WORK

How it works

1. 1

   Read the limitsa small model call pulls equipment, age group, and experience level from the question

2. 2

   Expand gym slanga dictionary turns shorthand like RDL and BSS into full exercise names

3. 3

   Retrievepgvector finds the closest exercises and passages, filtered in SQL to what the client can use

4. 4

   AnswerGemini writes from that evidence only and cites every claim

5. 5

   Checkcode verifies every citation before the answer is shown

What I built

1. 1

   The React Native apprecord a visit, transcribe it with Groq Whisper, and let the agent draft the activity log for review

2. 2

   A matcher that resolves a spoken location against 922 records by checking how many of the name's distinctive words were heard, ignoring filler words, and tolerating transcription typos; it had only been scoring the first 500 of 900+ sites, so I fixed that and backed it with 27 regression tests

3. 3

   Confidence and ambiguity thresholdswhen two locations score too close, the app asks the user to pick instead of guessing