Tag Features
Everything you need for AI-assisted document workflows—from data collection through professional output
Smart Data Collection
Traditional data collection is tedious: open a document, find the relevant information, switch to your form, type it in, repeat 50 times. Tag transforms this into a streamlined workflow.
### Batch Autofill Wizard
Select up to 50 documents at once from anywhere on your computer. The wizard provides:
- Multi-folder selection - Browse and pick files from different locations
- Favorite folders - Save frequently used paths for quick access
- Document-to-form mapping - Attach relevant source documents to each form that needs data
- Per-form AI configuration - Choose AI vendor (Claude, Gemini, OpenAI, or Cohere) and model for each form independently
- Routing flexibility - Use Tag-managed keys (AWS Bedrock) or your own API keys (BYOK) per form
- Parallel processing - Up to 30 forms process simultaneously
- Real-time progress - Progress bars show what's running; detailed JSON traces show what happened
How it works: You design forms with fields that match the data you need. Forms use RNG (RELAX NG) schemas that define structure and validation rules. When you run batch autofill, AI scans your source documents, finds the specific information for each field, and populates the form. You review and correct before the data flows into final documents.
### Advanced Data Import
Unlike simple form builders that only accept manual typing, Tag pulls data from multiple sources:
- Excel/CSV imports with field-level transformations (e.g., reformat dates, split names, apply calculations)
- Database queries (SQL: MySQL, PostgreSQL, SQL Server, Oracle; NoSQL: MongoDB, CouchDB)
- API calls to web services and cloud systems
- Semantic data endpoints for knowledge graphs and linked data
- Office documents (extract tables from Word, data from Excel)
- Manual entry when needed
### Coordination Across Teams
When multiple people contribute to one document:
- Shared forms become the coordination point
- Each team member adds their data when available
- Form status tracking shows what's complete and what's pending
- Permissions control who can edit what
- Version history tracks all changes
> Why this matters: Turn 3 hours of data entry into 15 minutes of verification. Stop losing time to manual copying and pasting. Start focusing on reviewing and improving content instead of typing it.
Targeted AI Processing
The difference between AI that helps and AI that frustrates is control. Tag doesn't generate entire documents from vague prompts—it processes specific data with specific instructions.
### AI-Chains for Precision
AI-chains bundle everything needed for a focused task: the data to process, the context to provide, the prompt that instructs the AI, and writing samples that guide style.
How AI-chains work:
1. Attach to form fields - By convention, fields named `*_ai` support AI-chain attachment
2. Define data sources - Select which form fields, local files, or other data the chain sees
3. Connect prompts - Pull from your prompt library or write inline
4. Provide writing samples - Show AI your professional voice with examples of your writing
5. Choose vendor and model - Use Claude for complex reasoning, Gemini for fast extraction, or compare multiple models
6. Execute on demand - Run AI on one field, one form, or all forms together—you decide when
What makes this powerful:
- Granular control - AI processes exactly the data you specify, nothing more
- Reusable patterns - Save successful chains for similar tasks elsewhere
- Vendor flexibility - Switch between Anthropic Claude, Google Gemini, OpenAI GPT, or Cohere models per task
- Complete transparency - Detailed JSON traces show every request and response (required for HIPAA/PIPEDA audit trails)
- No hidden prompts - Everything is in your library, versioned and testable
Writing samples guide style:
Instead of relying on AI's default voice, provide samples of your actual writing. AI analyzes the examples and matches:
- Tone and formality level
- Sentence structure and paragraph length
- Technical vocabulary appropriate to your field
- Organizational patterns you consistently use
This isn't just prompt engineering—it's teaching AI to write like you.
### Prompt Library Management
Successful prompts become organizational knowledge assets:
- Version control - Track prompt changes over time
- Testing and validation - Confirm prompts work before deploying broadly
- Sharing across teams - Make proven prompts available to everyone
- Metadata tagging - Label by capability (extract, summarize, classify), domain (healthcare, education, legal), or use case
- Model compatibility tracking - Document which models work best with each prompt
### Multiple AI Vendors Supported
Tag integrates with four major AI providers:
| Vendor | Strengths | Typical Use Cases |
|--------|-----------|-------------------|
| Anthropic Claude | Most accurate, handles complex reasoning, excellent with repeating elements | Primary choice for AI-chains and complex content generation |
| Google Gemini | Fastest, lowest cost, good for simple structured extraction | Autofill of straightforward forms, verbatim text extraction |
| OpenAI GPT | Moderate speed and cost, balanced capabilities | Fallback for autofill when Claude is too slow/costly |
| Cohere | Canadian data residency available | Organizations with data sovereignty requirements |
Switch vendors anytime: All prompts work across providers with minimal adjustment. Compare results, manage costs, avoid vendor lock-in.
