Welcome to my blog domain where I share personal stories about things I've learned, projects I'm hacking on and just general findings. I also write for other publications.
This post is the second in a three-part series on building an AI call assistant, detailing how to build the "Intelligence layer" that processes transcripts, maintains conversation context, and generates intelligent responses by integrating pluggable LLM providers with a knowledge base and session orchestration.
This post is the one off a three-part series on building an AI call assistant, explaining how to create the "listening layer" that streams live phone audio through Twilio and converts it to real-time transcripts using pluggable speech-to-text services.
AI isn't language-neutral. Token Inequality causes higher costs and latency for non-English users. Learn how tokenizer bias works and how to mitigate it.
