Skip to content

LobSmash

Recreational padel runs on chaos: late feedback, misaligned partners, and plans that die in group chat.

Core trick

Receives WhatsApp messages and photos through Kapso webhooks, then returns Gemini-generated coaching, including image-based feedback.

Tags

Description

Recreational padel runs on chaos: late feedback, misaligned partners, and plans that die in group chat. LobSmash Coach is a WhatsApp-native coach that gives timely, structured guidance (including image feedback), helps players pair up, and steers duo pre/post-match sessions—wired through Vercel, Next.js + Kapso webhooks and Gemini, with Playtomic links to book courts. It’s aimed at the everyday problem of access and alignment: cheaper than a human coach, closer than another app nobody opens.
trenchsheikh/lobsmash-whatsapp★ 00 forksTypeScriptCreated Mar 21, 2026 · last push Mar 26, 2026

README excerpt

# LobSmash Coach

**Your padel coach lives in WhatsApp.** Built for the [Vercel × Google DeepMind “Zero to Agent”](https://community.vercel.com/) hackathon series — coaching, memory, and duo play in the chat app you already use.

![Next.js](https://img.shields.io/badge/Next.js-15.2-black?style=flat&logo=next.js)
![React](https://img.shields.io/badge/React-19-61DAFB?style=flat&logo=react)
![Gemini](https://img.shields.io/badge/Gemini-3%20Flash-4285F4?style=flat&logo=google)
![WhatsApp](https://img.shields.io/badge/WhatsApp-Wassist-25D366?style=flat&logo=whatsapp)
![Postgres](https://img.shields.io/badge/Postgres-Supabase-3FCF8E?style=flat&logo=postgresql)

## Why this exists

Padel is fast, technical, and social. Generic AI chat feels cold; a coach in **WhatsApp** meets players where they plan matches, share clips, and talk strategy. LobSmash Coach uses **Gemini** for multimodal reasoning (text + images/video) and **structured coaching** so every reply is actionable — not a wall of text.

## What you get

- **WhatsApp-native coach** — Inbound messages via [Wassist](https://wassist.app) **Bring Your Own Agent** webhooks; your server returns `{ "type": "message", "content": "…" }` with the coach reply (extra-long answers may continue via `reply_callback`). See [docs](https://docs.wassist.app/concepts/bring-your-own-agent).
- **Chat-first coaching** — Replies match intent (casual, booking, technique, duo debriefs) instead of a fixed template; structure only when it genuinely help

Team