> 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/reference/ai-agents.md). # AI agents The AI agents available in BriefTech and what each one produces. AI agents read your documents and produce structured output. Each agent is purpose-built for a task. ## Analysis agents | Agent | Produces | Where you find it | | ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Organise** | Reads every document — including image-only ones such as scans and photographs, which it can still describe from the image when there is no readable text to extract — and determines its document type, summary, key dates, and other details. | Its summary and key dates are what fill the **Summary** and **Key Dates** headings of the **Summary** view in the preview pane — see [The preview pane](/reference/preview-pane.md). | | **Duplicate Document Finder** | A list of duplicate and near-duplicate documents. Currently in beta and free to use. | The **Tools** menu on the Files and Review tabs, listed as **Duplicate Document Finder**. | ## Workflow agents | Agent | Produces | Where you find it | | ------------------------ | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Create court bundles** | A paginated court bundle to Singapore court standard. See [Court bundle settings](/reference/court-bundle-settings.md). | **Create Bundle** on the Index tab tab opens the bundle panel; a second **Create Bundle** button inside that panel starts the run. | | **Download all files** | A ZIP archive of your index files. See [Export formats and options](/reference/export-formats-and-options.md). | **Download Files** on the Index tab tab opens the download panel; in it, tick **All Files** and click **Export** to start the ZIP. | {% hint style="info" %} **Cost:** Running the analysis agents (Organise, Duplicate Document Finder) is free. The workflow agents produce an **export** — the first time a document is included in a court bundle or download it is committed to your Document Index and consumes credits. See [Credit costs and pricing](/reference/credit-costs-and-pricing.md). {% endhint %} ## Agent activation * When you create a matter, BriefTech activates the agent that reads and describes each document, and the agents behind the **Create Bundle** and **Download Files** buttons on the Index tab tab. * **Duplicate Document Finder** is listed in the **Tools** menu of every matter, and runs only when you choose it. The first time it is used in a matter, the matter's owner confirms a one-time activation — see [Find and remove duplicate documents](/how-to-guides/organise/find-remove-duplicates.md). ## Related
How AI analysis works: agents and playbooksWhat agents and playbooks are, and what they extract.How AI analysis works: agents and playbooks
Bulk-edit metadata across many documentsChange labels, collections, dates, descriptions and index categories on many documents at once.Bulk-edit metadata across many documents
Document metadata fieldsThe document fields you can edit in the Review tab and their accepted values.Document metadata fields
Review an AI-Analysed MatterA guided run through the Review stage — take a matter the AI has analysed and confirm, correct and refine its details until it's ready to index.Review an AI-Analysed Matter
--- # 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/reference/ai-agents.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.