Agent Documents

Agents can read, edit, and create documents, apps, databases, and executable scripts

Documents are first-class storage in Abundly. Each workspace, each team, and each agent has its own document library, and your agents can read across all of them—just like a colleague who has access to a shared drive plus their own files. The platform tracks every change with full version history.

Documents can be pure content, such as a text file or PDF or image, or they can be Interactive Apps or Agent Databases.

Documents work out of the box with no configuration. For external files like Google Drive or SharePoint, enable the corresponding capabilities.

Where documents live

Documents are organized into three scopes, mirroring how teams share information in real life:

• Workspace documents — Shared with everyone in your workspace. Find them on the Workspace page under the Documents tab. By default, only workspace admins can add, remove, and edit files; admins can adjust this under the workspace Settings tab, in the Documents section, to also let all members and/or agents edit.
• Team documents — Shared within a single team. Find them on the team’s home page under Documents. By default, only team admins can edit; team admins can adjust this under the team’s Settings tab, in the Documents section, to also let all team members and/or team agents edit. Workspace admins can always manage any team’s documents. People who aren’t in the team but can use one of its agents see the team documents read-only on that agent’s Documents page, except documents hidden from agents.
• Agent documents — Belong to a single agent. Find them in the agent’s Documents page. Anyone with edit access to the agent can manage them.

When working, an agent can read documents from all three scopes—its own, its team’s, and the workspace. By default, it can only create or edit documents in its own library, but workspace and team admins can grant agents edit access to those libraries too—either all agents, or only admin-only agents.

The full-page Documents views (workspace, team, and agent) all use the same tree-based file explorer. The agent’s Documents page shows the workspace and team scopes the agent can reach alongside its own library, so you can browse everything the agent works with from one place.

You can move a document between scopes from its menu, or by dragging it onto another scope or folder in the file explorer (for example, promote an agent document to a workspace document so other agents can use it). On desktop you can also drop files from your computer directly onto any scope to upload them there.

Supported file types

Documents are plain text by default—typically Markdown for simple formatting. You can also upload other file types:

File type	How it works
Text & Markdown	Native format, directly editable by you and the agent
Code files	JavaScript, TypeScript, HTML, CSS, JSON, YAML, and more—stored as editable text
SVG graphics	Stored as editable text, rendered as vector graphics in preview
PDFs, Word, PowerPoint	Transcribed to text—original file preserved for reference
Spreadsheets	Transcribed to text—original file preserved for reference
Apple iWork (Pages, Keynote, Numbers)	Converted and transcribed to text—original file preserved for reference
Images	Vision AI generates a text description the agent can read
Audio	Automatically transcribed to text with speaker labels and timestamps
Video	Audio track extracted and transcribed with speaker labels and timestamps (video frames not analyzed)

A single document’s text or data is limited to about 15 MB. Anything larger — whether pasted into the editor or written by an agent — is rejected with a clear “too large” message rather than saved. Upload big files as files instead, or split the content into smaller documents. An oversized text attachment on an incoming email is skipped instead: the email still reaches the agent, just without that attachment.

For uploaded files (PDF, audio, video, etc.), the platform creates a text version that the agent works with. Transcription runs automatically in the background as soon as the file is uploaded — whether you drop it into a chat or add it to an agent, workspace, or team library — and a short description is auto-generated afterwards so the file is easier to find later. For example, upload a meeting recording (audio or video) and the transcript is ready moments later, so you can ask the agent questions about what was said. You can access the original via the Original file button. If you edit the text, it will diverge from the original—the agent always works with the text version.

For audio and video, the document menu has a few transcript actions:

• Identify speakers replaces the generic “Speaker 1”, “Speaker 2” labels with real names. The dialog shows a few quotes per speaker (click a timestamp to hear that part of the recording), and Suggest names lets an AI model guess the names from how people address each other. While speakers are still unidentified, the transcript toolbar also shows an Identify speakers shortcut.
• Remove speaker labels and Remove timestamps strip that information from the transcript without re-transcribing — handy for voice memos.
• Re-transcribe redoes the transcript with an explicit language (if auto-detection picked the wrong one) or without speaker labels. See the ElevenLabs integration for the transcription provider and the OpenAI Whisper fallback.

