Martin Fowler

We recently completed a short seven-day engagement to help a client develop an AI Concierge proof of concept (POC). The AI Concierge provides an interactive, voice-based user experience to assist with common residential service requests. It leverages AWS services (Transcribe, Bedrock and Polly) to convert human speech into text, process this input through an LLM, and finally transform the generated text response back into speech.

In this article, we’ll delve into the project’s technical architecture, the challenges we encountered, and the practices that helped us iteratively and rapidly build an LLM-based AI Concierge.

What were we building?

The POC is an AI Concierge designed to handle common residential service requests such as deliveries, maintenance visits, and any unauthorised inquiries. The high-level design of the POC includes all the components and services needed to create a web-based interface for demonstration purposes, transcribe users’ spoken input (speech to text), obtain

To read the full article click on the 'post' link at the top.