> Why this matters: Predictable, professional-quality results because you control exactly what AI does. No hallucinations in your outputs because AI works on verified data with targeted instructions. Reusable expertise across your team instead of knowledge trapped in individuals' heads.
Professional Document Generation
Tag excels at generating complex documents that maintain your standards and branding. The template designer gives complete control without requiring coding expertise.
### Rich Template Designer
Create sophisticated layouts with full formatting control:
- Tables with dynamic rows, merged cells, calculated totals
- Sections with conditional inclusion based on data
- Styles and formatting - fonts, colors, spacing, headers/footers precisely as you want them
- Mixed content - combine fixed text (disclaimares, standard language) with dynamic fields and AI-generated sections
- Repeating elements - generate tables or paragraphs for lists of items in your data
- Nested structures - complex documents with multiple levels of organization
### Multiple Output Formats
Generate from one template:
- Microsoft Word (.docx) - full formatting preserved, ready for final editing
- Google Docs - direct export to Google Drive for cloud collaboration
- Fillable PDF - include form fields, signatures, checkboxes for recipient completion
Your branding, formatting, and professional standards remain consistent across all formats.
### Document Catalogs
Tag includes curated catalogs professionally designed by subject-matter experts:
Psychological Assessments (60+ protocols)
- Cognitive: WAIS-4, WAIS-5, WISC-5, WPPSI-4, Leiter-3, Ravens-2, Shipley-2, WNV
- Academic: KTEA-3, WIAT-3, WIAT-4, WJ-4-ACH, WRAT-5
- Executive Functioning: BRIEF-2, Brown EF/A, CEFI, Conners-4, CPT-3, D-KEFS, DREF
- Memory: ChAMP, CVLT-3, CVLT-C, WMS-4, WRAML-3
- Mood/Behavior: BAI, BASC-3, BDI-2, BYI-2, CBRS, MASC-2, MMPI-3, PAI, RCADS
- Adaptive: ABAS-3, Vineland-3
- Neuropsychological: Beery VMI, Motor Battery, RCFT
- Autism: ADI-R, ADOS-2, ASRS, GARS-3, SRS-2
- Plus validity tests, forensic instruments, and report sections
Speech-Language Pathology
- Speech: DEAP, DEMSS, GFTA-3, SPAT-D-3
- Language: CELF-5, CELF-P3, PLS-5, PPVT-5, TOLD-P:5, TOLD-I:5
- Phonological: CTOPP-2, NWR, PAT-2
- Plus screening tools and report sections
VA Disability Benefits Questionnaires
- 40+ fillable PDF forms across all body systems
- Pre-configured prompts for autofill from medical records
- Support for regulated healthcare documentation
Educational Reports
- Progress reports, IEPs, psycho-educational evaluations
- Structured for team collaboration
Each catalog includes:
- RNG schemas that define form structure
- Default autofill prompts tuned for specific tests/assessments
- Writing samples showing professional report style
- Output templates formatted to professional standards
### Custom Catalog Creation
For organizations with specialized needs:
- Document your unique report types and forms
- Bind them to AI prompts for autofill and generation
- Share across your team for consistency
- Version and update as practices evolve
Your team's expertise becomes reusable institutional knowledge instead of staying in individuals' heads.
### Data Aggregation and Analysis
Need to see patterns across many documents?
- Combine data from multiple completed documents into spreadsheets
- Track trends across caseloads
- Generate reports for grant applications or outcome tracking
- Satisfy funder reporting requirements
- Identify patterns for quality improvement
> Why this matters: Your standards, your branding, every time—without compromise and without coding. Professional-quality documents in minutes instead of hours. Institutional knowledge that survives staff transitions.
Flexible Integration
Real-world workflows involve data from many places in many formats. Tag handles integration complexity so you don't have to.
### Data Source Connectivity
File-based imports:
- CSV and Excel with field-level transformations (split fields, reformat dates, apply calculations, merge data)
- XML and JSON with bidirectional conversion (read either, write either, transform between them)
- Office documents - extract tables from Word, data from Excel, text from PDFs
Database connections:
- SQL databases - MySQL, PostgreSQL, SQL Server, Oracle, SQLite
- NoSQL systems - MongoDB, CouchDB, and other document stores
- Direct queries or parameterized imports for flexibility
- Read and write operations where permissions allow
Web and cloud services:
- REST APIs with authentication (OAuth, API keys, basic auth)
- SOAP services for legacy system integration
- Cloud storage (AWS S3, Google Cloud Storage, Azure Blob)
- Semantic data endpoints (SPARQL for knowledge graphs and linked data)
Secure network access:
- Connect to databases on private networks (VPN, corporate intranet)
- Access file shares behind firewalls
- Work with systems that can't be exposed to the public internet
### Desktop Architecture Advantages
Tag runs on your computer (Windows or Mac), not in a browser:
Performance benefits:
- Fast processing of large files without upload/download delays
- Parallel operations leverage your CPU cores
- No waiting for server availability or network congestion
- Batch processing runs overnight on your machine if needed
Security advantages:
- Files stored locally, not on remote servers
- You control what data leaves your computer
- Direct connections to secure networks
- Encrypted transit when calling AI services
- Data masking for sensitive fields during testing/demos
Reliability benefits:
- Works offline for local data operations
- No dependency on external service uptime
- Your workflows keep running even if vendors have issues
### XML and JSON Expertise
Tag has sophisticated support for structured data:
- XML parsing and generation with schema validation (XSD, RELAX NG)
- JSON handling for modern web APIs
- Bidirectional conversion - read XML, write JSON; read JSON, write XML
- XSLT transformations for complex document generation
- XPath and JSONPath queries for precise data extraction
- Namespace handling for enterprise XML standards
This makes Tag suitable for industries with strict data interchange requirements (healthcare HL7, financial FIXML, government standards).
