Real engagements, two of them my own products, plus concept demonstrations of what I'd like to build next.
Recreated CRM screen for a real-estate team: a lead list, an open lead drawer with property details, tasks, a call log and a scheduled meeting.
One Hebrew CRM built around the team, with calendar, WhatsApp, phone and AI assistants connected to it.
Illustration: a finished run arrives as raw Garmin data, code scores it (scoring, de-duplication, training load, patterns), the AI explains it in plain language, and Maya the runner decides what to do with the advice.
A running coach built with a partner. Code does the math; AI explains it.
Illustration: an exercise submissions queue — pull requests come in, tests and drafted feedback go out, and a submission whose test timed out is flagged for the lecturer, who decides the grade.
Pull requests in, tests and drafted feedback out, the lecturer decides the grade.
Illustration: a small job is posted, a verified helper takes it, payment is secured before work starts and released on completion, an attempt to share a phone number outside the app is hidden, and the job owner leaves a fair review.
An app where strangers get small local jobs done and the money moves safely.
Proposals and demonstrations, not delivered client work. They show how a capability would work in practice, with fictional data, so we can discuss whether it fits your business.
Concept: a morning report that surfaces exceptions by owner: stuck leads, overdue tasks and a failed integration, sent to Yoav at 07:30.
A daily summary that tells a manager what needs attention, not everything that happened.
Concept: a guided WhatsApp conversation in which an assistant qualifies a new lead, understands a voice note, writes the answers to the CRM and hands over to an agent.
An assistant qualifies a new lead on WhatsApp, then hands over to a person.
