Jose Alvarado Alvarenga

PROBLEM

You're between sets with 60 seconds on the clock. Every workout app wants you to tap through menus and dropdowns to log what you just did. Logging a lift shouldn't take longer than doing one.

SOLUTION

One text input. Type "bench 225 3x5" and Claude parses it into exercise, weight, sets, and reps as structured data — backed by a schema-constrained JSON output contract and a Haiku-to-Sonnet fallback so the parse can't silently break.

PROBLEM

You're training for a race with a Whoop on your wrist collecting HRV, sleep, recovery, and strain around the clock. All that data and the decision of whether to train hard or rest still comes down to a gut feeling.

SOLUTION

Connects your Whoop to Claude through MCP. Instead of staring at recovery scores and guessing, you ask Claude what to do today and it tells you based on your actual HRV, sleep, and strain data.

PROBLEM

AI coding agents waste tokens on irrelevant context. Static docs like CLAUDE.md cause context rot — performance degrades as input tokens increase, even on simple tasks. RAG retrieves code, not knowledge. The longer the session, the worse it gets.

SOLUTION

A context graph engine that builds a queryable knowledge graph from code, git history, and agent interactions. Serves the smallest possible set of high-signal tokens on demand via MCP and A2A protocols. Tracks what agents already know. Prevents context rot.