These actions change the text version only, and the previous version stays in the document’s history.

Working with documents

Click any document to open it in a modal with a mode selector. Available modes depend on document type and context. If the agent changes a document while you have it open, click Reload in the header to see the latest version. Uploaded files such as PDFs and images, which the agent can’t change, have no reload button.

Use Copy link from a document’s menu to grab a direct link to it. Anyone with access to the agent — or to the workspace/team scope the document lives in — can open the link straight to that document or app, shown fullscreen, making it easy to reference a specific item in chat, Slack, or a ticket. This is different from publishing, which creates a public link that needs no account.

Links follow a fixed pattern, so you can also build one yourself when you know the ids. Start from your Abundly address (https://app.abundly.ai, or https://<your-tenant>.app.abundly.ai on a dedicated deployment) and add:

• Agent document — /portal/{workspaceId}/agent/{agentId}/docs?docId={documentId}
• Workspace document — /portal/{workspaceId}/workspace?docId={documentId}#documents
• Team document — /portal/{workspaceId}/teams/{teamId}?docId={documentId}#documents

For example: https://app.abundly.ai/portal/68f3c1a04b2e5d7f9a0c1b23/agent/6902ab77c4d1e05f38b6a914/docs?docId=691f4d2c8ae30b5619cf7d82

Folders and apps use the same docId parameter — pass the folder’s id and the link opens that folder, or runs it when the folder is an app. Documents that live inside a chat have no link of their own; save one to the agent, team, or workspace library first.

Edit mode

The text representation of the document—this is what the agent sees and works with. You can edit the text directly here. If you can’t edit the document, this mode is called Text and shows the text read-only.

View mode

A visual rendering of the document, depending on its type:

• Markdown → Rendered with formatting, headings, and links
• React or HTML → Live rendered application or web page
• Mermaid diagrams → Rendered flowcharts, sequence diagrams, etc.
• SVG → Rendered vector graphic (editable as text)
• Database documents → Interactive table view of the data

Here is an example of a preview of an Interactive App document.

Data mode (for databases)

For agent databases, you can open a dedicated Data mode to view and edit raw JSON plus the schema.

Changes mode

A version timeline showing every change made to the document. Click any version to view it, or click between two versions to see a diff of what changed. You can revert to any previous version, and for agent documents you can also approve or undo individual changes.

Visibility levels

Documents have two separate controls:

• Visibility to the agent controls what your agent can discover and read while working.
• Publishing controls whether people outside your workspace can open a public link.

By default, agents know which documents they have (name and summary) and can read the full content when needed. You can adjust visibility per document:

Level	Behavior
Full	Agent always knows the full content—included in every prompt alongside instructions. Use for essential context the agent should never forget.
Summary	(default value) Agent knows the document exists and its summary. Reads the full content only when relevant. Good for most documents.
Hidden	Agent cannot see or find this document. Use for your own notes or materials not relevant to the agent’s job.

To change visibility, click the visibility icon next to the document name in the Documents panel. Agents can set a document to Summary or Full, but only people can make one Hidden.

Start with the default Summary visibility. You can add many documents without overloading the agent’s context—it will read full content only when needed.

Folder visibility

Folders have their own visibility control with just Visible and Hidden (folders have no content of their own, so Full doesn’t apply). Click the visibility icon next to a folder name to change it.

Hiding a folder cascades to everything inside it:

• Every document and sub-folder underneath is treated as Hidden for the agent, regardless of the child’s own visibility setting.
• The folder and its contents disappear from the agent’s system prompt, from search results, and from folder browsing tools.
• In the Documents panel and file explorer, descendant documents and sub-folders show their visibility badge greyed out, with a tooltip explaining that an ancestor folder is hiding them — so you can tell at a glance which items are hidden because of a folder rather than their own setting.
• People who can see the workspace still see the folder normally in the Documents panel and the in-chat file explorer—only the agent’s view is affected.

Use folder hiding when you want to keep a whole area of materials (drafts, archives, personal notes) out of an agent’s reach without flipping visibility on each file.

