Methodology
How Lawerly Works
Last updated: July 3, 2026
Lawerly is grounded in a verified, hand-built knowledge graph of Pakistani statutes and case law. AI models are used for language generation and retrieval — they are not the source of legal truth. Every citation and case-status check comes from our own database, not from the AI model itself.
Which models we use
| Feature | Model | Hosting Country |
|---|---|---|
| Legal research chat | DeepSeek v4-flash | China (with US-hosted Gemma fallback) |
| Document & argument drafting | DeepSeek v4-flash | China |
| Scanned-judgment reading | Gemma 4 | United States (Cerebras) |
Citations are grounded in Lawerly’s own knowledge graph rather than the model’s memory: the drafting and chat text is generated by a third-party model, but every citation in it is checked against Lawerly’s database, and anything that cannot be confirmed is flagged in the text rather than passed off as verified. Overruled and distinguished precedents are flagged with the judgment that did it.
Have questions or concerns about the models we use or how your data is handled? Contact us at support@startuplab24.com.