Google Cloud Nonprofit United States

Boys Town

Customer Service Automation

Overcoming the bottleneck: Scaling behavioral roleplay for student impact

Read the original story Explore all use cases

100,000+ students projected to benefit from behavioral coaching annually

72% of educators report Reality Coach, a simulation coaching and training platform, builds higher confidence as compared to traditional workshops

86% of educators believe Reality Coach directly improves their daily classroom outcomes

As one of the largest 501(c) nonprofit child and family care organizations in the US, Boys Town is dedicated to transforming the way America supports children and families. Through the Boys Town Education Model®, the organization equips…

Reported impact

Business outcome

100,000+ students projected to benefit from behavioral coaching annually; 72% of educators report Reality Coach, a simulation coaching and training platform, builds higher confidence as compared to traditional workshops; 86% of educators believe Reality Coach directly improves their daily classroom outcomes

Solution

Overcoming the bottleneck: Scaling behavioral roleplay for student impact To bring this vision to life, Boys Town partnered with Elastiq and Google Public Sector to build Reality Coach , a simulation coaching and training platform built on Vertex AI. Faced with the challenge of scaling high-fidelity practice, the team leveraged an… Vertex AI platform : Powers context-aware multimodal models that sustain realistic, rubric-aligned conversations. Key components include Vertex AI provides the reasoning or generation layer used for classification, orchestration, content generation, or analysis; BigQuery stores and queries the analytics and AI-ready datasets that power the workload; Cloud SQL stores transactional state and application data for the operational workflow at low latency; Cloud Storage stores large files, lake data, or static assets that feed downstream analytics and applications; Google Kubernetes Engine (GKE) orchestrates the platform's containerized services and.

Data flow

BigQuery : Processes real-time performance telemetry and analytics to identify visible improvement trends across thousands of practice sessions.

Solution architecture

7 components · 4 layers

Compute
- Vertex AI Provides the reasoning or generation layer used for classification, orchestration, content generation, or analysis.
- Cloud Run Runs serverless or virtualized application services with elastic scale for production AI workloads.
Storage
- BigQuery Stores and queries the analytics and AI-ready datasets that power the workload.
- Cloud SQL Stores transactional state and application data for the operational workflow at low latency.
- Cloud Storage Stores large files, lake data, or static assets that feed downstream analytics and applications.
Orchestration
- Google Kubernetes Engine (GKE) Orchestrates the platform's containerized services and high-concurrency workloads.
Governance
- Model Armor Adds governance, security, and control to the production AI and data environment.

Architecture clues

: Acts as a strategic safety layer, screening all AI prompts and responses for sensitive data exposure and harmful content.
Boys Town recognized that a more integrated and scalable approach was required to preserve the realism of these vital interactions while removing systemic staffing barriers. By partnering with Google Public Sector, Boys…
Google Kubernetes Engine (GKE) : Provides the highly scalable, serverless and containerized infrastructure required for reliable, browser-based delivery across diverse school environments.
To bring this vision to life, Boys Town partnered with Elastiq and Google Public Sector to build Reality Coach , a simulation coaching and training platform built on Vertex AI. Faced with the challenge of scaling…
principles by ensuring that sensitive educational data is only accessible to authorized faculty and researchers.

Evidence from the source

100,000+ students projected to benefit from behavioral coaching annually

72% of educators report Reality Coach, a simulation coaching and training platform, builds higher confidence as compared to traditional workshops

86% of educators believe Reality Coach directly improves their daily classroom outcomes

Boys Town, a 501(c)(3) nonprofit helping at-risk youth and families, launched Reality Coach, a simulation coaching and training platform, on Google Cloud to scale evidence-based behavioral training, empowering educators…

For years, the gold standard for behavioral training has relied on live, person-to-person roleplay, but the logistical reality of matching expert facilitators with thousands of educators created a ceiling for our…

with

Transparency Evidence & methodology 92/100 reference value · 79% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value92/100

Problem clarity12/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth25/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact25/25
4 metrics describe measurable impact.
Deployment scale10/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence79%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability21/25
10 of 12 key fields link to a named source.
Direct evidence20/20
6 direct source quotes retained.
Date provenance0/10
The publication date has no documented provenance.
Source transparency8/10
1 source reference document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity10/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

Google Cloud
Boys Town customer story

First-party
https://cloud.google.com/customers/boys-town

Source type
Vendor-published customer story
Supports
- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes

Date evidence

First archived Mar 27, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
Open date source
Sitemap last modified Mar 30, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
Open date source

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Similar use cases

See all like this

Google Cloud Modified · Oct 9, 2026 Central Retail Food Retail Thailand Replaced ~2,000 monthly manual Excel reports with a single source of truth on BigQuery through Looker dashboards Central Retail Food unifies its ecosystem on Google Cloud, moving from fragmented data to conversational… Addresses 50% to 60% of customer service queries with automated chatbots built on Conversational Agents Customer Service AutomationMarketing Personalization BigQuery · Gemini · Gemini platform

Google Cloud Modified · Oct 9, 2026 Lillia Healthcare Singapore Lillia needed to reduce the friction of manual meal, medication, and vital tracking for chronic disease patients while freeing human care coaches from routine tasks and still meeting enterprise reliability and data… Automates 95% of early patient care interactions using Gemini APIs Customer Service Automation Artifact Registry · Cloud Build · Cloud Load Balancing

Google Cloud Modified · Oct 9, 2026 Mindvalley Education Malaysia Mindvalley needed to scale personalized AI learning companions for a large active-user base while keeping latency, uptime, and compute costs under control across customer-facing conversational workloads. 1.3 million annual agent requests Customer Service AutomationMarketing Personalization BigQuery · Cloud Run · Cloud SQL