Understanding Agentic AI | From Generative to Actionable Insights

EPISODE 1

Opening Framing — It's Not Magic

Diego opens with the idea everything else builds on: agentic AI is not a feature, a new kind of prompt, or autonomous magic. It's simply the next layer of abstraction in a pattern computing has followed for decades — manual processes became code, code became workflows, workflows became orchestration, and generative AI let us describe outcomes instead of steps. Agents add the missing piece: a system that receives an objective, plans, calls tools, and acts in the real world.

Most agents in production today aren't dramatically autonomous — they're well-designed workflows with a model making decisions inside boundaries a human architect already set. His summary: most agent demos are inspiring; most real-world deployments become a governance problem.

EPISODE 2

History & Context — Reactive vs. Proactive

To understand agentic AI, Diego zooms out to how computing has always evolved: human execution gave way to code, code to orchestration, orchestration to RPA, and eventually to generative AI, where you describe what you want instead of how to get it — still reactive. Agentic AI adds the final piece: agency.

His line for the whole shift: generative AI speaks, agentic AI acts. And because acting changes the risk, what used to be a prompt-engineering conversation becomes an architecture, security, and governance conversation.

EPISODE 3

Core Concepts — Agents, RAG, MCP

Most confusion around agentic AI is semantic, not technical, Diego argues, so Episode 3 builds the shared vocabulary: an agent is the system, not the model — if swapping the model breaks everything, you had a sophisticated prompt, not an agent.

Reasoning models trade compute for better multi-step problem-solving, at a real cost. RAG doesn't eliminate hallucination, it swaps it for retrieval problems. And MCP, "USB-C for tool access," standardizes integrations while expanding the attack surface. His closing point: agentic AI isn't AGI or ASI — it's about the ability to act, and that's what creates governance questions well ahead of any AGI debate.

Carlos Diego Cavalcanti

ABOUT THE PRESENTER

Carlos "Diego" Cavalcanti

Diego Cavalcanti is the CEO & CTO of Valcann, EPI-USE's Latin America cloud services division, where he leads strategy and technology direction for one of the region's most trusted SAP and cloud services partners.

Diego bootstrapped Valcann from the ground up, building the business on a simple philosophy: you can't scale a relationship. Client trust has to be earned individually, even as the company grows. That approach included launching a university internship program in 2019 to develop local talent and build an engineering pipeline grounded in Valcann's own culture rather than hiring purely for headcount.

When the pandemic hit, Diego and his team navigated the uncertainty month by month instead of committing to long-term bets, a discipline that carried Valcann through to its 2023 integration into Group Elephant and EPI-USE. He views resilience less as a fixed trait and more as a discipline built through consistent decision-making under pressure, and is now focused on how AI is reshaping the professional services model for firms like Valcann.

Connect on LinkedIn →