The challenge
The client wanted to assess whether large language models could support the analysis of its records and documents.
Built a prototype using large language models on Azure to analyse records for a justice organisation.
Ref: IMSFT104493
Video story · 1:01
The challenge
The client wanted to assess whether large language models could support the analysis of its records and documents.
The approach
Kumulus integrated AI components into an application on Microsoft Azure, covering architecture, APIs, Kubernetes hosting, machine learning components and operational controls.
The outcome
Reviewers now have a consistent, traceable input for the classification process. Preliminary review of RPG books was automated, producing a structured JSON record per document with its unique ID, title, author, publication year, classification status and initial analysis.
Could this work for your organisation?
The AI Audit shows where data and AI will deliver measurable value for you first.