Financial ServicesCustomer Service

How Telepass Uses Salesforce Agentforce to Resolve 87% of Customer FAQs

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.

Impact

87%

FAQ resolution rate (autonomous)

50%

Reduction in average call handle time

10 weeks

Time to measurable returns

40,000

Weekly AI-handled conversations

Challenge

Telepass's contact center handled 2 million annual phone requests with agents limited to business hours; its prior chatbot resolved fewer than 50% of interactions autonomously and transferred the majority to humans.

Solution

Salesforce Agentforce deployed as an autonomous customer service agent resolving FAQs and guiding human reps in real time, backed by Salesforce Data Cloud for unified knowledge and MuleSoft for API integration.

Tools & Technologies

What Leaders Say

Autonomous agents are resolving 87% of customers’ frequently asked questions and reducing average call handle times by 50%.

Marco Gaeta, Chief Information Technology Officer, Telepass
Get the full context.

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

Full Story

Telepass is the backbone of cashless mobility across Europe, processing 1.4 billion toll, parking, and ferry transactions annually for over 10 million customers in 18 countries. Its contact center handles 2 million phone requests and 900,000 chat requests per year, running with 300–400 agents seasonally across an 8AM–7PM operating window. As customer volumes grew and expectations for 24/7 service increased, Telepass needed to scale support without linearly scaling headcount.

Telepass selected Salesforce Agentforce as the foundation for AI-driven customer service automation. The implementation used Agentforce Service to handle inbound customer inquiries, Salesforce Data Cloud to ground the agents in a unified, harmonised knowledge base, and MuleSoft to orchestrate API connections across Telepass's backend systems. An internal AI agent was also deployed to provide service representatives with real-time guidance during calls — instantly surfacing company policies, product SKUs, and live offers.

The rollout moved quickly. The platform was operational in 6 weeks, and Telepass reported measurable returns within 10 weeks. Testing was largely automated, with 70% conducted via the Agentforce Testing Center, reducing manual QA overhead. The AI agent handles 40,000 conversations per week, covering everyday tasks like bill retrieval, vehicle agreement signing, owner status checks, and license plate management.

The outcomes were significant: Agentforce now resolves 87% of incoming FAQ inquiries autonomously, compared to the previous chatbot that handled less than 50% independently and transferred the majority to human agents. Average call handle time for agent-assisted interactions dropped by 50% through real-time AI guidance. Customer support availability extended from an 8AM–7PM window to 24/7 — without adding headcount.

Similar Cases

WE
World Economic Forum
75%
attendee inquiries resolved instantly by ai

The World Economic Forum deployed Salesforce Agentforce as EVA, an AI concierge for Davos 2026, resolving 75% of attendee inquiries instantly and generating personalised briefings for 3,000+ global leaders across 450+ sessions.

NonprofitSDSalesforce Data CloudSASalesforce Agentforce
N
Nexo
62%
cases resolved autonomously by agentforce

Nexo, a digital assets wealth platform handling over 20,000 complex monthly inquiries, deployed Salesforce Agentforce to deliver 24/7 AI-powered customer support across its app and website. The agent autonomously answers complex FAQs requiring real-time financial data and jurisdiction-specific knowledge, resolving 62% of cases and saving 2,600 hours of manual work.

Financial ServicesSASalesforce Agentforce
B
Block
75% saving 8-10+ hours
engineers saving time weekly

Block, the financial technology company behind Square, Cash App, and Afterpay, deployed Claude as the default model in its open-source AI agent, codename goose, running through the Databricks Data Intelligence Platform. The system gives approximately 4,000 employees across 15 job profiles direct access to internal data, automated SQL generation, and AI-assisted code writing. Engineers report saving 8 to 10-plus hours per week, with goose adoption doubling within a single month.

Financial ServicesCGcodename gooseDDatabricks
SB
State Bank of India
64 million
app downloads

State Bank of India partnered with IBM to build YONO, a comprehensive mobile platform combining banking, financial services, and marketplace that achieved 64 million downloads and a USD 40-50 billion valuation.

Financial ServicesIAIBM API ConnectICIBM Consulting
C
Campfire
3 days
reduction in monthly close time

Campfire embedded Claude into its accounting platform to automate monthly closes, bank reconciliation, and financial reporting. Customers now close their books 3 days faster, reconcile bank statements 90% faster, and generate reports 50% faster. Claude powers Ember, Campfire's AI chat interface for natural language financial queries.

Financial ServicesCAClaude API
N
nCino
3.5x
faster document filing

nCino, a cloud-based banking platform serving 2,800+ financial institutions, built domain-specific AI tools on Databricks and AWS leveraging 13 years of proprietary banking data. Their Banking Advisor delivers role-based AI insights natively within the platform, while Continuous Credit Monitoring automates risk alerts across the loan lifecycle. The result is 3.5x faster document processing and a shift from reactive to proactive portfolio management.

Financial ServicesAAWSSSalesforce
S
Stripe
1,370
engineers deployed

Stripe collaborated with Anthropic to create a signed enterprise binary of Claude Code, deploying it to 1,370 engineers with zero configuration. One team migrated 10,000 lines of Scala to Java in 4 days instead of 10 weeks.

Financial ServicesCCClaude Code
N
N26
70%
task automation in targeted processes

N26 deployed Claude via AWS Bedrock across 15+ internal use cases in its first year, automating up to 70% of tasks in targeted customer service processes and cutting manual processing by 50% across 24 European markets. New AI implementations now go from ideation to evaluation in 1–2 weeks.

Financial ServicesABAmazon BedrockCEClaude Enterprise