Litigation Analyzer Agent · Use case
How can we use an AI agent to summarise court filings for the case team on our own infrastructure?
A litigation analyser agent reads court filings and case material, summarises each document, builds a timeline and points out patterns and risks across them, citing the passage behind each point. The case team decides what they mean for the case. The agent runs on your own infrastructure, so case material is not sent to a public AI service.
Filings arrive.
Each one is long.
- ✗ 01Filings and exhibits arrive in volume, and the team has to read all of them to see how they fit together.
- ✗ 02Case material is confidential and privileged.
Where it stops for a person
Always: the case team decides strategy.Always. The agent predicts no outcome and gives no advice on strategy. The case team decides.
It summarises and cites.
The case team decides.
Step · 01
Filings and case material are connected or uploaded.
Step · 02
The agent summarises each document.
Step · 03
It builds a timeline of events and cites the source of each.
Step · 04
It points out patterns, inconsistencies and risks across the documents.
Step · 05
The case team reads the sources and decides.
Reads from · connectors
File Upload
SharePoint
Box
Filings arrive through File Upload or are read from SharePoint or Box, and are turned into text with Markitdown.
Acts through · MCP servers
Markitdown
Nothing. It summarises and cites. It files nothing with a court.
What you set up
- Connect or upload the filings and case material.
- Describe the issues in the case.
- Test on a closed matter.
Where it runs
The agent, its knowledge store and the model run on infrastructure you own or control. You choose the model and serve it yourself, so questions, documents and answers are not sent to a public AI service.
How you get it today
This page is labelled Use case: the agent is built in Katonic Studio. You describe the job, connect what is named above, add test questions and release the agent once it passes them. When the Catalog holds a tested template for this job, this page will carry the Template label and show how to take it.
Does the agent predict the outcome of a case?
No. It summarises and points out patterns. The case team judges.
Can we check a point it makes?
Yes. Each point cites the document and passage behind it.
Where is case material processed?
On your own infrastructure, with a model you serve. Nothing is sent to a public AI service.