Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I built 19 AI agents because one wasn't enough to coach my workouts

arvo.guru

Post reply on HN
Print view View original

1–3 of 3 posts

Show HN: I built 19 AI agents because one wasn't enough to coach my workouts

#1

Post by danielepelleri »

Hey HN,

  I've been lifting for years and got frustrated with fitness apps that either (a) generate a static plan and forget about you, or (b) require manual logging with no intelligence.
 
  So I built Arvo—an AI personal trainer that adapts after every single set, not just at the start of your workout.
 
  Why 19 agents instead of one? Each handles a specific job:
  - Exercise Architect (selects movements based on equipment/goals)
  - Load Navigator (calculates weight adjustments based on RIR)
  - Volume Manager (tracks MEV/MAV/MRV per muscle group)
  - Pattern Scout (extracts insights from natural language notes)
  - Movement Adapter (biomechanical weight conversion when swapping exercises)
 
  They coordinate to make decisions in

Show HN: I built 19 AI agents because one wasn't enough to coach my workouts
arvo.guru

Re: Show HN: I built 19 AI agents because one wasn't enough to coach my workouts

#2

Post by s4293918 »

Wow interesting usecase for chaining results from multiple agents together rather than a single prompt. Would definitely use this for my workouts. I used to use an app WL Analysis to measure heavy lift form, I'm sure there's better ways to do that with LLM these days.

Re: Show HN: I built 19 AI agents because one wasn't enough to coach my workouts

#3

Post by danielepelleri »

s4293918 wrote: post #2

Wow interesting usecase for chaining results from multiple agents together rather than a single prompt. Would definitely use this for my workouts. I used to use an app WL Analysis to measure heavy lift form, I'm sure there's better ways to do that with LLM these days.

100% agree
Post reply on HN