SAEPUL MALIKInspigo AI: Real-Time RAG for Personalized Learning
A streaming chatbot experience powered by OpenAI/Bedrock and a RAG pipeline, grounded in the platform’s own learning content.
Problem
Personalized learning benefits from conversational, context-aware assistance rather than static content lookup — but a foundation model answering purely from its general training data isn't grounded in what the platform actually teaches.
Architecture
Inspigo AI integrates Foundation Models (OpenAI, AWS Bedrock) behind a Retrieval-Augmented Generation pipeline. Instead of relying on the model's general knowledge alone, responses are grounded in retrieved content from the platform itself before generation happens.
Execution
The frontend work centered on the chat experience: handling real-time streaming responses token by token, and managing the perceived latency between a user's question and the first visible piece of an answer — the gap between "the model is thinking" and "the model is already answering."
Impact
The result reads less like a search box and more like a conversation — answers stream in immediately and stay grounded in Inspigo's own learning content rather than drifting into generic, ungrounded responses.