Skip to main content
Trust & Authority

Trust before intelligence

Anyone can generate legal text. What makes it trustworthy is provenance: every clause, template and figure on Lekha is sourced to authoritative law, explained in plain language, and scored on how well it can be verified. This page publishes exactly how that works — including where we fall short.

69
authoritative sources in the registry
84%
of clauses link to a source in our verified registry
45
Acts mapped in the knowledge graph
0
expert-reviewed templates (of 171)

How the Trust Score is calculated

Every Trust Score (0–100, graded A–D) is a transparent weighted sum of five factors — deterministic and reproducible, so the same content always scores the same and every figure can be inspected.

25%
Citation completeness
Does the content cite statute, and do those citations resolve to known authoritative sources?
20%
Source authority
How authoritative the cited sources are — official statute and regulators rank highest, secondary commentary lowest.
20%
Explainability
Whether a substantive plain-language meaning and purpose are present.
20%
Editorial review
Editorial-governance state: draft, curated, reviewed, or verified by a named human.
15%
Source freshness
How recently the underlying sources were last verified.

What the Trust Score does not mean

It measures how well-sourced, explained and reviewed content is — not whether a clause is legally valid, enforceable, or right for your situation. A high score means well-documented, not legally guaranteed. Lekha is educational and is not a substitute for advice from a qualified advocate.

Citation-backed AI answers

Every substantive AI answer on Lekha carries inline [n] citations resolved against the source registry below — inserted by a deterministic engine, not by the model citing itself, so a footnote can only ever point at an Act the answer actually named. Below is a real Vidhi answer, annotated at render time by the same engine the live chat uses:

Q: Which Indian law makes a non-compete clause after employment unenforceable, and does the DPDP Act cover employee data?
The Indian law that generally makes non-compete clauses after employment unenforceable is the Indian Contract Act, 1872 [1]. According to this Act, such clauses are often seen as restraining trade and are therefore not enforceable in most circumstances. As for the Digital Personal Data Protection Act, 2023 [2] (DPDP Act), it does cover employee data. The Act provides guidelines on how personal data, including that of employees, should be collected, processed, and stored, ensuring individuals' rights to privacy and data protection.
Moderately grounded2 authoritative sources cited. AI-generated — verify before relying.
Sources
🔒 Fabrication-proof by design

Citations are extracted from the answer's own text against the verified registry — never generated by the model. No section number is ever invented; naming the Act is the bar, and a wrong citation is treated as worse than none.

🧢 AI answers are capped, honestly

An AI answer can never grade A: its editorial factor is hard-capped because no chat reply is human-reviewed. The badge says so on every answer — high sourcing does not mean it is correct.

📡 Regulatory monitoring

A daily automated watch detects Indian regulatory changes from verified live government sources, maps them to affected templates, and notifies the users who generated them — see What changed.

Try it yourself: ask Vidhi any India-law question and expand the evidence behind its answer.

Source of truth

The authorities Lekha maps content to. Pointers go to the official repository of Indian law (India Code) or the relevant regulator — we don't fabricate citations. Explore how each connects to clauses and templates in the knowledge graph.

Gaps are reported honestly: where content cites an authority not yet in this registry, its Trust Score reflects the gap rather than hiding it.