Mikhail Semenov
RU
Open to new projects Remote · GMT+5 · relocation

Driving product through thoughtful AI adoption · Prof-IT

AI Product Manager.

I lead B2B products at Prof-IT since 2022, now voice AI agents. Alongside that I ship pet projects with AI agents, validating hypotheses in days, not sprints.
Open to AI Product Manager roles where the product grows through thoughtful AI adoption.

Message me on Telegram

Currently

What I do now

Role
Product Manager at Prof-IT (zvonobot, effebot, p1sms), since early 2022
Focus
Leading product development for the new product: voice AI agents for B2B
2026 signal
500,000+ minutes of new-customer conversations via voice AI agents
GitHub · last year 0 contributions github.com/RebSem

Hover a cell to see the exact date and number of contributions.

How I ship · Claude Code & Codex

I run a team of AI agents.

Spec, constraints, and review stay with me. Implementation goes to Claude Code and Codex. That is how a side project gets from idea to release in days, and how this site maintains itself: every change is an agent-written PR that I review.

  1. Spec

    I frame the problem, the constraints, and what “done” means.

  2. Agents build

    Claude Code and Codex write the code, run the checks, and open a pull request.

  3. Review

    I read every diff myself and merge only what I can defend.

  4. Production

    A merged PR deploys straight to production.

Projects

Selected work

Two tiers: products I lead at Prof-IT, and personal pet projects built in days. They show the speed I take an idea to release.

01 · Day job

Products I lead

Here I own product logic, metrics, and end-to-end delivery.

Flagship · 2026 Live in production

Voice AI-agent platform for B2B (Prof-IT)

I run it end-to-end · product, UX, engineering

  • Multi-tenant SaaS
  • Voice + LLM orchestration
  • B2B telephony

A new Prof-IT product I launched in 2026 and run end-to-end: product, UX, and engineering. A multi-tenant SaaS console built on top of telephony infrastructure: clients assemble and publish voice AI agents for outbound use cases like sales, onboarding, reactivation, and surveys.

What I built and keep in production

  • Client console: agent builder, prompt flows, campaigns, call history, and billing, all under one role.
  • Billing with a balance hold on campaign start, so clients never go negative and spend stays predictable.
  • Reliable call pipeline: a background poller reconciles statuses every 60 seconds so no call gets stuck and every minute is billed.
  • React 19
  • TypeScript
  • Vite
  • Flask
  • PostgreSQL
  • Redis
  • LLM orchestration
Read the full case

cursivo

Live

A personal product I lead from product logic to release. A CRM for car rental businesses covering the full cycle: fleet and utilization, bookings and contracts, customer base. AI handles the busywork: it reads and verifies client documents, scores deal risk, and suggests the next step to the manager. The goal: let a small rental operate like a chain, without growing headcount.

Type AI-powered car rental CRM

  • Next.js
  • TypeScript
  • Prisma
  • PostgreSQL
  • OpenAI
  • Linear

Read case Open cursivo.xyz

obrabot

Internal Prof-IT product

Internal Prof-IT product: a personal cabinet with analytics and dashboards for voice AI agents. AI segments calls and surfaces what needs human attention. I run the product.

Type Internal voice AI analytics dashboard at Prof-IT

  • Next.js
  • TypeScript
  • Prisma
  • PostgreSQL
  • OpenAI API
  • Google Sheets API

Read case

02 · Speed and a shared language with engineers

I take any idea to release in days

Not hobbies but proof: each project was personally built with AI coding agents (Claude Code, Codex) in 1–7 days from idea to a working release. That is how I validate hypotheses fast and speak the same language as engineers. Each one notes what it proves.

~2 days

bazabot

Telegram bot for cleaning client bases

Proves AI/ops in a real workflow: kills the manual base cleanup before call campaigns and speeds up data prep for the team.

Python · Telegram Bot API · CSV/XLSX · p1sms API

3 days

Zodial

Personalized PDF report platform

Proves A full product in 3 days: payments, delivery, and analytics end-to-end. Proof I can take a hypothesis to a working paid product.

Next.js · TypeScript · Prisma · SQLite · YooKassa · Resend

1 evening

tubedrop

macOS wrapper over a YouTube converter

Proves Speed and a shared language with engineers: a working open-source tool for my own pain point, built and shipped in an evening.

Python · yt-dlp · ffmpeg · macOS

github →
~7 days

Slopiq

iOS app for ski and snowboard sessions

Proves Product taste on a new platform: a native iOS app with an AI assistant, from zero to a working build in a week.

SwiftUI · iOS · Weather · AI Assistant

~2 days

portfo

This site

Proves This very site: the only public repo here, maintained agent-native through PRs. Proof of the approach in action.

Astro 5 · TypeScript · MDX · GitHub Actions

github →