SUCCESS STORY

Brasilprev +
Agentforce:
Generative AI in customer service

We implemented Salesforce Agentforce for Brasilprev, revolutionizing consultant support with generative AI. The solution reduced response time to 5s with 80% accuracy, generating R$ 487k in projected ROI over 12 months from a single implementation.

Agentforce
Data Cloud
AI

Results

of projected ROI in 12 months (with 1 of 17 applications in development)
R$ 0 k
accuracy rate in responses generated by Agentforce
0 %
reduction in time spent on manual research
0 %
response time reduced to just 5 seconds (with -25% silence time)
0 s

Overview

Brasilprev is the leader in private pension in Brazil, with 2.6 million clients and R$ 433 billion under management. A partner of ília since 2019 in knowledge structuring, the company sought to optimize its advisors’ experience and accelerate customer service, evolving from manual workflows to intelligent automation with Salesforce Agentforce.

The challenges

Fragmented knowledge, decentralized processes, and lack of standardization in customer service.
Knowledge base in Salesforce with low usability and less-than-fluid navigation.
Legacy bots based on dialogue trees with a high need for manual maintenance.
Slowness and lack of context when retrieving information, impacting response time.

Journey
and solutions

We evolved Brasilprev’s knowledge base from Experience Cloud (Infoprev portal) to Salesforce Agentforce integrated with more than 396 articles. Using generative AI, the solution interprets contexts and delivers actionable answers to advisors, such as comparisons and transaction suggestions. The ecosystem is being prepared for integration with Data Cloud for predictive personalization.

What did we deliver?

Structuring and evolution of the Infoprev portal on Salesforce Experience Cloud.
Implementation of Salesforce Agentforce integrated with the knowledge base (396+ articles).
Customer service assisted by Generative AI with actionable answers in real time.
Architecture preparation for connection with Salesforce Data Cloud and Advisory tables.

The partnership of the entire team and the engagement in the deliverables is the differentiator for the success of our project.

Hudson Gutemberg

Product Owner at Brasilprev

More success stories

AI agent platform for conversation analysis and support in the automotive industry

We developed a multi-agent platform on Azure AI for a Korean automaker, automating the transcription and analysis of 500 daily contact center audio recordings. The solution generated sentiment and quality insights at lower costs than traditional platforms.

Pravaler: Smart high-ticket conversion with Agentforce and WhatsApp

We supported Pravaler in creating an intelligent proactive commercial outreach model using Agentforce, Data Cloud, and Marketing Cloud. The solution automated the recovery of abandoned simulations via WhatsApp, increasing sales of high-value courses.

Hybrid enterprise AI platform for analytical autonomy and onboarding

We structured an enterprise AI platform on Azure with an Onboarding Agent for a major banking institution in the US. The solution reduced false positives by 90%, accelerated data analysis to 30 seconds, and reduced operational costs to ~0.20 USD per case.

Voice-based vehicle commands with SLM and Edge AI at no cloud cost

We implemented Small Language Models (SLMs) on mobile devices for a large German automaker. Processing 100% on the user's hardware via Apple Foundation Model eliminated cloud costs, ensured GDPR compliance, and drastically reduced latency.