> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omnifact.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Document Creation
> Generate finished Excel spreadsheets, Word documents, PowerPoint presentations, and data charts directly in chat.
export const Glossary = ({children, term}) => {
const glossaryDefinitions = {
'ai': 'Artificial Intelligence - computer systems that can perform tasks typically requiring human intelligence',
'artificial-intelligence-ai': 'Computer systems that can perform tasks typically requiring human intelligence',
'ai-assistant': 'An AI system designed to help users with tasks through conversation',
'space': 'A dedicated environment with a specialized AI assistant and optional Uploaded Files',
'spaces': 'Dedicated environments with specialized AI assistants and optional Uploaded Files',
'knowledge': 'The sub-menu in Space settings where you manage Uploaded Files and Connected Sources',
'uploaded-files': 'Documents manually uploaded to a Space under the Knowledge tab',
'prompt': 'Instructions or questions you give to an AI assistant',
'response': 'The AI assistant\'s answer to your prompt or question',
'query': 'A question or request for information',
'context': 'Background information that helps the AI understand your request',
'llm': 'Large Language Model - an AI system trained on vast amounts of text data to understand and generate human language',
'large-language-model-llm': 'An AI system trained on vast amounts of text data to understand and generate human language',
'privacy-filter': 'A system that automatically detects and masks sensitive information before it reaches AI models, and restricts images from being sent to non-EU hosted models for compliance',
'chat-instructions': 'Custom guidelines that define how an AI assistant behaves and responds in a Space',
'pattern-matching': 'The process by which AI recognizes and uses patterns in data to provide responses',
'patterns': 'Recognizable structures or trends in data that AI systems can identify and use',
'training-data': 'The text and information used to teach an AI system how to understand and respond to requests',
'natural-language': 'Everyday human language that people use to communicate, as opposed to computer code or formal syntax',
'hallucination': 'When an AI generates information that sounds plausible but is actually incorrect or fabricated',
'filtering': 'The process of automatically detecting and temporarily replacing sensitive information to protect it during AI processing',
'masking': 'Temporarily replacing sensitive information with generic labels to protect it from being seen by external AI models',
're-insertion': 'The automatic process of putting original sensitive information back into AI responses after they\'ve been generated with filtered data',
'retrieval': 'The process of finding and accessing relevant documents from Uploaded Files to answer questions',
'hosting': 'Where an AI model is deployed and made available for use - either by third-party providers, on your organization\'s own servers, or in private cloud environments',
'cite': 'To reference or mention the source of information, helping you know where an AI\'s answer came from',
'sidebar': 'A panel that appears on the side of the screen showing additional information and options',
'toggle': 'A button or control that switches something on or off, like opening and closing a sidebar',
'navigation': 'The system of menus and buttons that help you move between different parts of Omnifact',
'favoriting': 'Marking a Space as a favorite to pin it to the main navigation for quick access',
'pinning': 'Attaching a Space to the main navigation bar so it\'s always visible and easily accessible'
};
const definition = glossaryDefinitions[term];
return {children};
};
Instead of copying unformatted text or building spreadsheets from scratch, Omnifact can generate finished, ready-to-use business files directly in your conversation. Describe what you need, attach your raw data, and let your AI assistant build formatted workbooks, executive memos, slide decks, and visual charts.
## Supported Document Types
Every generated file is delivered as a standard Office or image file formatted for professional use. You can open, edit, and share them in Microsoft Office, Google Workspace, or Apple iWork without fixing misaligned tables or broken layouts.
Spreadsheets with live mathematical formulas, clean number formatting, and frozen header rows that recalculate dynamically when inputs change.
Structured memos, reports, and meeting summaries with proper heading hierarchies, styled tables, and clean margins.
Clean 16:9 widescreen slide decks with strong typography, comparison columns, and metric callout cards.
Deep analysis of attached datasets with inline charts and graphs rendered directly in chat for instant download.
