Documents drive businesses. From invoices and contracts to reports and compliance records, PDFs remain the universal standard for business communication. The ability to process, transform, and manage PDFs programmatically is essential.
Today, we’re excited to introduce the PDF by Workato connector, a native solution that brings comprehensive PDF processing capabilities directly into your recipes. No external services, no custom scripts, no workarounds required.
Why PDF Processing Matters
Modern document workflows demand flexibility and orchestration. Across every department, teams handle PDFs in increasingly sophisticated ways: your Accounts Payable (AP) team receives batch invoice files containing multiple invoices that need to be split into individual documents for IDP processing; your legal department consolidates contracts, amendments, and exhibits into complete packages; your operations team generates PDF reports from their business intelligence dashboards, database queries, and system logs to share insights with stakeholders.
These are everyday document workflow needs. The PDF by Workato connector makes them simple, reliable, and fully orchestrated within your existing recipes.
Meet the PDF by Workato Connector
The PDF by Workato connector brings powerful capabilities that transform how you handle documents in your workflows:
Split PDF Files: Break large PDF batches into individual documents by page ranges or fixed intervals.
Merge PDFs: Combine multiple files into consolidated documents, from contract packages to executive reports.
Convert to PDF: Generate PDFs from Word documents, Excel spreadsheets, CSV files, HTML content, and images.
Extract Text: Pull raw text from digital PDFs to feed into AI workflows for summarization or content analysis.
Stamp PDFs: Add text or image overlays like watermarks, approval codes, or processing timestamps to existing documents.
Specifications:
- Supported formats: Word (.docx), Excel (.xlsx), CSV (.csv), HTML, and image (.jpg/.png) files can be converted to PDF.
- Maximum file size: 100 MB
Why Choose Native PDF Processing?
Unlike solutions that require external PDF services or custom code, the PDF by Workato connector processes documents natively within recipes. This means:
Simplified Setup: No need to sign up for third-party PDF services, manage additional API keys, or maintain separate subscriptions. Everything works out of the box within Workato.
Enhanced Security: Your documents never leave Workato. No sending sensitive contracts, invoices, or HR documents to external services for processing.
Unified Platform: Build, test, and maintain your entire document workflow in one place. No context switching between tools or troubleshooting integration issues between multiple services.
Use Cases
Let’s look at how you can put the PDF by Workato connector to work.
HR Onboarding
Your HR team sends new hires a welcome packet containing offer letters, benefits information, company policies, and department-specific materials. Different roles require different combinations of documents.
The workflow:
- Triggered when a new hire is added to your human resources information system (HRIS)
- Pull the appropriate documents from SharePoint based on role, department, and location
- Convert any Word documents to PDF for consistency
- Merge the offer letter, benefits guide, policies, and role-specific materials into a single welcome packet
- Stamp the packet with the employee name and start date
- Send via DocuSign for acknowledgment signatures
New hire welcome packets generate instantly with role-appropriate documents. Your HR team focuses on welcoming new employees rather than assembling packages.
Contract Management
Your legal team manages contracts stored across SharePoint, DocuSign, and email attachments. When a contract comes up for renewal, you need to consolidate the original agreement, all amendments, and related communications into a single package.
The workflow:
- Trigger when a contract renewal date approaches
- Search SharePoint, DocuSign, and Gmail for all related documents using contract ID
- Merge the original contract, amendments, and correspondence into a single PDF
- Save the consolidated package to your contract management system
Contract packages assemble automatically when needed. Your legal team focuses on negotiating terms rather than gathering files.
Marketing Content Analysis
Your marketing team receives industry reports, competitor whitepapers, and partner proposals that need quick analysis for planning. Reading through lengthy documents to surface a few key insights pulls your team away from the work that actually moves strategy forward.
The workflow:
- Triggered when a new PDF is uploaded to your “Market Research” folder in Google Drive
- Extract the raw text from the document using the PDF by Workato connector
- Send the extracted text to your preferred LLM using Workato’s AI by Workato connector, with prompts to summarize key findings in a few bullet points, identify competitive threats, and pull out relevant market size data
- Post the AI-generated summary to your #marketing-insights channel in Slack
- Save the full text to a vector database for future retrieval and analysis
Fifty-page reports are summarized the moment they’re uploaded. Your marketing team focuses on strategy rather than reading through lengthy documents.
Complementary Power of the PDF connector and IDP
Accounts Payable Workflow: PDF Connector Meets IDP
Your accounts payable (AP) team receives a daily PDF file containing 50+ vendor invoices from your procurement system. Each invoice needs to be processed individually through your invoice approval workflow and accounting system. This is where the PDF by Workato connector and IDP by Workato work together to deliver a complete document workflow.
The workflow:
- Split the batch PDF by page ranges (e.g., every 10 pages)
- Use IDP to extract structured data from each document. IDP comes packed with features, including pre-configured schemas, free-form schema configuration, and the ability to auto-map data to the fields you need. Each field extracted from a document is given a confidence score, which can be used with recipe logic to build a custom review process based on your process needs.
- Route each invoice through your approval workflow based on IDP-extracted data
- Stamp processed invoices with approval codes
Now your AP team can start each day with invoices already split, extracted, and ready for review.
While both tools work with documents, they serve distinct purposes that multiply their value when combined:
PDF by Workato handles document manipulation. It splits batches, merges files, converts formats, adds stamps. Think of it as your document preparation and assembly line.
IDP by Workato understands document content. It identifies invoice line items, extracts purchase order numbers, recognizes vendor names, and pulls data fields with high accuracy using AI. Think of it as your intelligent document reader.
Together, they create end-to-end orchestration: the PDF by Workato connector prepares your documents for processing and IDP extracts the critical business data.
Getting Started
Ready to build your first PDF connector workflow? Good news, the PDF by Workato connector is available now in your workspace. Get started with the documentation.