How MrBeast Uses Salesforce Agentforce to Power 1M-Player AI Puzzle Experience

MrBeast and Salesforce built an AI-powered interactive puzzle challenge for Super Bowl 2026, engaging over 1 million players through a Slackbot agent that helped fans organize clues and test theories in real time. The entire enterprise-grade platform — capable of handling 1.5 million simultaneous users — was built in 42 days using Agentforce, Experience Cloud, and MuleSoft, with zero data retained from players.

Impact

1M+

Players who engaged with AI agent

1.5M

Platform concurrent user capacity

10M

Total sign-up capacity

42 days

Build timeline

0

Data leakage incidents

Challenge

Build a real-time, consumer-facing AI puzzle experience capable of engaging millions of Super Bowl viewers simultaneously, with an intelligent agent guiding players without revealing answers, all in 42 days with zero data retention.

Solution

Deployed Salesforce Agentforce as the AI backbone with a Slackbot interface, Experience Cloud for the puzzle environment, and MuleSoft for integrations — engineered to handle 1.5M concurrent users with a zero-leakage data architecture.

Tools & Technologies

Get the full story.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

MrBeast, the world's most-subscribed YouTuber, partnered with Salesforce to create one of the largest interactive AI-powered experiences ever built for a Super Bowl campaign. The goal was to demonstrate that Agentforce could power not just enterprise workflows, but a real-time, consumer-facing experience at massive scale — using the same core platform available to business customers.

The challenge was daunting: build a multi-layered interactive puzzle that millions of fans could solve collaboratively, with an AI agent actively guiding players without revealing answers, while protecting all player data. The system had to withstand massive concurrent load, defend against prompt injection attacks, and operate with zero data retention — all while delivering a delightful, responsive experience within a 42-day build window.

Salesforce built the platform using Agentforce as the AI backbone, with a Slackbot interface that let players test theories, organize clues, and get intelligent guidance. Experience Cloud powered the interactive puzzle environment, and MuleSoft handled integrations across the stack. Prompt Builder shaped the agent's behavior — helping players think through the puzzle without giving away solutions. A zero-leakage AI architecture ensured no player data persisted after sessions ended.

The results proved the platform's enterprise-grade capabilities at consumer scale. Over 1 million players engaged with the Slackbot AI agent during the campaign. The system was engineered to support 1.5 million simultaneous users and 10 million total sign-ups. The full platform shipped in 42 days with zero data leakage incidents — demonstrating that Agentforce could handle complex, high-stakes agentic deployments far beyond the CRM context it was originally known for.

Similar Cases

UG
UOL Group
80%
incident resolution time reduction

UOL Group is Brazil’s largest digital media, technology, and payments platform, serving eight out of ten Brazilian internet users monthly across more than 200 applications and thousands of cloud and on-premises resources. After migrating from Splunk to Elastic Security and deploying Elastic AI Assistant and Attack Discovery with Amazon Bedrock integration, UOL reduced security incident resolution time by 80% — from days to minutes — and cut false positive alert volume in half.

Media & Entertainment
EA
Elastic Attack Discovery
ESElastic Security
L
Luminate
334%
increase in daily data processing speed

Luminate powers the Billboard music charts and provides data intelligence across music, film, and television for major record labels, studios, and talent agencies. After migrating from on-premises Spark and SQL Server to Snowflake, the company achieved 334% faster daily data processing across more than 3.5 terabytes of daily input. Market reports that previously took a full month now run overnight, and Luminate can for the first time deliver cross-industry insights correlating music and TV consumption.

Media & EntertainmentSSnowflakeSCSnowflake Cortex AI
CA
Comcast Advertising
10–30%
reduction in data product development time

Comcast Advertising connects brands to nearly 125 million U.S. households through multiscreen TV campaigns spanning traditional and streaming platforms. The company’s data science team used Databricks Apps to transform complex predictive models into interactive forecasting dashboards accessible directly by sales and marketing teams. Development cycles shortened by 10–30%, with campaign managers gaining the ability to run what-if scenarios in real time without data science support.

Media & EntertainmentDADatabricks AppsDDatabricks
TW
The Washington Post
100%
invoice tax accuracy coverage

The Washington Post is a technology-forward media company combining world-class journalism with digital innovation. Facing an unmanageable volume of vendor invoices with inconsistent tax formats, The Post deployed an AI Agent powered by proprietary large language models through Automation Anywhere’s Agentic Process Automation platform. The result: 100% of invoices are now validated for tax accuracy, tax overpayments have been eliminated entirely, and the Finance team captured $1 million in automation value within year one.

Media & EntertainmentAAAutomation Anywhere
T
Telepass
87%
faq resolution rate (autonomous)

Telepass deployed Salesforce Agentforce across its customer contact center, resolving 87% of FAQs autonomously and reducing average call handle time by 50% — live in 6 weeks with measurable returns within 10.

Financial TechnologySDSalesforce Data CloudAAgentforce
E
Engine
15%
average handle time reduction

Engine, a B2B travel platform handling 500,000+ annual traveler requests, deployed an Agentforce AI agent called Eva that autonomously manages over 30% of customer cases end-to-end. The implementation reduced average handle time by 15%, lifted CSAT from 3.7 to 4.3, and delivered $2M in estimated annual cost savings — all within a 12-day deployment timeline.

Travel & HospitalitySASalesforce AgentforceABAgentforce Builder
UM
UChicago Medicine
100
patient marketing segments built

UChicago Medicine deployed Salesforce Agentforce for Health alongside Health Cloud and Marketing Cloud to provide 24/7 AI-driven patient support. Autonomous agents handle prescription refills, appointment scheduling, insurance verification, and parking logistics — tasks that previously required live staff and averaged 4 minutes each. The team built 100 targeted patient marketing segments in just 4 months.

HealthcareSASalesforce AgentforceSHSalesforce Health Cloud
R
reMarkable
37%
cases handled by ai

reMarkable deployed Salesforce Agentforce in 3 weeks, with AI agent Mark handling 37% of 27,000+ monthly support cases at satisfaction levels matching human agents, plus an internal IT agent via Slack.

Consumer ElectronicsSASalesforce Agentforce