### Excel Spreadsheets with Dynamic Formulas
When Omnifact creates an Excel workbook (`.xlsx`), it includes active mathematical formulas rather than static values. Formulas such as `SUM`, `IF`, `SUMIFS`, and `INDEX/MATCH` recalculate automatically across the entire workbook whenever you update an assumption or change a figure.
The assistant formats your data with readable column widths, currency and percentage styles, and frozen header rows so large tables remain easy to navigate.
Before delivering your spreadsheet, the assistant automatically evaluates formulas in a secure environment to catch calculation errors (such as `#REF!` or `#DIV/0!`), ensuring you receive a dependable workbook.
### Formatted Word Documents and Memos
For project proposals, executive summaries, meeting protocols, and decision memos, Omnifact outputs structured Word documents (`.docx`).
The assistant applies consistent heading styles, standard page margins, and styled tables. Rather than bolding plain text, it uses authentic Word styles so outlines and tables of contents function seamlessly when opened in Microsoft Word.
### Professional PowerPoint Decks
Presentations generated by Omnifact (`.pptx`) use standard 16:9 widescreen slides. Each slide highlights a single core takeaway with readable typography and balanced spacing.
You receive clear content layouts, side-by-side comparison tables, and key performance indicator (KPI) metric callouts that you can present immediately or customize to your brand guidelines.
### Data Analysis and Visual Charts
Document creation also includes deep data analysis. You can upload spreadsheets, CSV files, or database exports and ask analytical questions in plain language.
Omnifact processes your numbers, calculates summary metrics, and generates custom visual charts directly in the chat thread. You can request bar charts, trend lines, and distribution plots that render inline and can be downloaded as high-resolution images.
## Creating a Document
Generating a file requires only a clear description of your goals and any relevant source material.
Start a new chat or continue an existing conversation where you want to work.
If you are building a document from existing data, click the **Plus (+)** icon on the left of the chat input and select **Upload from Device** or choose a connected cloud file. Learn more in [Attaching Files](/en/platform/core-features/chats/attaching-documents).
Specify the file type, purpose, and key content you want included.
**Examples:**
* "Create a 3-year financial model in Excel for a SaaS business, with an assumptions tab and dynamic revenue formulas."
* "Generate a two-page executive memo in Word summarizing our Q3 product roadmap."
* "Build an 8-slide PowerPoint deck in 16:9 presenting the key findings from the attached survey results."
* "Analyze this sales CSV and generate a bar chart comparing regional revenue."
The assistant will process your request, verify the content, and deliver a **Generated File Card** directly in the conversation. Click the card to preview the document or click the download button to save it to your device.
## Updating and Expanding Existing Files
You can also upload existing documents and ask the assistant to modify or expand them. For example:
* Attach a budget spreadsheet and ask the assistant to add a scenario analysis sheet with updated formulas.
* Upload a long PDF or document and request a summary slide deck in PowerPoint.
* Provide a draft memo in Word and ask the assistant to add formatted comparison tables.
The assistant reads the original file, makes the requested additions or calculations, and delivers an updated version while preserving your existing document structure.
## Previewing and Downloading Files
When the assistant completes a file, it appears directly in the conversation as a distinct **Generated File Card**:
* **File Metadata:** Displays the filename, file type icon, and file size.
* **Document Viewer:** Clickable cards open the built-in Document Viewer so you can review content without leaving Omnifact.
* **Direct Download:** Click the download icon to save the file locally.
## Security and Sandboxing
All document generation and data analysis take place in isolated, private execution environments:
* **Isolated Sessions:** Each conversation has its own temporary processing environment. Sessions reset automatically so your conversation data stays isolated.
* **Team Permissions:** Administrators manage access to code execution and document creation per user group. Learn more in [Group Management](/en/platform/team-administration/groups#workspace-access).
* **Network Egress:** The sandboxed execution environment has internet access enabled, allowing it to download public datasets or libraries when necessary.
Document creation and code execution capabilities depend on settings configured by your organization's administrators. If you do not see this capability in chat, verify with your administrator that the **Execute Code** capability is enabled for your group in [Group Management](/en/platform/team-administration/groups#workspace-access).