AI Marathon Coach Grounded in 90 Days of Actual Training Data
Built a coaching platform that reasons over real Garmin workout history — not generic templates — with a multi-turn AI interface grounded in the athlete's actual load data.
The Problem
Generic marathon training plans are static artifacts that do not adapt to current readiness, recovery, or long-run recency.
Data-heavy platforms can show ATL, CTL, and TSB trends, but athletes still need to interpret those signals and translate them into concrete next-step training decisions.
For marathon preparation, guidance had to reflect the last 90 days of actual workload rather than assumptions about the athlete's baseline fitness.
The Approach
Integrated Garmin Connect via OAuth 2.0 and ingested activity history, heart rate, and daily stats directly from the API.
Built a dashboard around endurance-critical signals: weekly mileage on a 12-week rolling basis, ATL/CTL/TSB load balance, zone distribution across Zones 1-5, and long-run history over 10 miles.
Implemented a multi-turn AI coaching interface that passes the previous 90 days of Garmin data as grounded context to Claude via AWS Bedrock.
Ensured follow-up questions retain context so recommendations account for current TSB, recent intensity distribution, and long-run spacing.
The Impact
- Delivers coaching guidance tied directly to real workout history, with no fabricated mileage or pace context
- Produces recommendations that are more specific and immediately actionable than generic plan templates
- Detects trend-level issues such as unintended intensity drift despite stable weekly mileage
- Improves decision quality for marathon build cycles by grounding every response in current load data