Overview

This course provides a comprehensive guide to developing and implementing agentic workflows tailored for the life sciences. Starting with an introduction to the concept of agentic workflows, students will learn to model and implement these workflows using Python. Key lessons include creating various types of workflow patterns such as prompt chaining, routing, parallelization, evaluator-optimizer, and orchestrator-worker. Through hands-on projects, including a sprint focused on rapid drug repositioning, learners will gain practical experience in applying these dynamic workflows to real-world research challenges.

Syllabus

Introduction to Agentic Workflows

Explore the course overview, meet your instructors, and learn how to access and use the Vocareum OpenAI API key for hands-on projects.

Why Agentic Workflows?

Compare deterministic vs agentic workflows using PubMed: rule-based filters vs LLM-powered analysis, highlighting agentic flexibility in context understanding and structured outputs.

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.

Using Agentic Workflows

Explore modern AI agentic workflows: designing agents with goals, tools, memory, and reasoning via hands-on demos and exercises contrasting agentic vs. deterministic approaches.

Agentic Workflow Modeling

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

Applied Agentic Workflow Modeling

Compare linear and multi-agent models, and implement a biomedical literature triage using parallel agents, LLM scoring, and evidence extraction.

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.

Implementing Agentic Workflows

Learn to design, implement, and test a sequential agentic workflow in Python, passing data through specialized agents to solve complex tasks like cell authentication and drug repurposing.

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

Learn to build agentic prompt chaining workflows in Python, creating multi-step LLM pipelines with explicit handoffs for complex, structured, and regulatory data processing.

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

Learn to implement agentic routing workflows in Python using LLMs for request classification, context extraction, and dispatching to specialist agents for structured, reliable recommendations.

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

Learn to design agentic parallel workflows in Python: run independent analyses concurrently, aggregate results, and synthesize findings for robust, efficient decision-making.

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

Learn to design agentic evaluator-optimizer workflows in Python, using AI agents to iteratively improve clinical study documents through multi-criteria evaluation and revision loops.

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-Worker Pattern with Python

Learn to implement the Agentic Orchestrator-Worker pattern in Python, coordinating specialized agents for protocols, equipment, and safety into a unified experimental workflow.

Project: Agentic Workflow for Rapid Drug‑Repositioning Sprint

You will build a reusable agentic workflow that turns one prompt into a ranked drug-repurposing shortlist and validation roadmap which is structured, reproducible, and auditable.