Capabilities
Language & Data
Software that can read Sinhala, Tamil and the documents nobody else can.
The problem we solve
The scripts and documents that matter most locally — Sinhala, Tamil, degraded archival material — are exactly the ones global tools handle worst.
What we do
OCR for Sinhala and Tamil at 97% accuracy; document intelligence for archives, court records and print collections; and the data-processing pipelines that make messy, real-world material usable at scale.
How we work
Our five-stage method — Understand, Model, Build, Validate, Operate. See the approach →
FAQ
[CONTENT REQUIRED]
Relevant projects
Sinhala & Tamil OCR
Optical character recognition for Sinhala and Tamil at 97% accuracy, digitising archives, court records and print collections at scale.
View case →
AskLex.law
A legal research assistant for Sri Lankan law: statute and case-law questions answered in seconds, with citations a lawyer can verify.
View case →