At first, ordinary runners learned to run by reading books. Later, as the running boom arrived, joining running clubs to learn and hiring coaches gradually became more common.

In the past two years of the AI era, there appear to be new ways of doing things. However, whether it's running apps or running social platforms, their original underlying architecture designs had little to do with AI.

For example, if runners want AI to analyze their workouts on Strava data, the only way is to export a CSV file, then copy and paste it into the AI chatbox, and the next time there’s a new question they have to repeat the whole process, which is very tedious.

But as of June 1, Strava officially integrated Claude large model, and previous makeshift solutions will be a thing of the past.

Strava officially announced the launch of MCP connector that can seamlessly integrate the AI model Claude into users' accounts.

After runners grant authorization, they can use simple, straightforward language to ask Claude various questions about their own training, and the AI will draw on the runner's dynamic real-time data to provide the most accurate analysis.

Whether it's heart rate, pace,GPS track, or brandand race history, AI will provide a complete 'panorama' rather than an outdated, static snapshot.