Documentation

Short technical write-ups on how Routebook is built — doubles as portfolio depth. Each page is a stub; deeper detail is available on request. The User Guide at the end is the end-user reference for the running app.

Architecture overview

How the pieces fit: Next.js App Router, Supabase, Mapbox, AI SDK, MCP, Langfuse. Where TanStack Query ends and Jotai begins.

AI coach: memory, search, tools

Multi-turn coaching with profile and episodic memory, hybrid semantic + keyword search, tool-using answers, prompt versioning.

MCP server

HTTP Streamable + SSE, OAuth and Personal Access Tokens, scope-gated tools, Goose / Claude Desktop wiring.

Fitness model & workout generation

Bannister CTL/ATL/TSB, FIT parsing, Strava sync (resumable, webhooks), structured Zwift .zwo generation.

Case study: productizing this for a coaching business

What a customized deployment looks like — surfaces, scope, integrations, timeline.

User Guide

End-user reference: drawer navigation, map controls, performance overlays, POIs, fitness analytics, and the AI coach.