Skip to main content

OSL extraction

When you upload an Ontario Standard Lease, our AI extracts key information automatically. This page explains what gets extracted and how.

Extracted fields

Landlord information

FieldSource in OSL
NameSection 1 - Landlord(s)
AddressSection 1 - Address for Giving Notices
EmailSection 1 - Email
PhoneSection 1 - Phone

Tenant information

FieldSource in OSL
Name(s)Section 2 - Tenant(s)
EmailSection 2 - Email
PhoneSection 2 - Phone

Property information

FieldSource in OSL
AddressSection 3 - Rental Unit
Unit NumberSection 3 - Unit (if applicable)
ParkingSection 3 - Parking Space

Lease terms

FieldSource in OSL
Start DateSection 4 - Tenancy Start Date
End DateSection 4 - End Date (fixed-term)
Lease TypeSection 4 - Fixed-term or Month-to-month
Base RentSection 5 - Lawful Rent
Rent Due DateSection 5 - Due Date
Payment MethodSection 5 - Payment Method

Services and utilities

FieldSource in OSL
ElectricitySection 6
HeatSection 6
WaterSection 6
InternetSection 6
ParkingSection 6
Air ConditioningSection 6

Deposits

FieldSource in OSL
Rent DepositSection 7
Key DepositSection 7

Extraction technology

The extraction pipeline uses a multi-provider AI chain for maximum reliability:

  1. Google Gemini (primary) — First-choice AI provider for extraction
  2. OpenAI (fallback) — Used if Gemini is unavailable
  3. Anthropic (fallback) — Third-tier fallback

The system also performs:

  • PDF text parsing — For text-based PDFs
  • OCR — For scanned documents
  • Clause legality scanning — Automatically flags illegal lease clauses per the RTA

Progress tracking

A real-time progress UI shows extraction status as each field is processed. You can see which sections have been extracted and review results as they come in.

Confidence scores

Each extracted field has a confidence score:

High confidence (90-100%)

  • Field clearly readable
  • Standard format recognized
  • Likely correct

Medium confidence (70-89%)

  • Field readable but unusual format
  • Some ambiguity
  • Review recommended

Low confidence (below 70%)

  • Field difficult to read
  • Non-standard format
  • Manual verification required

Handling edge cases

Handwritten text

  • Printed text extracts best
  • Handwritten may need OCR
  • Very poor handwriting may fail

Multiple tenants

  • All tenant names are extracted
  • Each becomes a separate tenant record
  • All linked to the same lease

Non-standard formats

If your OSL has been modified:

  • Core fields usually still extract
  • Custom additions may be missed
  • Review carefully and add manually

Edit and regenerate

After extraction, you can edit any field and regenerate the OSL:

  1. Review extracted data on the OSL preview
  2. Click Edit Details to modify any field
  3. Click Regenerate to produce an updated OSL with your changes
  4. The regenerated OSL reflects your corrections

Comparing to original

You can compare extracted data to the original PDF:

  1. View extracted data
  2. Click "View Original"
  3. Side-by-side comparison
  4. Correct any discrepancies
Editing lease terms after generation?

If you later edit the lease's rent, dates, or other key fields, the generated PDF may become out of date. See Stale OSL detection below.

Stale OSL detection

When you edit lease terms (rent amount, start date, due day, or other OSL-relevant fields) after a PDF has already been generated, the system automatically marks the cached document as out of date.

An amber "Standard Lease is out of date — regenerate" banner appears on the lease Overview tab whenever the stored PDF no longer reflects the current lease terms.

warning

Downloading a stale OSL will serve the old PDF. Always regenerate before sending the document to tenants.

How to regenerate

  1. Open the lease and go to the Overview tab
  2. Click Regenerate Standard Lease (available on the Overview tab for unsigned and declined leases)
  3. The new PDF is generated and the out-of-date banner clears

Which leases can be regenerated?

esig statusCan regenerate?
None (unsigned)Yes
DeclinedYes
Sent / SignedNo — editing terms on a sent/signed lease does not mark it stale

Regenerating resets the stale flag and stores a fresh PDF. The prior document is replaced.

Improving extraction

Before uploading

  • Use clean, high-quality scans
  • Ensure all pages included
  • 300 DPI or higher recommended

After uploading

  • Review all fields
  • Check medium/low confidence items
  • Correct errors before confirming

Data validation

The system validates extracted data:

  • Dates are valid
  • Rent amount is reasonable
  • Postal codes are valid format
  • Email addresses are valid format

Invalid data is flagged for review.

Next steps