Know someone who needs a haircut? 🙋 Send them to TrimsByTracy.com, where they will find the salon of Tracy Turnblad, a solo hairstylist in Baltimore who needed an expert to tame her booking flow the way she tames manes.

I had a lot of fun working on this Proof of Concept, from ideating design system inspiration to working through the nooks and crannies of a hairstylist's booking flow, to figuring out how to succinctly communicate the value added in an overview video. I also continue to learn each time I build something new with Lovable. This time I was focused on reducing the amount of time spent testing, which is what my "Process" video is about. I hope you'll take a look at that since I personally think what I shared there is very valuable and should be standard to all builders' workflow and possibly considered for productization by Lovable. Regardless, I hope you enjoy taking a look around TrimsByTracy! All built with care in Lovable. - Drake https://trimsbytracy.com/ https://trims-by-tracy.lovable.app

The delight of booking, Mr. Pinky made me smile.

On a phone call, silence is the bug.

A text chatbot can take three seconds to reply and nobody minds. A voice agent can't. Leave a caller in silence for a beat too long and they say "hello?", start talking over it, or hang up.

That one fact shaped everything we built on Talk-Lee, an AI voice agent that answers business calls for healthcare, real estate and finance teams. Scheduling, support, lead qualification, around the clock.

The goal was a reply in under 500ms. You don't get there with a faster model. You get there by making sure nothing waits for anything else.

→ Speech to text streams while the caller is still talking

→ An LLM and intent layer keeps track of what they actually want

→ Text to speech streams back, so the agent starts talking before the whole answer is ready

→ An orchestrator decides in real time whether to answer, book or hand off to a person

Then it has to do something useful. It books into Calendly, logs the lead in HubSpot, and passes the hard calls to a human with the context already attached.

Where it landed. Under 500ms responses, 1,000+ concurrent calls, 30+ languages, GDPR and TCPA compliant.

Third project in a row with the same lesson. The model is the easy part. The plumbing around it decides whether anyone keeps using it.