Evolved conversational layer (collab with UTN BA team)
Cleon worked alongside the UTN BA technical team to improve the existing chatbot — enriching intent capture and ensuring every conversation generated a unique, reusable identifier downstream.
CASE STUDY / CENTRO DE E-LEARNING UTN BA
1,65M emails turned into 1,65M conversations with context.
51.85% open rate on over 1.65 million emails — nearly 2× the online education benchmark — the first two months after go-live.
CLIENT
IndustryOnline education
Students351.000+
Courses650
StackSFMC · IA · Journey
01 / EXECUTIVE SUMMARY
UTN BA had a chatbot in development capturing lead conversations, but that signal was lost at the email layer: everyone got the same template — no nurturing, no funnel-stage segmentation.
Cleon worked with UTN BA’s technical team to evolve the chatbot and introduced a new architecture: nurturing leads at different funnel stages and generating hyper-personalized emails dynamically through a language model, using the lead’s conversation ID as the key to retrieve the full history.
02 / THE CHALLENGE
The challenge wasn’t volume — it was disconnection.
- 01The chatbot captured each lead’s specific intent (which course, which doubt, which level).
- 02But email consumed that signal as a static template: everyone got the same message.
- 03No nurturing strategy, no funnel-stage segmentation.
- 04Previous attempts to process thousands of chat histories in real time collapsed the infrastructure (timeouts, latency, intermittent errors).
- 05Result: flat engagement and rising CAC, with the most valuable signal — the conversation itself — sleeping in the system.
03 / THE SOLUTION
UTN BA didn’t need another tool — they needed a technical partner to articulate the pieces they already had. From Cleon we designed four moves. Scroll to see how they wire together in the architecture.
THE ARCHITECTURE
The chatbot acts as the orchestrator — talking to the LLM through API + MCP. Marketing Cloud pulls leads directly from Salesforce and queries the orchestrator’s API at send-time for each email’s generative body.
Automated generative email anchored to the conversation ID
★ Architecture introduced by Cleon
The central innovation. Every email uses the lead’s conversation ID as the key to retrieve the full chat history and feed it to a language model that writes the message body dynamically. These are not templates with variables — they are emails generated, one per lead, with the real conversational context and the funnel stage as input.
Chatbot-as-orchestrator: Salesforce CRM + AI + Marketing Cloud
The chatbot acts as the orchestrator: it coordinates calls to the LLM through API + MCP (Model Context Protocol) and writes Lead / Opportunity state into the Salesforce CRM. Marketing Cloud pulls leads directly from the CRM for audience segmentation and queries the orchestrator’s API at send-time to generate each email’s personalized body. Engagement flows back into the CRM so Lead stages and Opportunities stay in sync. Zero system downtime over 1.65M sends.
Always-on journey
Every chatbot conversation triggers an individualized flow. We removed the concept of "mass send" from the stack.
04 / THE RESULTS
First two months post go-live (Jan–Feb 2026).
Open Rate
51,85%
↑ 2× industry benchmark
industry: 25% – 35%
Emails sent
1,65M
zero downtime
CTOR
11,77%
in line with benchmark (~13%)
Bounce rate
0,73%
↓ below benchmark (~1,5%)
Unsubscribe
0,48%
↓ below benchmark (~0,5%)
“We had the chatbot, the CRM and the data, but we were missing the layer that could integrate them with our lead communications in a relevant way. Cleon designed the architecture that connects our sales funnel with personalized, generative emails for each lead — and today we converse at scale with metrics that lead the market.”
Joana Scaminacci
Marketing & Strategic Alliances Manager · Centro de e-Learning UTN BA
05 / WHAT IT MEANS FOR THE BUSINESS
Email went from a declining channel to the highest-relative-engagement channel at UTN BA. A ~20 percentage-point lift in open rate on 1.65M sends translates into incremental qualified-lead pipeline that the institution absorbs without adding marketing headcount — the marginal cost of the next personalized email trends to zero.
06 / WHAT WE LEARNED
The conversation ID → CRM → language model → Marketing Cloud architecture solved a problem most orgs with chatbot + CRM + email have today: the pieces exist, the layer that articulates them does not.
From this pattern, Cleon developed an in-house leadbot + generative orchestration product that extends the same architecture to clients without an existing chatbot.
Have conversations that never reach the inbox?
A 45-minute diagnostic call. We map the gap between your chatbot/CRM and your email stack before we talk solutions.