the index and the bundle share one source of truth.From Document Index to court bundle
Roles and permissions in a shared matterHow access is shared and what each role can do.Roles and permissions in a shared matter
Manage AccountCross-cutting account work: sharing matters, managing access, and handling credits.Manage Account
Find, organise, and archive your mattersFind, pin, filter, and archive your matters from the Matters list.Find, organise, and archive your matters
Download an invoiceGet a receipt or invoice for a credit pack purchase.Download an invoice
Profile settingsThe fields in your user profile.Profile settings
Matters list: states and indicatorsThe icons, badges, and metadata shown on each matter in the Matters list.Matters list: states and indicators
Signing in and creating an accountHow to sign in to BriefTech, create an account, reset your password, and choose between Google, Microsoft, and email sign-in.Signing in and creating an account
--- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.brieftech.ai/concepts/the-matter-pipeline.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.