How Grupo Falabella Uses Agentforce to Resolve 60% of WhatsApp Inquiries

Grupo Falabella, one of Latin America's largest retailers, deployed Salesforce Agentforce on WhatsApp to autonomously handle customer service inquiries across seven countries. The AI agent resolves 60% of requests without human intervention, operates 24/7, and has driven a 3x increase in WhatsApp conversations in just three months — shifting customer support away from costly phone channels.

Impact

3x

Growth in WhatsApp conversations

2.5 million

LLM calls per month

60%

WhatsApp inquiries resolved autonomously

70–75%

Customer satisfaction rating

25%

After-hours conversations

70%

WhatsApp support share post-pilot

9 weeks

Time from build to production

17%

Online sales growth

36 million+

Customers served

Challenge

As online sales grew 17% and customer service volumes surged, Grupo Falabella's existing WhatsApp chatbot could not handle complex, policy-heavy inquiries — forcing customers to call the contact center and limiting the scalability of support across seven countries. Training human agents to navigate the vast range of product return policies, country-specific rules, and service scenarios was equally difficult and expensive.

Solution

Grupo Falabella deployed Salesforce Agentforce as an autonomous AI agent within WhatsApp, capable of answering FAQs via a RAG-powered knowledge base, retrieving real-time order status through API integrations, and escalating complex cases to live agents — all in natural, empathetic Spanish and within nine weeks of build time.

Tools & Technologies

What Leaders Say

Returning a refrigerator or a TV is different from returning a T-shirt, or a carton of milk. There are a lot of processes, definitions, and policies around what you can return, when, and how depending on the product. And solutions are different in every country. Training a human being to really understand what to do in every single situation is extremely difficult.

Daniel Arancibia, E-commerce Services & Product Corporate Executive Director, Grupo Falabella

Before Agentforce, it was very common to see customers start out on WhatsApp and then call our contact center because they couldn't find the right answer. Now that's changing. People are staying on WhatsApp because they see that Agentforce interactions actually work.

Mariana Albarracín, Customer Service & Quality Manager, Grupo Falabella

For human beings, sometimes it's hard to be kind all the time. We get tired and have our own feelings. It's not always easy to be empathetic, but Agentforce is kind by default.

Daniel Arancibia, E-commerce Services & Product Corporate Executive Director, Grupo Falabella

Agentforce is great. It can give information, it can take action, and it doesn't lose the human touch — even though it isn't a human.

Mariana Albarracín, Customer Service & Quality Manager, Grupo Falabella
Get the full story.

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

Full Story

Grupo Falabella is one of Latin America's most recognized retail conglomerates, serving over 36 million customers across seven countries through a diverse portfolio that includes multispecialist retail stores, Sodimac home improvement centers, Tottus supermarkets, Banco Falabella financial services, and Mallplaza shopping centers. As digital commerce accelerated — with online sales rising 17% — so did the volume and complexity of customer service demands arriving via phone and WhatsApp.

The company had previously deployed a basic chatbot within WhatsApp to deflect common questions, but the results were underwhelming. Although more than 80% of customers used WhatsApp daily, only half chose it for support, and many of those still ended up calling the contact center because the bot couldn't handle nuanced requests. Compounding the problem was the sheer complexity of Falabella's product and policy landscape: return rules for a refrigerator differ fundamentally from those for a T-shirt or a carton of milk, and policies vary by country. Training human agents to master every scenario across every market was both costly and impractical.

To address these challenges, Grupo Falabella implemented Salesforce Agentforce — an AI-powered autonomous agent built on the Agentforce 360 Platform — directly within WhatsApp. The solution handles three core service scenarios: answering FAQs by querying a Salesforce knowledge base using retrieval-augmented generation (RAG) powered by Data 360; providing real-time order status by pulling live data from Falabella's e-commerce platform via API; and escalating complex cases to live agents with full conversation context intact. An Einstein chatbot handles initial identity verification before seamlessly handing off to Agentforce through an omni-channel flow. The entire deployment — from build to production — took just nine weeks, with measurable business value emerging within two weeks.