Protected documents

Some agent documents are really part of how the agent works—a script it runs, a checklist it follows, a template it fills in. Changing one changes the agent’s behaviour, much like editing its instructions.

Marking an agent document Protected treats it that way. A protected document is read-only for the agent unless someone with Edit access to the agent is in the chat. The agent cannot change it during a scheduled run, from an incoming email or webhook, in a Slack or Teams conversation, or when a colleague with only Use access asks it to. It also cannot be changed through the public document API or an agent’s own exposed document endpoints.

This closes a gap: without it, someone who cannot edit an agent’s instructions could still change how the agent behaves by asking it to rewrite one of its documents.

To protect a document or folder, choose Protect from its options menu — the same menu that holds Publish, whether you open the document or use the ⋮ menu on its row in the file explorer. Choose Lift protection there to remove it again. Both need Edit access to the agent. Protected items carry a shield badge in the document header and next to their name in the file explorer.

Protecting a folder cascades to everything inside it, including documents the agent adds later—the simplest way to lock down a whole set of scripts or reference material at once. Items protected by an ancestor folder show the shield badge with a tooltip naming that folder, and their options menu points at it rather than offering to unlock them individually; lift the protection on the folder instead.

You can also just ask the agent to protect or unprotect a document while you are chatting with it—handy right after it has written something that shouldn’t later be overwritten. That works because you hold Edit access. Protecting needs that just as much as unprotecting does: a protected document carries the authority of an editor having blessed it, so someone without edit rights cannot give a document that status by asking the agent for it.

Protection applies to agent documents. Workspace and team libraries have their own write rules, set by admins under the Documents section of the workspace or team Settings tab—see Where documents live.

Adding documents

You can add documents in three ways. The flow is the same for workspace, team, and agent documents—open the corresponding Documents page or tab and use the same controls.

1. Upload or create directly

Each Documents view has Create document and Upload document buttons at the top—use them to start a new text document or upload files from your computer. You can also drag files straight onto the list. Each section and folder still has a kebab menu with New Folder, New Document, and Upload when you want to add content into a specific folder, and individual documents and folders have a row-level menu (⋮)—also in search results—with the same options as the document’s own menu (such as Copy text content, Protect, Move, and Delete) plus Rename, so you can manage items right from the list without opening them first. Uploaded files appear right away in the folder you dropped them on, marked as waiting or uploading; you can cancel an individual file or keep adding more while others upload.

2. Save from a conversation

Drag a file into the chat, discuss it with the agent, then ask it to save the result. For example:

• Drag a meeting transcript, ask for a summary, then “save this as an agent document”
• Ask the agent to draft a newsletter, refine it together, then “save this to the newsletters folder”

When the agent opens content in the side panel (a chat-scoped document), click the menu and choose Save as agent document to promote it to a permanent agent document without asking the agent to do it. The same menu also offers Save to Google Drive, which creates a native Google Doc in your My Drive.

3. Instruct the agent to create documents automatically

Add instructions like:

• “When processing an invoice, add it to the processed invoices database”
• “Save all incoming emails to a message log”
• “After posting release notes, save a copy to the ‘release notes’ folder”
• “When you receive an email with an attachment, save it as an agent document”

4. Download from a public URL

Ask the agent to fetch a file from a URL and save it—for example, “Download the PDF at https://example.com/report.pdf and save it to the reports folder.” Images, PDFs, Markdown, and plain text are all supported. The URL must use https://; plain http:// addresses are refused.

Finding documents

Each Documents view—agent, workspace, or team—has a free-text search field at the top. It matches by document name, description, or type, and results appear as a flat list with folder-path breadcrumbs so you can see where each match lives. The search is scoped to the current section, so a workspace-documents search won’t surface agent or team documents.

The search loads the whole library up front, so results appear straight away even in libraries with thousands of documents. When a query matches more items than the view can show, the field tells you how many extra matches were left out — narrow the keywords to reach them.

Organizing with folders

Documents can be organized into folders. Create folders in the Documents panel and drag documents to organize them. Folders can be nested as deeply as you need, and nesting works the same way across workspace, team, agent, and chat document libraries. Reference folders in your agent’s instructions: “Save meeting notes to the ‘meetings’ folder.”

