ByePhone- An AI assistant to automate tedious phone calls

Name: ByePhone- An AI assistant to automate tedious phone calls
Availability: InStock
Author: gitpullups

by gitpullups·Feb 22, 2026·5 points·3 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemSlick

Automates annoying calls with natural voice, but GPT-4o chains cost more than just calling yourself.

Strengths

•Phone number scraping + dynamic form generation from LLM handles diverse businesses without templates
•Natural voice and hold-menu navigation mean genuinely hands-off calls, not just voice recording
•Honest cost breakdown (using Sonnet to cut expenses) shows engineering maturity, not handwaving

Weaknesses

•Unit economics unclear—Twilio + LLM chains per-call will exceed human time for many users
•Competes with existing call automation (Aircall, Five9, custom Twilio agents) without clear moat

Post Description

I have a bit of phone anxiety, and have a ton of dread around making phone calls to restaurants, banks, doctors, and so on and on.

I thought: AI could do this with a web form turned into a prompt.

Stack started out simple -> using 11labs for voice + claude + twillio, but it actually got rather complex (even though I tried vibe coding most).

First off, finding the phone numbers quickly is hard. This is done by scraping the web with some basic duckduckgo search and structure with openai calls.

Second, collecting the right information. I’m still struggling a bit with this but the architecture is that: A) user puts in call objective and business name B) if keywords are detected spin up one of the default form categories C) if not, get structured json from gpt-4o-mini and turn into react form

The cost of making a single call spun out of control, but luckily sonnet can handle a lot of the calls and I’m ok paying for twillio.

Ended up taking months to build my week-long project because of course.

It’s still WIP so feel free to email me: [email protected] with any ideas or issues u ran into. \