# rhdh AI demo

## abstract

## problem statement

When adopting internal developer portals and implementing self-service and automation in an erterprise, the number of options can feel overwhelming for end-users. They need to be able to efficienlty find resources that are relevant to what they are doing.

## proposed solution

To address this, an AI powered recommendation engine is proposed, that takes the user's team membership, role, and behaviour into account.

### overview

Generic analytics plugin for backstage...

Ingestion...

Self-contained system with local model...

[diagram]

### data capture

Custom backstage plugin that records events and associated metadata

### data generation

Selinium IDE to record a library of user actions combined

### data ingestion and transformation

Microservice that serves as the event sink and transforms & writes the event to redis

### processing

OpenShift AI

### display recommendations

Backstage frontend plugin... you might also be interested in x...

### reinforcement

Backstage frontend plugin (thumbs up/down + comments)