### Security Designed In
Local data storage:
- Your files live on your computer, not Tag servers
- Standard OS file permissions apply
- Backup and recovery under your control
Encrypted transit:
- All AI calls use HTTPS/TLS
- Requests to cloud services encrypted end-to-end
- No plaintext data in transit logs
Data flow control:
- You choose what data goes where
- Explicit routing per AI operation (BYOK vs Managed)
- Data masking features: send fake data during testing
Audit trails:
- Detailed JSON traces for every AI interaction
- Logs support HIPAA, PIPEDA, GDPR compliance requirements
- Track who did what and when
> Why this matters: Work with data wherever it lives, however it's formatted. Better security than web applications. Fast local processing. Integration patterns that work with your existing systems.
## How Features Work Together
Tag's capabilities combine to create seamless workflows:
### Example: Psychological Assessment Report
1. Data collection - Upload test protocols (PDFs), previous reports, background documents
2. Batch autofill - Select all source documents, map to relevant forms, run extraction in parallel
3. Review and verify - Check auto-filled data for accuracy, correct any errors, add missing information manually
4. AI transformation - Run AI-chains to generate narrative sections (Background, Behavioral Observations, Diagnostic Impressions)
5. Document generation - One-click generation of formatted Word document with all content assembled
6. Final editing - Clinician reviews, adds professional judgment, makes refinements
Time savings: From 3+ hours of manual writing to 30 minutes of review and refinement.
### Example: Team-Based Student Evaluation
1. Form setup - Educational coordinator creates shared forms for student case
2. Distributed data entry - Multiple specialists contribute their assessments asynchronously
- School psychologist adds cognitive test results
- Speech therapist adds language evaluation data
- Classroom teacher adds behavioral observations
- Social worker adds family background
3. AI synthesis - Chains pull from all forms to generate summary sections
4. Coordinator review - Reviews complete picture, ensures consistency
5. Document generation - IEP and progress report generated with all input integrated
6. Team approval - All contributors review final versions
Coordination benefits: No more emailing Word docs back and forth. Clear visibility into what's complete. Consistent format across many students.
### Example: Enterprise Compliance Workflow
1. Database integration - Connect to corporate HR and incident databases
2. Data extraction - Automated queries pull relevant cases needing documentation
3. AI classification - Classify incident types and route to appropriate templates
4. Batch processing - Generate initial reports for 50+ cases overnight
5. Human review queue - Compliance staff review auto-generated reports, flag issues
6. Workflow tracking - Blueprint model shows where each case is in the process
7. Audit trail - Complete documentation of what AI did, what humans changed
Scale benefits: Process hundreds of cases consistently. Clear audit trail. Compliance team focuses on exceptions, not routine documentation.
---
## What You Won't Find in Tag
Autonomous AI agents: Tag does not include AI agents that independently take actions. Every AI operation is explicitly triggered by a human clicking a button. This is deliberate—we believe in Human-at-the-Wheel, AI-in-the-Loop.
Generic document generation: Unlike tools that generate entire documents from a single vague prompt, Tag requires you to design workflows. This takes more initial setup but produces predictable, compliant results.
Cloud-based storage: Tag is a desktop application. If you need cloud storage for your files, use your existing solutions (Google Drive, OneDrive, Dropbox). Tag reads from and writes to wherever you store files locally.
Real-time collaboration editing: Multiple users can contribute to shared forms asynchronously, but Tag doesn't support Google Docs-style simultaneous editing of documents. Final document generation happens on one person's computer.
These are intentional design decisions aligned with our philosophy: human control, predictable workflows, security, and compliance.
Tag is available for Windows 10/11 and macOS 11+. All features described are included in both Individual-BYOK and Individual-Managed subscription plans. Blueprint modeling features are available through consulting engagements.