Missed calls, missed revenue: the local-first phone assistant I'm building
Previous posts in this series covered the infrastructure: running three AI models sequentially on one server and why I run speech-to-text locally instead of calling a cloud API . This one is about the business problem I'm building toward. The problem I run a solo consulting practice. Client communication arrives over three channels: phone calls (including voicemails I check hours later),…
This piece explores the business challenge of managing client communication across multiple channels - phone calls, messaging apps, and email. It details how the author, who runs a solo consulting practice, found manual tracking of commitments, follow-ups, and open questions to be time-consuming and prone to missed opportunities, especially with phone calls which are often ignored.
The author highlights that small businesses lose 40-60% of potential leads due to missed calls. Existing tools only handle one communication channel at a time, leaving no integrated solution to tackle the problem. The author is building a system that generates a daily summary report, including missed contacts, commitments, scheduling mentions and open questions.
The infrastructure for local call transcription, semantic search embeddings, and image processing is already in place, but the author is still designing the output format and developing an entity resolution method to link communications across channels despite challenges like multiple phone numbers, email aliases, and name variations. The next step is to have the report generator produce a usable output format.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
