nSymbol Tag Overview
Professional Document Generation with AI-in-the-Loop
A desktop application for Windows and Mac that puts you in control of AI-assisted document workflows
Gathering Data - The Hard Part Made Easy
For professionals, traditional document creation starts with a painful process: manually entering data, chasing down information across multiple sources, copying and pasting from old files, and hoping you didn't miss anything critical.
Tag transforms data collection into a streamlined workflow
Forms automatically adapt to your needs, pulling data from wherever it lives: source documents (PDFs, Word files, scans), databases and APIs, spreadsheets, or manual entry when needed.
Instead of reading a 20-page assessment report and manually typing key details into fields, you attach the document and let AI extract exactly what you need. Tag doesn't display the AI’s response; it searches for specific information and maps it to the right fields in the form.
You can chain multiple AI operations together: scan several documents, pull test scores from each, calculate summaries, and populate a comprehensive form. As your workflow matures, the amount of work that can happen from a few mouse clicks is tremendous.
The staging area concept
Forms become a verification point where you review what AI extracted before it flows into your final document. No hallucinations reach your output because you catch them here. When multiple team members contribute data, everyone works with the same shared forms, adding their pieces as information becomes available.
Many workflows include multiple “logical“ staging areas. What this really means, is the same forms are used for human review at multiple stages of the process.
For example, after autofill runs the imported data is reviewed in forms to ensure accuracy. When that is done, AI-Chains can be run to transform the data in some way. The same forms are then used as a staging area for final review and manual editing. So the concept of a staging area is not complex, it simply refers to a step in the workflow that requires human input. Everything revolves around the forms.
What Makes Tag Different
No Black Box AI
Unlike tools that generate entire documents from a single prompt (with unpredictable results), Tag breaks complex tasks into smaller, focused operations. Each AI interaction has a specific job: extract these dates, summarize this section, classify this document type.
You see exactly what AI is doing because you design each step. Prompts aren't hidden - they're in your library, versioned and testable.
Human-at-the-Wheel
AI assists, but humans decide. You choose where AI helps (data extraction, first drafts, pattern recognition) and where human judgment is required (interpretation, clinical decisions, final approval).
Every AI-assisted workflow has explicit review points. You're never locked into accepting AI suggestions; you verify, modify, or reject as appropriate.
Your Data Stays Yours
Tag is a desktop application, not a web service. Your files live on your computer, not on our servers. When you use AI features, Tag connects directly to AI providers (like AWS Bedrock for our Managed plan, or AI vendors directly for BYOK plans) with encrypted requests that aren't retained for training.
This architecture enables HIPAA and PIPEDA alignment. We don't claim "Tag is HIPAA compliant" (compliance requires organizational policies beyond software), but the design supports regulatory requirements for healthcare, education, and other sensitive data environments. We can help you define the additional policies required to achieve proper HIPAA and PIPEDA compliance.
Transforming Data - AI as Your Assistant
After you have autofilled, imported, or manually entered starting data it is time to transform it. This is where AI-Chains can help to identify patterns, generate summaries, create narrative content that sounds like you.
An AI-chain bundles almost everything needed for a specific task:
The data to process - this is pulled with precision from all forms related to the document
Additional source documents - you can read from unchanging file paths, or get prompted at runtime for dynamic ones
There may be a system prompt that Tag attaches to help with certain tasks
There may be a custom prompt from the user’s prompt library
AI vendor and model settings can be customized for each chain
Save it once, attach it to a form field, and run it with a click. The field may also attach writing samples that guide style. This means that the same AI-Chain can be paired with different writing samples from different team members. This can dramatically change the end result.
No vendor lock-in
Switch between Anthropic, Google, OpenAI, or Cohere models effortlessly. Compare results. Use different vendors for different tasks based on speed, cost, or capability. When a model gets upgraded or a vendor changes pricing, you can adapt without rebuilding your workflows.
Full transparency
Every AI interaction generates a detailed JSON trace showing exactly what was sent and received. For PIPEDA and HIPAA requirements, this creates the audit trail auditors expect. For quality improvement, it shows you what's working and what needs refinement.
No hallucinations on verified data
Because AI-Chains work on data you've already verified in the staging area, and because prompts are focused on specific tasks with clear context, the risk of AI making things up drops dramatically. You're not asking it to generate an entire report all at once; you're asking it to process verified information according to your instructions.
Generating Documents - Professional Quality, Guaranteed
You have clean data. You've processed it with targeted AI assistance. Now you need a professional document that meets your standards.
Tag's template designer gives you complete control
Design sophisticated layouts with tables, sections, conditional content, and custom styling - all without coding. Mix fixed content (your standard language, disclaimers, formatting) with dynamic sections that pull from your data or AI-generated text.
Tag was designed to support important open standards including RNG, XSLT, XPath and XSL-FO. These provide the generation engine.
