Agentic Workflows for Life Sciences Research

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

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

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.

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

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

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

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.

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.

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.

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

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

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

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

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

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.

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.

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

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