Deleting a folder that still contains documents or sub-folders prompts for confirmation and shows what will be removed, so you don’t lose files by mistake.

One folder name has a special meaning: anything placed in a top-level skills folder in an agent’s, team’s or workspace’s documents becomes a skill that the agent, or every agent in that team or workspace, can load on demand.

Version control

Every edit—by you or the agent—creates a new version automatically. The Changes mode lets you:

• Browse history — See all versions with timestamps and who made each change
• Compare versions — Side-by-side diff view to see exactly what changed
• Approve or reject (agent documents only) — Optionally mark changes as approved or rejected (rejecting creates a new version with that change undone)
• Revert — Roll back to any previous version if needed

Publishing documents

You can publish a document to make it available to anyone with the link. Open the document menu and choose Publish (or Publish details if it is already published). This works for documents in any scope—workspace, team, or agent.

Anyone with the link can view the document—no Abundly account required. If it is an app, they can interact with it. Published documents are marked with a Published badge in the Documents view. Logged-in visitors can also use Copy to my agent from the viewer to clone the published document into one of their own agents—handy for sharing templates, dashboards, or reference material across workspaces.

Use cases:

• Share a live dashboard with colleagues
• Publish an input form for data collection
• Share reports, drafts, or documentation externally
• Create a public-facing interactive app

You can also publish Interactive Apps and Agent Databases. For agent databases, choose what public users can do:

• Read to query and view data
• Create to insert new items
• Update to modify existing items
• Delete to remove items

Publishing a database exposes its entire contents. The Read/Create/Update/Delete toggles control which operations public viewers can perform; they don’t restrict which rows are visible. See publishing apps with data for details.

For uploaded files (like PDF, audio, or spreadsheets), you can optionally enable Also publish original file so anyone with the link can download the original file without logging in.

If a published app depends on other documents, publish those documents too (with at least Read enabled) so the app can access them from the public link. The app’s Publish details dialog lists any referenced databases that aren’t publicly readable yet: switch one on to publish it read-only, or open it from the list to choose other permissions.

Published apps update automatically. Create a dashboard, share the link, and your colleagues always see the latest data.

Requiring Microsoft sign-in

On enterprise instances with Microsoft SSO, the publish dialog offers a Who can open the link choice (when enabled for the workspace):

• Anyone with the link — the default, works as described above.
• Only people in your Microsoft organization — visitors sign in with their Microsoft work account before the document opens. They don’t need an Abundly account; access is controlled entirely by your Microsoft organization. Data changes made through a protected app are recorded with the signed-in visitor’s identity.

An app and the databases it references each carry their own setting, and the publish dialog flags mismatches — a protected app publishing its database without sign-in would leave the data more open than the app.

Workspace admins can also require sign-in for every published document. Under Workspace → Settings → Documents, choose Your Microsoft organization only. Then:

• Every published document requires Microsoft sign-in, including documents that were published to anyone before. The per-document choice is locked to sign-in.
• Agent tools that create public image or audio links save the file but don’t create a link, since recipients outside your organization couldn’t open it.

Switching back to Anyone, or your Microsoft organization reopens documents that were published to anyone before. Documents published while sign-in was required keep requiring it.

Turning off publishing for a workspace

Workspace admins can disable document publishing for the whole workspace under Workspace → Settings → Documents. Where the sign-in option is available, choose No one (publishing off). When it is off:

• New publish attempts are rejected everywhere — the Publish button, agent tools that generate public images or audio, and any external API that tries to set a document as published all refuse the change.
• Any documents that were already published stop resolving at their public links, and any external referrers (for example emails that link to a published image, or published apps that load their own assets) will no longer work until publishing is turned back on.

Turning publishing back on restores the previously published documents; no republishing step is needed.

Turning document publishing off takes previously published documents offline for the whole workspace. Use it deliberately.