The results have been transformative. Agentforce now autonomously resolves 60% of WhatsApp inquiries, with 70–75% of customers rating their interactions four or five stars. Conversations on the platform have tripled in just three months, and the agent handles 2.5 million LLM calls per month. A quarter of all Agentforce interactions occur outside business hours, delivering always-on support that was previously impossible. Just three weeks after the Colombia pilot launch, WhatsApp's share of total support interactions had already climbed to 70% — well ahead of the company's 75% target — demonstrating rapid customer adoption and satisfaction.

Looking ahead, Grupo Falabella plans to expand Agentforce to additional brands including Sodimac and to add transactional capabilities such as order cancellations. The broader Agentforce 360 Platform is also being leveraged to unify customer data across shopping categories, enabling more personalized marketing and sales engagement at scale — positioning Falabella to become the definitive one-stop destination for its customers' everyday needs.

Similar Cases

M
Morrisons
98.96%
data reporting lag reduction

Morrisons, one of the UK’s largest supermarkets serving nine million customers weekly across 500 stores, migrated its on-premise data warehouse to BigQuery and Looker, reducing reporting lag by 98.96% from one day to 15 minutes. Real-time data now powers Vertex AI demand forecasting models and a customer-facing Product Finder app that receives 50,000 hits per day during peak periods.

RetailVAVertex AIBBigQuery
E
Etsy
~80x
listings per theme increase via algotorial curation

Etsy, the global marketplace for handcrafted and vintage goods, serves nearly 90 million buyers across more than 130 million listings from 5 million sellers. Using Vertex AI, BigQuery, Dataflow, and Gemini, the company built a personalized search and discovery platform it calls “algotorial curation” — increasing listings per theme by 80x, driving a 5% lift in SEO-driven visits, and delivering a 3% conversion improvement for sellers.

RetailVAVertex AIBBigQuery
PS
Pacers Sports & Entertainment
340,000+ fans
home game attendance (indiana fever 2024 season)

Pacers Sports & Entertainment (PS&E) struggled to connect fan data spread across 30 disconnected platforms, making personalized engagement nearly impossible. By deploying Salesforce Data 360, Marketing Cloud, and Agentforce, PS&E unified its entire fan data ecosystem into a single golden record. The organization is now positioned to deliver hyper-personalized experiences across the Fever, Pacers, and all PS&E properties.

Sports & EntertainmentAAlive5SCSales Cloud
R
Rakuten
~50% reduction
mean time to recovery

Rakuten integrated OpenAI Codex into incident response, CI/CD pipelines, and autonomous development — cutting mean time to recovery by 50% and compressing quarter-long projects into weeks.

RetailOCOpenAI Codex
S
Super-Pharm
50% to 90%
inventory accuracy

Super-Pharm leveraged Google Vertex AI for ML-powered demand forecasting, improving inventory accuracy from 50% to 90% and making forecasting 10x more efficient.

RetailGBGoogle BigQueryGVGoogle Vertex AI
S
Shopify
< 24 hours
model upgrade deployment

Shopify built Sidekick, an AI commerce assistant powered by Claude Sonnet on Google Vertex AI, enabling millions of merchants to reach their first sale in days instead of weeks.

RetailCOClaude on Vertex AIGBGoogle BigQuery
CW
Camping World
40%
customer engagement increase

Camping World deployed IBM watsonx Assistant as a virtual agent named Arvee across all web properties, increasing customer engagement by 40% and improving agent efficiency by 33%.

RetailICIBM ConsultingIWIBM watsonx Assistant
F
FedEx
+13 percentage points (25% to 40%)
customer activation rate improvement

FedEx unified siloed sales, shipping, and web data using Salesforce Data 360 to act on customer signals in real time. By automating dormant account reactivation and personalizing outreach at scale, FedEx achieved over 2,000% ROI and improved customer activation rates by 13%. The platform now powers more than one billion personalized emails annually.

Logistics & TransportationADAzure Data LakeSCService Cloud