Analytics

The Answering Machine is a proof-of-concept system that I built using pre-LLM natural language processing (NLP), specifically NLTK, to produce answers to questions asked about data in plain English.

Looking back, this project was a great insight into what LLMs immediately allowed that was incredibly difficult before. This project was several months of work that the openAI sdk would probably have allowed in a few weeks - and that few weeks would have been mostly frontend design and a bit of prompting.

Try it here: http://voicequery-dev.s3-website-us-west-2.amazonaws.com/ Github: https://github.com/hockenmaier/voicequery

The system uses natural language processing to produce answers to questions asked about data in plain English.

Editor’s note from 2025:

First Ten is no longer available after Google discontinued custom voice apps in 2023, but I’m leaving this article here as a record. Now, similar apps can be built in hours or minutes using modern AI models. First Ten used a now outdated intent routing system to fetch information from a serverless architecture about the Bill of Rights. Interestingly, my infrastructure for this app is still up and running behind the scenes because it’s truly serverless and costs nothing to host.

First Ten is an educational app containing information about the U.S. Bill of Rights, accessible on Google devices and smart speakers.