What was the impact of the AI solution?

Serves more than 100,000 women a month. Achieved 10X user growth over two years. The company says Google Cloud credits and serverless infrastructure helped it stay lean, scalable, and cost efficient. The platform supports private, personalized health insights while keeping customer data secure.

Source

GCP

Moody Month uses Gemini 2.5 Pro and Vertex AI on Google Cloud to deliver privacy-preserving personalized women’s health insights

Use case typeCustomer personalizationUpdated Jun 7, 2026

Moody Month built an AI-powered women’s health and wellness tracker on Google Cloud to deliver personalized hormone forecasts and research-backed advice. The company designed the platform to keep sensitive health data private by isolating user data in Firestore and avoiding exposure of raw user data to LLMs. It uses Cloud Run microservices, Gemini 2.5 Pro, Vertex AI, BigQuery, Looker Studio, and supporting Google Cloud services to generate, match, and visualize insights at scale.

Organization: Moody Month
Industry: Healthcare
Location: United Kingdom
Published: June 2026

Reported outcomes

1,000%

user growthRevenue & growth

100,000 users/monthmonthly users served

Strategic outcomes

Customer experience & trustDelivered private personalized health insightsRisk & complianceProtected sensitive health data from LLM exposureScale & capacityScaled efficiently on serverless infrastructure

Catalog median for revenue & growth deployments: +34% across 150 reported metrics. Compare benchmarks →

Primary read

Use case focus

Showing 3 of 3

1Customer personalization
2Real-time analytics
3Workflow orchestration

Provide personalized health and wellness insights tied to women’s hormonal cycles while protecting sensitive user health data and avoiding exposing raw data to LLMs.

Built prediction microservices on Cloud Run to forecast cycle length and generate insights.
Isolated sensitive user health data in Firestore and stored authentication details in Firebase Authentication.
Used Gemini 2.5 Pro and Vertex AI to generate expert-verified insight patterns and code without sending private user data to the model.
Applied the pre-generated patterns in separate Cloud Run services so user data could be processed privately.
Streamed outputs into BigQuery, visualized performance in Looker Studio, and orchestrated an internal AI analyst layer with Cloud Scheduler, Pub/Sub, and Cloud Tasks.

Technologies

Gemini 2.5 Pro Vertex AI Cloud Run Cloud Run functions Firestore Firebase Authentication BigQuery Looker Studio Cloud Scheduler Pub/Sub Cloud Tasks Cloud Storage Google for Startups credits

Serves more than 100,000 women a month.
Achieved 10X user growth over two years.
The company says Google Cloud credits and serverless infrastructure helped it stay lean, scalable, and cost efficient.
The platform supports private, personalized health insights while keeping customer data secure.

Architecture

Moody Month built a custom Google Cloud architecture centered on Cloud Run microservices. Sensitive user data is kept in Firestore, authentication details in Firebase Authentication, and model/data outputs flow into BigQuery and Looker Studio. Gemini 2.5 Pro is used to generate expert-verified insight patterns and corresponding code, while a separate Cloud Run service applies those patterns to private user data. Cloud Scheduler, Pub/Sub, and Cloud Tasks orchestrate an internal AI analyst layer for business insights.

Sources & evidence1

Groundedness: 5/5Type: Customer StoryPublished: Jun 7, 2026Publisher: Google CloudEvidence: PrimaryConfidence: High

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence