Abdullah OmerOpen the canvas

AI trust · LegalTech · Shipped

Malakah Citations

Making a legal AI show its sources, down to the article.

Malakah chat answering a legal question with the contract and cited source side by side

Lawyers wouldn’t act on an AI answer they couldn’t check. I designed the system that lets every claim in Malakah’s answers open the exact article of Saudi law it came from.

My role
Product Designer at Stixor, for Malakah. Legal chat, legislation CMS and evaluation admin.
Duration
2024 – 2026
Team
Lawyers, plus the internal content and AI team as users.
Stack
12 interviews, Pattern comparison, Arabic (RTL) + English (LTR), Internal tools
  • 10 of 12 would re-check an unsourced answer
  • 1,000+ legal professionals

Problem

An answer you can’t check is a research task.

A lawyer is accountable for every piece of advice they give. Saudi law also changes, so “the law says” is only useful if you know which version said it.

The reframe: not “make the answer more accurate”, but “make every claim cheap to check”.

Chat answer that mentions article numbers without linking to them
The starting point: article numbers, no links

Approach

A citation is only as good as the three layers under it.

A source link only works if the law is stored in pieces small enough to point at, and if retrieval reliably finds the right piece.

  • Structure the law. A legislation CMS for the content team: chapters, parts, articles, annexes and amendments.
  • Measure retrieval. An evaluation tool for the AI team: did the right articles come back, and in what order?
  • Show the source. Legal chat for lawyers: each claim links to its article, which opens beside the answer.

Solution

Four ways to show a source.

I judged every option by one question: how much work is left for the lawyer between reading a claim and trusting it?

  • A link on every claim won. It opens the exact article beside the answer, with the cited text highlighted.
  • Then, the version. A correct article in an outdated version is still wrong advice.
Each point ends with a View Law and Details link, with the law panel open beside it
Claim-level citations

Solution · Content

Making the law addressable.

You can only link to an article if the system knows where each article starts and ends. So the content team rebuilds each law as a tree before it’s published.

  • Source priority. Tell “the law says” apart from “a guideline suggests”.
  • A translation check next to Publish. An unchecked translation is the wrong text.
Legislation CMS preview: a nested tree of chapters, parts and articles
Legislation CMS

Solution · Quality

Measuring whether the right article comes back.

A wrong article, shown with confidence, is worse than no citation. Teams upload test sets and compare runs by precision, recall, F1 and nDCG.

The citation a lawyer sees is the output of retrieval, so this was the most direct way to improve what they’d trust.

Evaluation admin page with a results table of F1, recall, precision and nDCG
Evaluation tool

Results

The claim-to-source pattern shipped.

The source opens as a third panel next to the chat and the contract, so a lawyer can check a claim while drafting without switching tools. Malakah serves 1,000+ legal professionals.

Malakah workspace: chat answer, contract and cited source side by side
Chat, contract and source, side by side

Learnings

Trust is a path, not a badge.

Next, I’d test citation density on long answers, measured by time to verify.

  • The visible pattern depends on invisible structure. The CMS and the evaluation tool are what made the citation link true.
  • Design for the people behind the AI too. The content and AI teams were users of this system as much as the lawyers.

See Malakah Citations on the canvasRead the full case studyView the presentation (PDF)