What web design looks like in the real world.

Junior lawyers were spending 8–12 hours per matter manually reading judgments to extract parties, statutes, and precedents. Existing general-purpose LLMs confidently returned wrong citations, which made enterprise clients nervous and stalled paid pilots. The founders needed a system that could cite every answer back to a real paragraph in the source document.

1. Automate structured extraction of parties, statutes, and holdings from Indian judgments.
2. Guarantee every AI answer resolves to a real paragraph in the source PDF.
3. Reach 90%+ citation accuracy in blind evaluation before pilot handover.
4. Ship a reviewer console so in-house lawyers can correct extractions in-flow.

1. Weeks 1–2 · Discovery + evaluation set

   Sat with senior counsel to define what a correct citation looks like; built a 500-judgment blind evaluation set before writing pipeline code.

2. Weeks 3–6 · Ingestion pipeline

   Parsed judgment PDFs with GROBID, structured into parties, statutes, holdings, and paragraphs; loaded into Postgres with pgvector.

3. Weeks 7–10 · Retrieval + answer engine

   Hybrid BM25 + vector retrieval, followed by a citation-verification step that rejects any claim not anchored to a real paragraph.

4. Weeks 11–13 · Reviewer console

   Built the lawyer-in-the-loop UI: accept, reject, or correct extractions; corrections feed back into evaluation.

5. Weeks 14–16 · Pilot hardening

   Ran the blind evaluation with two enterprise buyers, tuned thresholds, and shipped the pilot handover doc.

• OCR quality on older scanned judgments was poor; a pre-clean step and a per-court PDF quality profile were required.
• Statute references use inconsistent shorthand across courts, so a normalisation layer had to be maintained by hand initially.
• Enterprise legal teams wanted a full audit log of every AI decision — added append-only citation logging late in the build.

• Judgment ingestion pipeline. PDFs are parsed, structured into parties, statutes, holdings, and paragraphs, and indexed with hybrid BM25 + vector search for fast retrieval.
• Citation-verified answer engine. Every AI-generated claim must anchor to a source paragraph before it is shown to the user — no hallucinated precedents.
• Lawyer-in-the-loop feedback loop. A reviewer console lets in-house lawyers accept, reject, or correct extractions, with corrections feeding back into model improvement.

Not published. This engagement is under NDA. We can arrange a reference call with the client at proposal stage — we do not publish paraphrased or synthesized quotes.

• In regulated verticals, an auditable citation chain sells more than any raw accuracy number.
• The evaluation set is the product — write it first, revisit it every fortnight.
• Lawyer-in-the-loop is not a fallback; it is the reason the system is trustworthy enough to sell.