HubSpot Solution Blueprint

Fintech Ecosystem Orchestration: Unifying Fragmented Support Channels into a Governed Intercom Stack

A scaling Mexican digital SOFIPO struggled with a fragmented "Frankenstack" that erased customer context between voice and digital support.

We consolidated Zendesk and Infobip into a unified Intercom environment via Apache NiFi. Integrating Vozy voice-bots and Incode KYC ensured clean context handoffs, accelerating loan disbursements.

Executive Summary

Context

A mid-sized Mexican digital SOFIPO was burdened by a fragmented support stack (Zendesk, Infobip, SendGrid) that prevented real-time context sharing and inflated operational costs during a period of rapid customer growth.

What We Built

We engineered a unified fintech support ecosystem centered on Intercom, integrating third-party voice (Vozy), identity (Incode), and messaging gateways (Airmovil) into a single governed workspace.

Tech Stack

Intercom (Chat/Bots/Ticketing), Vozy (Voice Bots), Incode (KYC Video), Apache NiFi (Middleware).

Not a fit for organizations that rely purely on voice-only support or those without the technical capacity to manage API integrations between specialized fintech microservices.

The Challenge

"Context fragmentation" defined the failure mode. A customer might start an interaction with a Vozy voice bot to inquire about a loan, but upon switching to digital chat or video verification via Incode, all previous context was lost. This forced customers to restart their authentication and inquiry process multiple times, leading to high drop-off rates in the lending funnel.

Simultaneously, the bank was paying for redundant seat licenses across Zendesk and Infobip, with no single source of truth for customer interaction history. The technical team faced the additional constraint of needing to maintain Mexican GDPR compliance while syncing sensitive financial data from a legacy core into this multi-vendor support stack.

Our Approach

Apache NiFi bridged the legacy core and the new Intercom-centric ecosystem, a strategy we called "Stack Consolidation via Middleware." Every tool in the stack referenced the same customer ID and compliance status. We had to choose between a complex, long-term sync for Zendesk and a hard cutover. We picked the hard cutover: decommissioning Zendesk and moving straight to Intercom’s unified helpdesk forced a single workflow for all agents.

To solve the voice-to-chat gap, we engineered a custom handoff protocol between Vozy and Intercom. The voice bot’s intent data gets pushed into Intercom as a "pre-filled" conversation before the user even types their first message. We also embedded Incode’s video verification directly into the Intercom messenger interface.

Impact

30% Reduction in Agent Redirection

By equipping Intercom Resolution Bots with context from the NiFi data layer, the system successfully resolved routine account and lending inquiries. This reduced the volume of tickets requiring human intervention, allowing the bank to scale without a linear increase in support headcount.

Unified Customer Context

Voice, chat, and video interactions consolidated into Intercom, so customers no longer had to repeat information during channel switches. This "Zero-Friction Handoff" directly improved the completion rate for complex loan applications.

Decommissioning of Legacy Tech Debt

Replacing Zendesk and Infobip removed redundant licensing costs. Consolidating the stack into a unified environment reduced the technical management burden on the bank’s internal DevOps team.

Secure KYC Video Integration

Integrating Incode directly into the conversational workflow allowed for secure, real-time identity verification during the loan disbursement phase. This accelerated the time-to-fund for new lending products while maintaining strict regulatory compliance.

Technical Blueprint

Unified Context Handoff (Vozy to Intercom)

We built an API bridge that captures intent and entity data from Vozy voice interactions. When a user is escalated to digital chat, this data is pushed into Intercom as custom attributes, so the agent or bot immediately knows the previous voice-based context.

Intercom-Incode Video Bridge

To facilitate secure identity verification, we embedded Incode’s KYC video workflows into the Intercom Messenger. This enables "One-Click KYC" within a support thread, where the verification results are automatically logged against the Intercom user record.

Middleware Data Distribution (Apache NiFi)

Apache NiFi serves as the "Fintech Router," pulling real-time customer data from the legacy banking core and distributing it to Intercom and Vozy. That means a "Do Not Contact" flag or a balance change reflects across all communication channels within seconds.

Performance-Based Resolution Modeling

We shifted the support metrics from "Ticket Response Time" to "Automated Resolution Rate." By using Intercom’s Fin (AI Agent) and Resolution Bots, we established a cost-per-resolution model that aligns vendor expenses with successful customer outcomes.

An omnichannel orchestration architecture utilizing Apache NiFi as a compliance engine to connect a legacy core banking system with Intercom. It integrates Incode KYC for video verification and Vozy Voice Bots for intent-driven handoffs. This centralized model remedies context fragmentation, reducing agent redirection while enforcing PII tokenization and rate limiting.

Scope it with us

FAQ

How do you handle the security risk of passing sensitive banking data between different vendors like Vozy and Intercom?

We implement "Attribute Tokenization" at the Apache NiFi level. Instead of passing raw PII (Personally Identifiable Information), the middleware passes unique tokens that allow each system to reference the customer's core record securely. Sensitive data is only decrypted within the specific environment where it is needed for a verified interaction.

What is the benefit of replacing a legacy ticketing system like Zendesk with a conversational platform like Intercom?

For high-growth fintechs, ticketing systems often create a "waiting room" experience that kills conversion. Moving to an Intercom-led stack allows for real-time resolution and proactive marketing triggers. This shift turns "support" into a "growth channel," where a simple inquiry about a card can be instantly converted into a loan disbursement opportunity.