Use case

Turn your sleep data into an actual answer

Sleep data is where the gap between “here's a chart” and “here's what's going on” is widest. Stage breakdowns are only useful once something correlates them with the rest of your life.

YouI've been waking up tired even when I sleep 8 hours. Why?
Assistant → whoop_sleep({ days: 30 })
Your time in bed is fine — 8h 6m average — but efficiency is only 81%, so actual sleep is closer to 6h 34m. The pattern is late: awake time averages 1h 12m and clusters in the second half of the night. Deep sleep is also low at 47 minutes against a 1h 12m average earlier in the year. Nights following days with strain above 15 were the worst of the set.

Illustrative example. Your assistant calls the tools itself — you never name them.

Time in bed is not time asleep

WHOOP doesn't return “time asleep” directly — it's in-bed minus awake. Plenty of people are in bed eight hours and asleep six and a half, and that difference is the whole explanation for feeling wrecked.

Correlation is where it gets useful

Ask your assistant to line sleep up against something else it knows: your calendar, your training log, notes about alcohol or late meals. That's a question a sleep app structurally can't answer because it only holds one of the two datasets.

Before and after

Changed something? “Compare my sleep for the 30 days before 1 June against the 30 days after.” Two tool calls, one paragraph, no spreadsheet.

Prompts to try

  • Compare my sleep stages this month against last month.
  • Which nights had the least deep sleep, and what was my strain the day before?
  • Has my sleep efficiency changed since I stopped drinking coffee after 2pm?
  • Include naps — how much total sleep am I really getting?

Tools involved

whoop_sleep · whoop_recovery

Ask this about your own data

14-day free trial. Card required so there's no second signup at the end; cancel before day 14 and you're charged nothing.