Skip to main content

​
Document Intelligence

Every document is unique, but legal documents follow patterns. Our system understands these patterns and uses that knowledge to provide smarter validation, better risk detection, and more accurate editing.

​
How We Understand Documents

When you upload a document, we don’t just process text. We understand:

Document Type

Is this an NDA, MSA, SOW, or something else?

Structure

What sections exist and how are they organized?

Key Parties

Who are the parties to this agreement?

Critical Terms

What are the key dates, terms, and provisions?

​
Document Type Recognition

We automatically identify the type of document you’re working with:
Document TypeWe Look For
NDAConfidentiality definitions, permitted disclosures, return of information
MSAServices descriptions, payment terms, change order provisions
SOWProject scope, deliverables, milestones, acceptance criteria
EmploymentPosition, compensation, benefits, restrictive covenants
SaaSAccess rights, SLA, data protection, service levels
PurchaseGoods/services, pricing, delivery, acceptance
LeasePremises, rent, term, maintenance obligations
AmendmentRecitals, specific modifications, ratification
Document type affects how we validate, what risks we look for, and what sections we expect to find. An NDA has different standards than an MSA.

​
Expected vs. Actual Structure

​
What We Expect

Each document type has expected sections. For example, an NDA typically includes:
Definitions
Confidential Information
Obligations
Exceptions/Exclusions
Term and Termination
Return of Information
Remedies
Miscellaneous Provisions

​
What We Find

We analyze your actual document and identify:
  • Present sections that match expected structure
  • Missing sections that are typically included
  • Additional sections specific to your document
  • Section boundaries for targeted editing

​
Why This Matters

When a standard section is missing, it might be:
  • Intentional (not needed for this deal)
  • An oversight (should be added)
  • Different naming (called something else)
We note these findings without blocking your work—just giving you visibility.

​
Key Information Extraction

​
Parties

We identify the parties to the agreement: 
Parties Detected:
- Acme Corporation (the "Company")
- John Smith (the "Consultant")

​
Key Dates

We extract important dates:
Date TypeValue
Effective DateJanuary 1, 2024
Term24 months
ExpirationDecember 31, 2025

​
Critical Terms

We identify key terms that affect the agreement: 
Key Terms:
- Governing Law: Delaware
- Arbitration: Yes, AAA Rules
- Confidentiality Period: 5 years
- Non-Compete: 2 years, 50-mile radius

​
How Classification Improves Editing

​
Better Validation

When we know document type:
  • We check for section-specific requirements
  • We apply appropriate risk thresholds
  • We verify expected provisions are present

​
Smarter Risk Detection

Different documents have different risks:
  • NDA: Focus on confidentiality scope, duration, permitted disclosures
  • MSA: Focus on liability caps, indemnification, IP provisions
  • Employment: Focus on compensation, non-compete, termination rights

​
More Accurate Editing

Understanding document structure means:
  • Section references are understood in context
  • Related provisions are updated consistently
  • Cross-references remain accurate

​
Confidence Levels

Our classification includes a confidence score:
ConfidenceMeaning
90%+Very clear document type, strong pattern match
70-89%Likely document type, most indicators present
50-69%Possible document type, some indicators present
Below 50%Unclear type, classified as “general”
When confidence is lower, we apply broader validation rules to ensure nothing is missed. We err on the side of more thorough review.

​
Automatic Tier Selection

Document classification determines validation tier:
ClassificationValidation TierWhy
Legal contract (high confidence)LegalFull 5-pass validation
Legal contract (lower confidence)LegalErr on side of caution
Non-legal documentStandardEfficient processing
Complex/high-valueEnterpriseMaximum rigor (optional)
You can always override automatic tier selection if you need more or less validation for a specific document.

​
Supported Document Types

Confidentiality agreements, mutual NDAs, unilateral NDAs, confidential disclosure agreements
Professional services agreements, consulting agreements, master agreements
Work orders, project agreements, service orders, task orders
Offer letters, employment contracts, executive employment agreements, contractor agreements
Software license agreements, subscription agreements, cloud services agreements
Sales agreements, procurement contracts, supply agreements, vendor agreements
Commercial leases, equipment leases, real property leases
Contract amendments, modifications, change orders, supplements

Risk Detection

How classification enables smart risk detection.

Multi-Pass Review

How we validate based on document type.