# How boAt delivers personalized fitness coaching with Amazon Bedrock

DevFeed: [How boAt delivers personalized fitness coaching with Amazon Bedrock](<https://devfeed.tech/articles/how-boat-delivers-personalized-fitness-coaching-with-amazon-bedrock-107150.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/how-boat-delivers-personalized-fitness-coaching-with-amazon-bedrock/>)

Author: Natasha Sah

Published: 2026-10-29T18:16:38Z

Content type: article

Language: en

Sources: [AWS Architecture Blog](<https://devfeed.tech/sources/aws-architecture-blog.md>)

Topics: [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>)

Tags: [advanced-ai-capabilities](<https://devfeed.tech/tags/advanced-ai-capabilities.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-api-gateway](<https://devfeed.tech/tags/amazon-api-gateway.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-documentdb](<https://devfeed.tech/tags/amazon-documentdb.md>), [amazon-elastic-compute-cloud-amazon-ec2](<https://devfeed.tech/tags/amazon-elastic-compute-cloud-amazon-ec2.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [cost](<https://devfeed.tech/tags/cost.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [fitness](<https://devfeed.tech/tags/fitness.md>), [india](<https://devfeed.tech/tags/india.md>), [smartwatch](<https://devfeed.tech/tags/smartwatch.md>), [users](<https://devfeed.tech/tags/users.md>)

## AI overview

boAt's AI Coach uses Amazon Bedrock and AWS Lambda to generate personalized fitness plans and adherence nudges from smartwatch metrics, user preferences, goals, and a predefined period of history stored in Amazon RDS for MySQL and Amazon DocumentDB. Lambda expands legacy data keys into clearer descriptions for the model, supplies context to Meta Llama 3.3 70B Instruct, and parses responses for the companion app, substituting safe defaults for missing fields. Prompt constraints list watch-supported activities, though the article says prompt tuning cannot eliminate all model errors. Users can configure nudge tone. The team chose Bedrock's unified model API, per-invocation CloudWatch metrics and cost allocation, and on-demand inference that scales without provisioned model compute and charges per token. It plans to consider batch inference as adoption grows; cross-Region inference profiles are described as a way to extend throughput. The feature has reportedly been in production for over six months, serving millions of users in India.

## Source excerpt

Learn how boAt built its AI Coach feature on Amazon Bedrock and AWS Lambda to deliver personalized, real-time fitness coaching to millions of smartwatch users across India, and the design choices that made the solution scalable and cost-effective.