# An AI legal assistant that refuses to cite law it can't verify

> Source: <https://dev.to/mrpkk/an-ai-legal-assistant-that-refuses-to-cite-law-it-cant-verify-2cje>
> Published: 2026-10-19 14:41:58+00:00

We built AILegal — a legal assistant for people who can't afford a lawyer — around a single rule: **never state a legal fact we haven't verified against the official source.** This post is about the engineering that makes the rule enforceable, and about what still doesn't work.

Early versions used the usual approach: a careful prompt, a corpus in the context window, "answer only from these sources". It failed in ways that are easy to miss if you don't check:

Neither answer *looked* wrong. That's the dangerous part: a plausible citation is worse than an obvious refusal.

Every norm in the corpus is a record, not a paragraph in a prompt:

```
Norm(
    id="us-cares-4024c",
    code="15 U.S.C. § 9058(c)",
    jurisdiction="us",
    summary="...",              # plain-language, human-reviewed
    source_url="https://...",   # official text
    source_hash="...",          # hash of the checked version
    checked_at="2026-10-18",
    verified=True,              # human review passed
)
```

The corpus currently has **53 norms**: 11 Russian, 26 US, 9 UK, 7 Canadian.

A scheduled job runs **every three days**. It fetches every official source, requires that the numbers and terms from our summary actually appear in the fetched text, and stores a hash of the version it checked. If the hash changes, the norm is flagged for a human re-check.

`verified` is deliberately *not* set by the machine. The script proves "the text says what we claim"; a human decides "this norm is usable for a deadline". Those are different claims, and conflating them is how legal AI ends up inventing law.

At answer time the rule is boring on purpose: if a norm isn't verified, the assistant does not name deadlines or article numbers derived from it. It says what it can't confirm and asks for the missing fact.

We also measured a "soft" classifier that catches paraphrases by word-stem similarity. The exact stage resolved 12 of 31 test paraphrases; the soft stage added hints for 14 more, of which 8 were correct — roughly 57% precision. That is nowhere near enough to answer a legal question: every other hint would be about a different problem. So the soft stage only asks a clarifying question. It never produces a verdict.

Synonyms. "вычисли" vs "посчитай", "списали" vs "удержали" — different words, same meaning. Without a source of synonymy, similarity scoring can't tell them apart. We tried local embedding models (`nomic-embed-text`, `qwen3-embedding`) on a canonical paraphrase; the results were top-3/top-4 with cosine gaps of 0.001–0.03 — noise. The real fix is not a better model but a semantic representation of the norms themselves: everyday search phrasings, written and reviewed per norm. That's legal work, not a prompt tweak.

If you ask a legal assistant "what's the deadline?" and it answers confidently, you can't tell a verified answer from a hallucinated one. The gate makes the failure mode boring: "I can't confirm this from the official text." Boring is what you want when the cost of a wrong answer is a missed court deadline.

Try to break it: [ailegal.legal](https://ailegal.legal) — take any norm, compare it with the source it links to, and try to make the assistant state something the source doesn't.

*Not legal advice. Legal content is RU/EN; the interface speaks more languages.*