Skip to main content

Files & Attachments

Files are first-class citizens in MeetLoyd. You can upload documents to conversations, attach files in chat, and let agents generate documents on the fly. Every file is security-scanned before processing.

How It Works

When you attach a file in chat, MeetLoyd:

  1. Scans the file through a zero-trust security pipeline
  2. Parses the content automatically (text extraction from PDFs, DOCX, XLSX, etc.)
  3. Injects the full parsed content into the agent's prompt
  4. Stores a compact summary in conversation history

The agent can immediately read, analyze, and reference your documents -- no manual download needed.

Supported Formats

FormatExtensionsMax Size
PDF.pdf50 MB
Word.docx25 MB
Excel.xlsx25 MB
PowerPoint.pptx100 MB
CSV.csv10 MB
Text.txt5 MB
Markdown.md5 MB
JSON.json10 MB
Images.png, .jpg, .gif, .webp20 MB
Blocked formats

Legacy Office formats (.doc, .xls, .ppt) are blocked because they use the OLE Compound format which can contain hidden macros and embedded executables. Convert to modern formats (DOCX, XLSX, PPTX) before uploading.

Security Pipeline

Every uploaded file goes through a zero-trust security pipeline before it is stored:

CheckWhat It Does
Magic bytes verificationVerifies file content matches the claimed MIME type
Macro detectionBlocks files containing VBA macros or executable code
Zip bomb detectionDetects compression bombs in Office documents
XXE preventionBlocks XML External Entity attacks in Office XML
Path traversal blockingPrevents directory traversal in file names
Embedded executable detectionFinds hidden executables inside documents
Script injection detectionCatches script tags, event handlers, and JS protocol URIs

If a file fails the scan, it is quarantined (saved to a secure location, not accessible) and the upload returns an error with details about the threat.

Content Injection

When you attach files to a chat message, MeetLoyd does not just send the agent a download link -- it injects the full parsed content directly into the agent's prompt.

Token Budgets

To prevent excessively long prompts, injected content is token-budgeted per model:

Model SizeToken Budget
Large (Claude Opus/Sonnet, Gemini Pro)~16,000 tokens
Medium (GPT-4o)~12,000 tokens
Small (Haiku, Mini)~6,000 tokens

If a file exceeds the budget, content is truncated. When multiple files are attached, the budget is split evenly.

What the Agent Sees vs. What is Stored

Content
Agent promptFull document text (e.g., the complete text of your PDF)
Conversation historyA compact summary (e.g., [Attached: Q4.pdf (3 pages, 2.1k words)])

This keeps conversation history lightweight while giving agents full context when they need it.

Uploading Files

Via Chat

Click the paperclip icon in any chat -- Admin conversations, Openspace team/agent chats, or Loyd:

  1. Click the paperclip button next to the message input
  2. Select one or more files from your device (up to 10 per message)
  3. Files upload immediately and appear as removable chips below the input
  4. Type an optional message
  5. Click Send

The agent receives the full extracted text automatically. Attached files also display as artifact cards in the conversation with format-specific icons and a download button.

Auto-Parsing

Every file is automatically parsed when uploaded. The extracted text is cached so agents can read your documents instantly without re-processing.

FormatWhat is Extracted
PDFFull text content, page count, plus vision descriptions of each page (diagrams, charts, screenshots)
DOCXParagraphs, headings, tables, plus vision descriptions of embedded images
XLSXCell values across all sheets, plus vision descriptions of embedded images
PPTXSlide text and notes, plus vision descriptions of embedded images
CSVAll rows and columns
TXT/MD/JSONRaw content

After upload, the file's parse status reflects the result: parsed (success), failed (extraction error), or unsupported (format not supported for parsing).

Image Understanding

Diagrams, screenshots, charts, and photos inside your documents aren't just ignored -- MeetLoyd sends each image through a vision-capable model and inlines the description alongside the extracted text. So when you ask an agent about a figure on page 3, it actually knows what's on page 3.

How MeetLoyd picks the vision model

Per image, in order:

  1. Your agent's BYOK model, if it supports vision (Claude, GPT-4o, Gemini Pro, Gemini Flash, Qwen-VL). No platform billing -- it's your own API key.
  2. The platform vision utility model (configurable per tenant via utilityModels.vision in tenant settings). Default is Claude Sonnet; on-prem and BYOD tenants typically override to a self-hosted Qwen2.5-VL on vLLM to keep everything off the public internet. This path consumes platform credits.
  3. No vision model available and no credits -- the image is left with a placeholder [Image present but not described -- configure a BYOK vision model or credit your account...]. The rest of the document still works.

What the agent sees

For Office documents (DOCX/XLSX/PPTX), descriptions appear in a dedicated section appended to the extracted text:

Body text from the document...

## Embedded images

[Image 1 (q3-revenue.png): A bar chart showing Q3 revenue by region,
with EMEA leading at €4.2M.]
[Image 2 (org-chart.png): Organizational chart of the sales team,
with 3 regional leads reporting to the VP of Sales.]

For PDFs, each page is rasterized and described as a whole, since a page often mixes text and graphics:

Page 1 text...

Page 2 text...

## Pages (visual)

[Page 1: Title page with company logo and report title "Q3 Review".]
[Page 2: Revenue chart with the 4 quarters, Q3 highlighted in green...]

Caps

To protect cost and latency, MeetLoyd caps visual analysis at 20 images per Office document and 20 pages per PDF. Documents larger than this still upload successfully -- the excess pages/images just aren't visually described, and a note is added to the content so the agent knows.

On-prem and BYOD customers

If you're deployed on-prem or require full internet isolation (banks, regulated industries), set utilityModels.vision = 'qwen2.5-vl-72b' in your tenant settings. All image descriptions then run on your self-hosted vLLM deployment, with zero cloud egress.

Agent-Generated Documents

Agents can create documents during conversations using the generate_document tool. Generated files appear as artifact cards in the chat. See Document Generation for details.

Storage Backends

BackendWhen UsedDescription
Cloudflare R2ProductionDurable S3-compatible object storage
Local filesystemDevelopmentFiles stored locally, suitable for dev only

The backend is selected automatically. Uploads and downloads work the same regardless of backend.

Workspace Sync

If your team has a provisioned Google Shared Drive or SharePoint site, uploaded files are automatically synced to an Attachments folder in the team's shared drive. Sync is non-blocking -- your message sends immediately. If no workspace is configured, files are still stored durably in MeetLoyd's storage.

See Team Workspace Provisioning for setup details.

Cloud Storage Integrations

MeetLoyd's file management is for files uploaded directly to the platform. For files stored in cloud services, use the integration tools:

FeatureMeetLoyd FilesGoogle Drive / OneDrive
StorageCloudflare R2 (durable)Google / Microsoft cloud
Security scanningYes (zero-trust pipeline)Provider's own scanning
Content parsingAuto-parsed on upload, cachedVia read/export tools
Agent injectionAuto-injected into promptManual read via tools
Chat attachmentsDirect upload via paperclipLink sharing
Workspace syncAuto-synced to team driveNative

See Google Workspace Integration and Microsoft 365 Integration for cloud storage tools.

Best Practices

PracticeWhy
Use modern formatsDOCX/XLSX/PPTX instead of DOC/XLS/PPT -- more secure and better supported for parsing
Link files to conversationsAttach files through the chat UI so they are contextually linked
Check file sizeLarge files are supported but token budgets apply -- split very large documents if needed

Conversations
How chat conversations work in MeetLoyd
Document Generation
Let agents create documents on the fly
Memory
How agents remember across conversations