In fact, even if you don’t use AI you can build complex dynamic content using intuitive point-and-click screens. You can import data from CSV or elsewhere, use it in expressions, create repeating tables, create dynamic lists, and much more. Tag’s document generation engine pre-dates the AI revolution and provides a powerful toolkit for you to create the output you want.
Multiple output formats
Generate word processing documents (.docx), Google Docs, or fillable PDFs. The .docx files created can be edited by most modern word processors, including Microsoft Word. Google Docs can be generated directly within Google Docs without needing to save to a file first. Complex government PDF forms can be filled from data in your forms, and saved to a PDF file for final editing.
In all cases you are pulling data from verified forms in a Tag report. Using AI is optional, and it can be used as sparingly (or expansively) as you want.
Document catalogs for common needs
Tag includes curated catalogs for psychological assessments (WAIS, WIAT, WISC, and 60+ other protocols), speech-language pathology evaluations, VA disability benefits questionnaires, and educational reports.
These aren't generic templates; they're built by subject-matter experts who understand the data and intent of the generated document. Data fields, prompts, and writing samples are already configured. You just customize and provide the source data.
Multiple topics downloaded from catalogs can be combined together. They become conditional sections in a report, that hide or show depending on checkboxes in the setup form.
For private or organizational needs, custom catalogs make your document types point-and-click accessible. Your team's expertise becomes institutional knowledge rather than staying in individuals' heads.
Aggregation and analysis
Tag has another key feature that has nothing to do with AI. It can combine data from multiple completed documents into spreadsheets for analysis. This helps you see patterns across your caseload, generate reports for grant applications, or satisfy reporting requirements for funders.
This feature builds on Tag reports. Once a report is created, it has a clearly defined set of data fields. Every time you generate a document from that report, Tag saves the data in a structured file.
After you've created multiple documents, you can ask Tag to gather all similar files and combine them into a CSV spreadsheet, with each document becoming one row. You can then analyze the spreadsheet directly or import it into other software.
For example, clinicians often use this to track their practice data annually. If you organize client documents in subfolders by year (like a "2026" folder), Tag can scan all subfolders to find matching reports. The result is a spreadsheet with one row per client and columns that match the form fields, making it easy to analyze trends over time.
Four Apps Working Together
Tag consists of four integrated applications, each with a specific role:
Dashboard - Your starting point for getting-started wizards, catalog browsing, and quick access to common tasks. Launch forms, create reports, generate documents - all from one place.
Scribe - Template designer and document generator. Create word processing templates with full formatting control. Design forms that collect data from multiple sources. Run batch autofill operations on up to 30 source documents in parallel. Generate Word docs, Google Docs, or fillable PDFs.
Automate - AI-Chain builder and executor. Create reusable AI operations that bundle context, prompts, and model settings. Switch between AI vendors. Capture detailed audit trails. Automate also supports other files types to varying degrees (XML, JSON, CSV, ZIP, SVG, PDF and more).
Blueprint - Workflow modeler and architecture visualizer (consulting clients only). Create formal models of your data flows using OWL ontologies. Visualize where AI touches data, where humans review, and how systems integrate. Query your data model to support governance and change management.
You don't need all four apps for every task. Solo practitioners might work primarily in Dashboard and Scribe. Small teams might add Automate for custom AI-Chains. Enterprises adopt Blueprint for formal governance.
The apps share data seamlessly. Forms created in Scribe run AI-chains built in Automate. Catalogs browsed in Dashboard generate reports for use in Scribe. Workflows modeled in Blueprint orchestrate across all three.
Governance and Growth - Built for the Long Term
As your use of AI grows, management becomes critical. Which prompts work well? What happens when models change? How do you ensure team members use AI consistently and safely? Tag is designed for mature, sustainable AI adoption.
Security by design
Data is processed locally on your desktop. Encrypted transit ships it to and from AI services. You control what information gets sent to which AI vendors.
When private personal information (PII) is involved, our Managed AI plan routes requests through AWS Bedrock with guarantees of zero data retention and no training on your data/prompts. For BYOK plans, you connect directly to AI vendors and follow their privacy policies. Either way, audit trails capture every AI interaction, supporting HIPAA, PIPEDA, GDPR, and other regulatory frameworks.
Machine-readable architecture
Blueprint (available through consulting engagements) creates formal models of your workflows using OWL ontologies. This isn't just documentation - it's a knowledge base that can be queried. Ask questions like: "Which workflows use this AI model?" "Which prompts process protected health information (PHI)?" "Where do humans perform reviews?"
Prompt libraries and catalogs as organizational knowledge
Successful prompts become reusable assets. Version them, test them, and share them across your team. When models change you can modify affected prompts in one place. If new team members join, they can learn from pre-approved AI interactions. If team members leave, institutional knowledge doesn't walk out the door.
Catalogs are used to support reusable report sections. They encapsulate data field definitions, word processing templates (if needed), AI prompts and writing samples are related to one subject. Use sections from our pre-built catalogs, or have us create a custom catalog for your team.