Editing and searching documents

Agents don’t need to rewrite entire documents to make changes. They can:

• Edit precisely — Replace, insert, or append text
• Search within a document — Exact match, full-text, or semantic (meaning-based) search
• Find documents — Fuzzy keyword matching across names, descriptions, and content. In very large libraries the agent gets the most relevant matches back plus a count of the remaining ones, so it can narrow the query rather than stalling on an unbounded result set
• Browse folders — Page through very large folders instead of trying to load everything at once
• Rename and describe — Update document names and summaries

Use semantic search within documents to find content by meaning, not just keywords. For example, searching “global warming” can find sections about “climate change.”

Copying and downloading documents

Use Copy text content to copy a document to the clipboard. For Markdown documents (including uploaded files whose text has been extracted to Markdown), both a formatted version and the raw Markdown are placed on the clipboard in one copy — so pasting into rich editors like Slack, Google Docs, Word, or email keeps headings, bold text, lists, and tables, while “Paste without formatting” (Cmd/Ctrl+Shift+V) or plain-text-only targets receive the raw Markdown.

You can download individual documents in several formats:

• Download file — Get the document as a file with its own extension (.md, .csv, .json, …). For uploaded files whose text has been extracted, this appears as Download text content and gives you the extracted text.
• Download as docx file — Convert a Markdown or plain-text document to a .docx file. Not offered for HTML, apps or code, which would only export as their source text.
• Download as PDF — Convert a document to a PDF. Markdown, rendered documents (HTML, SVG, React apps), and embedded images are all included; code, CSV and JSON are printed as-is.
• Download original — For non-text files (PDF, audio, etc.), download the original file

To download multiple documents at once, use Download all in the Documents panel to get a ZIP file containing everything in the current folder, including any nested subfolders. You can also choose Download folder as ZIP from a folder’s menu to download just that folder’s contents.

On the full-page Documents views, you can also multi-select items with the row checkboxes and then bulk move, download, or delete the whole selection in one go.

To delete multiple documents at once, use Delete all from the Documents panel menu to remove everything in the current view.

Documents as extended context

Agent documents are a powerful way to give your agent additional context without bloating its instructions. Instead of pasting everything into the instructions, store reference materials as documents:

• Checklists — Step-by-step procedures for specific tasks
• Templates — Formats for reports, emails, or communications
• Guidelines — Company policies, compliance rules, or style guides
• Reference data — Product catalogs, contact directories, FAQs

With Summary visibility (the default), the agent knows these documents exist and reads them when relevant—keeping its context focused while still having access to everything it needs.

For best results, guide your agent on when to use specific documents:

• “Before responding to compliance inquiries, read the compliance guidelines document first”
• “When drafting emails, use the email template in the templates folder”
• “All meeting notes are saved by date—search for them when you need context”

If you don’t want the agent to create or edit documents, disable the Edit Documents capability in settings.

Chatting about documents

Click Chat about this next to any document to start a new conversation about it. The document opens in the side panel, is attached to your first message, and a short prompt is prefilled — edit it or add your question, then send. The agent has immediate access to the document, making it easy to ask questions, request edits, or work through the content together.

For folders, use Chat about this folder. The folder is attached the same way, and sending the first message includes a recursive listing of its documents and subfolders — names, ids, and descriptions only, not the full contents — so the agent knows what’s inside and can pull up any specific document on demand with its document tools.

Open a document in every new chat

Some agents are mainly used through an app or dashboard stored in their documents. Pick that document (or app folder) under Settings → Main settings → Communication → Chat start document, and every new chat opens with it in the side panel and attached to your first message, just like Chat about this. The setting applies to everyone who chats with the agent, and with the Update Agent Settings capability you can also ask the agent to change it. To use an app as your start page, open it fullscreen and bookmark it (see Apps).

If the agent is set to take the first turn, it waits for you to write first instead. A Chat about this link still opens the document you chose.

FAQ

Where are my documents stored?

It depends on the document type:

• Agent documents (created directly in Abundly) are stored in EU data centers in Stockholm, Sweden. They remain fully under your control—you can delete them at any time.
• External documents (Google Drive, SharePoint, etc.) remain on their original provider’s servers. The agent accesses them through your permission but doesn’t copy them to Abundly’s infrastructure.

For example, if you share a Google Doc with an agent, the document stays on Google’s servers and is accessed only through your authorized connection.

See Infrastructure & Compliance for details on data residency and security.