iTromsø · IBM, VC2
10 minutes per day — time spent reviewing potential stories
Independently reportedMedia & entertainment · Document processing · NLP · In production
Document processing
Teranet · SortSpoke
Vendor-reportedPublic sectorCanadaIn productionEnterpriseNLP
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by sortspoke.com (vendor self-report). Checked against the source page on 2026-09-05. 4 of 4 figures below appear on that page word for word.
The problem
Extracting valuable data from 250,000 historical land registry documents was prohibitively expensive due to variety, multiple formats, and bilingual content.
What was deployed
- Vendor
- SortSpoke
- Products
- SortSpoke's AI-powered document processing platform
- Technique
- NLP
- Build or buy
- Bought off the shelf
- Deployment
- SaaS
- Data used
- 250,000 historical Ontario condo declarations and Quebec land transfer documents
- Scale
- 250,000 documents
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
Cost savingsfrom traditional template-based solutions
“an estimated 85% cost savings over traditional template-based solutions”
Quoted word for word from the source
Time reductionfrom manual extraction
“97% time reduction compared to manual extraction”
Quoted word for word from the source
under 20 secondsProcessing time per documentper document
“Processing time was consistently under 20 seconds per document”
Quoted word for word from the source
1,000+Hours saved on manual processing
“1,000+ Hours Saved on Manual Processing”
Quoted word for word from the source
hoursTime to go live
“Up-and-running in hours”
Quoted word for word from the source
Zero maintenance costs, no IT consultants neededMaintenance costs / IT consultant needfrom traditional solutions requiring IT consultants
“Zero maintenance costs: No IT consultants were required as the system was fully managed by Teranet's own subject matter experts”
Quoted word for word from the source
ROI as stated: a particularly successful technology investment
“What impressed us most about SortSpoke was its ability to start delivering value immediately without extensive setup or template creation”
Difficulties and limits
- Valuable Data Trapped in Diverse Historical Documents
- Formats and layouts varied extensively with no standardization
- Documents were in both English and French
- Data points appeared in various formats—tables, paragraphs, or single values scattered throughout the documents
- Some data spanned across multiple pages
- manual extraction and existing template-based technologies were economically unfeasible
Sources
- sortspoke.com — vendor self-report, 2025-03-16
Similar deployments
Amplitude · Wolfia
4X — throughput of security questionnaires
Vendor-reportedTechnology & software · Document processing · AI agents · Scaled
Adyen · Rossum
70 — automation rate
Vendor-reportedBanking & finance · Document processing · NLP · Scaled · 2023
Skaylink · Moterra
dropped by around 80% — NIS2 preparation time
Vendor-reportedTechnology & software · Document processing · LLM · Scaled
OM Pharma · DrugCard
3 minutes — review time per article
Vendor-reportedPharma & biotech · Document processing · NLP · In production
AMPREP (Amalgamations Repco) · Cimplify.AI
100% — invoice automation
Vendor-reportedManufacturing · Document processing · NLP · In production