Agentic Workflows

Übersicht

Go beyond simple automation and learn to architect intelligent systems. In this course, you'll master the art of designing and building agentic workflows using Python.

You'll explore core patterns like Prompt Chaining, Routing, and Parallelization to create teams of AI agents that can reason, plan, and act to solve complex problems. You will finish by building a complete, agentic project management system, proving your ability to translate high-level goals into powerful, adaptive AI solutions.

Lehrplan

• Introduction to Agentic Workflows
Introduces the foundational concepts of AI agents and agentic workflows, setting the stage for the course. It covers prerequisites, the course environment, and how to use the necessary API keys.
• 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
Covers the practical aspects of translating agentic workflow models into Python code. Students learn to structure agent logic, define agent classes, and orchestrate their interactions.
• 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
Provides hands-on experience in implementing the Prompt Chaining pattern. Students build a multi-agent chain to solve a problem where information is passed sequentially.
• 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
Students implement a routing system where a router agent uses an LLM to classify a query and then dispatches it to the correct specialist agent, which may involve orchestrating sub-tasks.
• 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
Students implement a parallel workflow using Python's threading module, where multiple specialist agents analyze a document concurrently, and a synthesizer agent combines their findings.
• 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
Students build a two-agent system (a creator and a critic) that works in a loop. The creator generates a solution, and the critic provides feedback until the solution meets all constraints.
• 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
Students implement a market analysis report generator where an Orchestrator agent creates a plan, assigns tasks to news, competitor, and trend analysis workers, and then synthesizes their findings.
• Course Review
Course review.
• AI-Powered Agentic Workflow for Project Management
In this project you'll build a comprehensive, reusable library of different agent types and then use them to create a multi-step agentic workflow to manage a technical project.

---

Unterrichtet von

Peter Kowalchuk

---

Fachgebiete

Computer Science