Agentic AI Foundations / Module 2
← Course Hub
MODULE 2 · EXPLORE

Exploring Agentic AI

What makes a system "agentic"? The Perceive → Reason → Act loop, four architecture patterns, and where MCP fits in.

🔄 The Perceive → Reason → Act Loop

Every agent, no matter how simple or complex, runs the same loop:

Key distinction: A chatbot stops at "reason." An agent closes the loop with "act," and keeps looping until the goal is met.

🏗️ Four Agent Architectures

📋

Workflow (Deterministic)

A fixed sequence of steps defined by a human, with an LLM doing the reasoning inside each step. Predictable and auditable — the right default for anything regulator-facing.

🧭

Autonomous

The agent decides its own next step at each turn, without a fixed script. More flexible, harder to audit — used sparingly in finance, usually only for research/drafting tasks with a human review gate.

🤝

Hybrid

A deterministic skeleton (e.g., "always check GL, then bank statement, then classify") with autonomous reasoning inside individual steps. The most common pattern for finance agents in practice.

👥

Multi-Agent

Several specialized agents (a Break Triage agent, a Credit Review agent, a Reporting agent) coordinated by an orchestrator that routes work to the right specialist.

🏦 Banking & Finance Examples by Architecture

ArchitectureFinance Example
WorkflowFixed month-end close checklist: pull trial balance → reconcile → flag variances > threshold → notify preparer, in that exact order every cycle
AutonomousAn agent researching the current regulatory capital treatment of a new product type before a human analyst reviews the draft summary
HybridA reconciliation agent that always follows the same 4-step check sequence, but reasons freely within each step about how to classify an unusual break
Multi-AgentAn orchestrator that routes an incoming request to either the AML Screening Agent, the Expense Policy Agent, or the Close Reporting Agent based on the topic

🔌 A First Look at MCP

The Model Context Protocol (MCP) is how an agent connects to real systems — your core banking platform, a document repository, a market data API — instead of just talking about them. Module 4 and the MCP deep-dive cover this in depth; for now, the important idea is: an agent's usefulness is capped by what it can actually reach, and MCP is the standard way to extend that reach safely.