Making Justice Seamless

with AI

Product Category

Legal-tech, Social-Impact, AI product


Role

Responsible for user interviews and led end-to-end product design

Responsible for user interviews and led end-to-end product design

Client & Stakeholders

Agami


glimpse of a court hearing

A tense courtroom. A lawyer, mid-argument, cites a specific section of a law to support their client. The judge, however, doesn't meet their gaze throughout the hearing.

Instead, both their heads are buried in paperwork.

The Problem

Buried in a paper chase

In the current system, Lawyers and advocates cite applicable Acts and Laws to support their arguments. Judges then depend on the court clerks to find all documents related to the cited acts and laws, which can take weeks or, in some cases, even months.

How might we help judges to break free from this manual chase and

deliver timely judgments?

enters JIVA

Before JIVA

6 weeks

Before JIVA

6 weeks

With JIVA

6 sec

With JIVA

6 sec

Research & discovery

We immersed deep into the judiciary

To get a deeper understanding of the problem and identify scenarios where a streamlined system of accessing documents can significantly improve court hearings, with interviews and recorded court cases.

SolutioN

01.

One-click access to every law document

Search

Cmd

+

J

01.

One-click access to every law document

Search

Cmd

+

J

01.

One-click access to every law document

Search

Cmd

+

J

We designed JIVA to leverage AI more efficiently and give judges one-click access to legal documents, including amendments and case laws, in real-time.

AI understands the context

of the query to fetch the most relevant documents, based on natural language input and organises them accordingly.

Follow-up queries open as an overlay,

allowing users to focus on the new question without losing the context of the previous query.

02.

Calibrating trust with design

Is AI in the courtroom reliable? A key challenge was to ensure that judges can clearly differentiate between extracted legal information and AI-generated insights.

02.

Calibrating trust with design

Is AI in the courtroom reliable? A key challenge was to ensure that judges can clearly differentiate between extracted legal information and AI-generated insights.

02.

Calibrating trust with design

Is AI in the courtroom reliable? A key challenge was to ensure that judges can clearly differentiate between extracted legal information and AI-generated insights.

To build trust, the generated content appears visually different, creating a clear distinction from the extracted content. This transparency ensures judges understand the source and weight they can give to each piece of information.

Extracted by AI

Leveraged familiarity to build comfort by keeping the extracted content visually similar to printed court documents.

Generated by AI

appears in the form of chat messages in the font Urbanist to keep it visually distinct from extracted documents.

03.

Going one step further

When laws undergo amendments, their older versions remain applicable for cases filed before the amendments. Therefore, when lawyers cite laws and specific sections relevant to their cases, assessing which version of a law applies in a particular scenario is also important. Figuring this out manually through physical documents is cumbersome and time-consuming.

03.

Going one step further

When laws undergo amendments, their older versions remain applicable for cases filed before the amendments. Therefore, when lawyers cite laws and specific sections relevant to their cases, assessing which version of a law applies in a particular scenario is also important. Figuring this out manually through physical documents is cumbersome and time-consuming.

03.

Going one step further

When laws undergo amendments, their older versions remain applicable for cases filed before the amendments. Therefore, when lawyers cite laws and specific sections relevant to their cases, assessing which version of a law applies in a particular scenario is also important. Figuring this out manually through physical documents is cumbersome and time-consuming.

For efficiency and accuracy, we designed JIVA to :

help judges track citations across related documents efficiently

seamlessly navigate & understand all referenced sections of documents

automatically suggest relevant documents not initially cited by lawyers

The side panel makes it easier to navigate through multiple documents

To avoid distractions, the panel only appears upon clicking an annotation

JIVA’s AI analyses versions of every document and annotates all changes

The Blue annotations mark substitutions, the Reds mark omissions, and the Yellows highlight insertions.