Overview

Master the design and implementation of advanced agentic workflows, specifically for the financial sector. Using Python and Large Language Models (LLMs), you will build autonomous systems capable of processing SWIFT transactions, detecting fraud, and automating compliance. You will implement agentic workflow patterns including Evaluator-Optimizer, Parallelization, Prompt Chaining, Routing, and Orchestrator-Workers. The course culminates in the "SwiftGuard" project, where you will engineer a complete multi-agent ecosystem to secure international financial messaging against sophisticated threats.

Syllabus

Introduction to Agentic AI Workflows for Financial Services

Learn how AI agents replace rigid rules to detect fraud in SWIFT transactions. Start your journey into adaptive financial workflows.

Understanding Agentic Workflows

Explores what defines a modern AI agent, its core components (Persona, Knowledge, Tools, Interaction), and the different types of agents based on their LLM interaction model.

Agentic Workflow Modeling

Design and visualize agentic workflows. Learn common agent types as building blocks for creating visual workflow diagrams.

Agentic Workflow Implementation for Financial Services

Learn to implement agentic workflows for SWIFT transaction processing using specialized AI agents for validation, fraud detection, risk assessment, and orchestration.

Agentic Workflow Patterns: Prompt Chaining Workflow

Introduces the Prompt Chaining pattern for breaking down complex tasks into a sequence of smaller, dependent steps. It covers strategies for task decomposition, validation, and context management.

Implementing Agentic Prompt Chaining Workflows with Python for Financial Services

Learn to build multi-agent prompt chaining workflows in Python, with each agent sequentially analyzing SWIFT transactions to produce a comprehensive, consensus-based decision.

Agentic Workflow Patterns: Routing

Teaches the Routing pattern, which involves classifying incoming tasks and directing them to the most appropriate specialized agent or processing path.

Implementing Agentic Routing Workflows with Python for Financial Services

Learn to implement agentic routing for SWIFT messages in Python using LLMs to intelligently triage transactions through specialized processing workflows.

Agentic Workflow Patterns: Parallelization

Introduces the Parallelization pattern for executing multiple agent tasks concurrently. It covers strategies for task decomposition (sharding, aspect-based) and result aggregation.

Implementing Agentic Parallelization Workflows with Python for Financial Services

Learn to build scalable multi-agent fraud detection workflows in Python using parallel processing, agent design, and modular aggregation for fast, adaptable SWIFT message analysis.

Agentic Workflow Patterns: Evaluator-Optimizer Workflow

Focuses on the Evaluator-Optimizer pattern, an iterative process of generation, critique, and refinement to improve output quality. It emphasizes clear evaluation criteria and actionable feedback.

Implementing Agentic Evaluator-Optimizer Workflows with Python for Financial Services

Learn to build Python workflows that validate, optimize, and auto-correct SWIFT messages using LLMs for efficient message processing and auditability in financial systems.

Agentic Workflow Patterns Orchestrator-Workers Workflow

Introduces the advanced Orchestrator-Workers pattern, where a central agent dynamically plans, delegates, and synthesizes the work of multiple specialized worker agents.

Implementing Agentic Orchestrator-Workers Pattern in Python for Financial Services

Learn how to implement the agentic Orchestrator-Workers pattern in Python to automate SWIFT post-processing, generating dynamic compliance and audit reports with modular, extensible agents.