Applications · Client work / Case study
IRLI: bringing case data into one working system
A confidential backend management tool for the Immigration Reform Law Institute, combining case-data consolidation with a retrieval-augmented generation pipeline.
Contribution
Backend development, case-data consolidation, and RAG integration
NDA
Confidential client backend
Confidential project / abstract workflow
Project context
Client backend development for IRLI. The organization is named with permission; the application remains under NDA. This overview describes the project at a high level without exposing case records, internal screens, source code, or deployment details.
Confidential application under NDA. The external link identifies the organization; it is not a demo or a website developed as part of this project.
High-level project workflow
- 01Consolidate case information
- 02Retrieve relevant context
- 03Use context in generation
- 04Support case-management work
01
The brief: connect information to the work it supports
The Immigration Reform Law Institute needed a backend tool for managing and consolidating case-related information. McKay's contribution was the application backend and a RAG pipeline, bringing data consolidation and retrieval-assisted generation into the same project. The focus was internal operational software, rather than a public-facing website.
02
The data problem: collection is only the starting point
Putting information in one place and making it useful are related but different tasks. In case-management work, the important question is not simply whether a record exists, but whether relevant information can be brought into the context of the task at hand. Consolidation was the foundation of this project: connecting case data to a backend workflow instead of treating each source as an isolated destination.
03
The RAG layer: retrieval before generation
Retrieval-augmented generation combines retrieved information with a generative model, so generation can draw on supplied context rather than model parameters alone. That is the general pattern behind the RAG component in this project. The specific models, data sources, retrieval configuration, and internal interfaces are not disclosed here. The reference below explains the technique, not the client's private implementation.
04
The design consideration: useful context, not automatic authority
For this class of application, relevance and reliability are separate questions. Retrieving a passage does not by itself establish that a generated response is complete or correct. The engineering problem is therefore broader than connecting a model: the relationship between source information, retrieved context, and generated output matters. This is a design consideration, not a claim that the system replaces professional judgment or delivers a measured level of accuracy.
05
The result: substantive backend work, presented with boundaries
The delivered work combined a case-management backend, data consolidation, and a RAG pipeline for a real client. Its portfolio value is the integration of those responsibilities into one application. Because the project is confidential, this case study uses a purpose-made abstract illustration rather than reconstructing the interface or publishing sample client records. No performance figures or operational results are disclosed.
Delivered outcomes
- A backend management tool built for the client's case-related work.
- Case information consolidated into a shared application context.
- A retrieval-augmented generation pipeline incorporated into the backend.
More in applications
Have a similar problem to solve?
Discuss your project