Document Templates

Upload your own branded Microsoft Word and HTML templates and let Servantium merge in engagement and quote data automatically. Generate proposals and SOWs in seconds.

Note

For a high-level comparison of how templates and data schemas differ, see the Templates vs. Data Dictionaries overview.

Quickstart

Navigate to Settings > Document Templates to upload and manage your organization’s document templates.

In-Depth

Servantium uses standard Microsoft Word (DOCX) files and generated HTML code as templates. This allows you to maintain your brand’s exact styling, typography, and layout while automating the insertion of data.

Creating and Uploading

  1. Design your template in Microsoft Word.
  2. Use Merge Fields to indicate where data should be inserted (e.g., {{engagement.name}}, {{quote.total}}).
  3. In Servantium, go to Settings > Document Templates.
  4. Click Create. The system instantly generates a new template and redirects you directly to its workspace.
  5. On the template screen, rename the template to match its purpose.
  6. Optionally upload an Example Document (Word or PDF). The system securely stores this via internal Google Cloud Storage (gs://) URIs and provides it to the AI document templating agent as reference context.
  7. Upload your master DOCX file, or configure raw markup directly in the HTML Content code editor.

AI Template Generation

Servantium features intelligent AI agents that can automatically convert your example documents into reusable HTML/CSS templates.

  • Multimodal Extraction: When you upload an example document, the backend multimodal AI processes the file, extracting text via OCR and identifying assets (like logos).
  • Code Editor: The resulting structure populates the HTML Content field. This dedicated code editor provides an improved developer experience for configuring and refining the final template markup, and features a live preview that updates in real-time as you code.
  • Visual QA: The system runs a visual QA pass to check if the generated HTML visually matches the source document structure. If minor spacing, font, or syntax errors are detected, the QA agent automatically makes up to 5 attempts to fix them itself using the system tools. If visual QA still fails after 5 attempts, the system finalizes the document and leaves the remaining formatting for manual human review to prevent infinite loops.
  • Workflow Summary: Upon successful completion, a dedicated Summary Agent provides a conversational overview of all assets generated during the session, including templates, reusable snippets, and custom data fields.

How it works

When a user generates a document from an engagement or quote, the backend merging engine:

  1. Fetches the template.
  2. Scans for all merge fields.
  3. Resolves those fields using data from the specific Engagement, Quote, Organization, and the User’s Profile.
  4. Generates a final, ready-to-send PDF or DOCX file.
Note

For a complete list of available merge fields and advanced formatting options (like tables and conditional logic), refer to the Documents Guide.

Need more help?

Our support team is available to assist you.

Contact Support