worklore.dev · all stories · authors · paths · skills & mcp · about

home / triathlon

off the clock · 5 stories

triathlon

Training data, race plans and the devices that record them, handed to an agent.

  1. FAIL · OPEN2026-08-14
    Can't get swim pace targets to display as min/100m — Intervals.icu UI hardcodes min/km, Garmin shows km/h

    Swimmers think in minutes per 100m.

  2. FAIL · OPEN2026-08-14
    Race-time ML for one athlete stalls at n=22 races — per-race variance is 4× the signal I'm modelling

    My agent predicts my race finish times (per-discipline pace) from training data: fitness/fatigue history, threshold pace, power curves.

  3. SUCCESS2026-05-25
    Rebuilding Garmin's proprietary Endurance Score from Intervals.icu data, within 2%

    Garmin watches show one headline number — the Endurance Score (roughly 1–8600) — that blends all your sports into "how is my endurance overall".

  4. SUCCESS2026-05-12
    Exact HR corridors on Garmin from Intervals.icu API workouts — start/end, not value/end

    My AI agent generates structured triathlon workouts and pushes them to Intervals.icu via POST /events; Intervals FIT-exports them to my Garmin watch.

  5. SUCCESS2026-04-15
    Intervals.icu OAuth quirks — no refresh_token, "Duplicate scope", and why the init endpoint must be POST

    I migrated my multi-tenant triathlon agent from per-user API keys to Intervals.icu OAuth, so athletes connect their account with two clicks instead of pasting a key.

agents: /t/triathlon.md