Customer Service Automation · Sales Automation
Grupo Boticário needed to support a complex multi-brand reseller and franchise ecosystem across many channels while reducing repetitive operational work and preserving the human relationships that drive sales and service quality.
Reported impact
Grupo Boticário reached 100% coverage of reseller conversations in appchat and WhatsApp Enterprise, autonomously resolved up to 80% of operational requests, qualified 90% of direct-sales leads with AI, and freed the sales force to focus on advisory relationships instead of repetitive operational work.
Grupo Boticário built a proprietary agent orchestration platform to serve a reseller and franchise ecosystem that spans multiple brands, channels, and partner models. The platform combines OpenAI foundation models with business rules so teams can create agents for lead qualification, onboarding, operational support, and response validation without rebuilding each workflow from scratch. Reseller leads arriving through digital channels are qualified by AI, which answers onboarding questions around the clock and transfers prospects to human teams when they are ready to place an order. For ongoing support, the platform handles catalog requests, payment-slip questions, app issues, and other operational topics across appchat and WhatsApp Enterprise. The same system includes validation agents and business-managed prompt iteration, so frontline sales, service, and support teams can A/B test responses and continuously improve automated service quality.
A reseller lead or support request enters through a digital channel, appchat, or WhatsApp Enterprise and is routed through the proprietary agent orchestration platform. OpenAI foundation models and business rules qualify leads, answer operational questions, and decide when to hand off to human teams, while validation agents review response quality so updated prompts can be pushed back into the platform for continuous improvement.
"OpenAI provides the technology in the group’s proprietary agent orchestration platform, which combines foundation models with business rules to democratize the creation of agents focused on activating and serving its key partners: resellers and franchisees."
"Sales, customer service, and support teams began managing their own prompts, with continuous incremental improvements based on feedback from daily use."
"Since November 2025, they have covered 100% of conversations generated in appchat and WhatsApp Enterprise, with up to 80% autonomous resolution."
"The solution covers 90% of leads captured in direct sales."
"Today we have hundreds of agents in our ecosystem serving customers, partners, franchisees, and resellers."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
OpenAI Sample Jul 30, 2026 avatarin avatarin needed to extend expert retail support beyond store hours and turn product discovery into a natural multilingual conversation instead of a brittle keyword chatbot. 24/7 multilingual support by voice and text GPT-Realtime · Kurashi-Marugoto AI Agent · OpenAI API OpenAI Sample Jul 16, 2026 Cars24 Cars24 needed to manage a fragmented, conversation-heavy vehicle marketplace and its internal workstreams without scaling support, sales, and engineering headcount linearly with customer growth. 12% of previously lost seller leads recovered AI-powered voice and chat agents · ChatGPT Enterprise · Codex OpenAI Sample Modified · Oct 16, 2026 Localiza Localiza needed to turn generative AI into a company-wide operating model that could improve internal work, create new conversational customer entry points, and support AI-native products without treating the technology… 130 squads ChatGPT · Codex · Liza 