Methodology
How LeaseLens builds your report
LeaseLens reads the documents, extracts key facts, applies a fixed set of risk checks, and then runs a staged AI drafting workflow. The report is designed to show what appears in the supplied pack, what is missing, and what still needs professional verification.
The current methodology is designed for England & Wales leasehold packs. It uses a rule library for the main risk categories so important findings are not driven only by open-ended AI responses or unsupported summary language.
How the report is put together
- Ingestion and file metadata capture
- PDF text extraction with OCR fallback for low-density files
- Document classification into core pack categories
- Extraction of charges, reserve figures, insurance details, and risk indicators
- Rule-based flagging and confidence handling
- AI pack triage, financial analysis, issue prioritisation, report drafting, and QA review
- Final QA pass to reduce overclaiming and highlight contradictions
Current AI step contract
- Each AI stage has a named prompt and a required JSON output format
- The report is built from structured step outputs rather than free-form AI text alone
- Every medium or high issue should carry source context or be framed as a verification prompt
- Missing documents reduce confidence rather than being treated as harmless
Guardrails
- No overclaiming or unsupported conclusions
- No “buy / don't buy” recommendations
- No clearance to exchange, proceed, renegotiate, or walk away
- Medium/high findings should carry source context where available
- Contradictions are converted into verification prompts
- Missing documents reduce confidence instead of being ignored
How to use the output
LeaseLens is a document-review aid. Treat the output as a structured starting point for adviser review and follow-up enquiries, not as legal advice, lender approval, valuation advice, or transaction clearance.
