Practical Development of Agentic AI Applications

Software

All attendees must have a modern web browser and an Internet connection.

Anatomy of an AI Agent

• Agent Design Principles and Use Cases
• Type Safety and Structured Agent Frameworks
• Creating and Running a Basic Agent
• System Prompts — Static, Dynamic, and Contextual
• Configuring Model Backends
• Synchronous and Asynchronous Execution Patterns

Structured Outputs and Result Validation

• Defining Result Types with Pydantic Models
• Constraining Agent Responses with Validators
• Handling Validation Failures and Retries
• Union Types for Multi-Format Responses
• Practical Data Extraction Patterns

Tool Integration and Design

• Tool Lifecycle — Definition, Validation, and Execution
• Tool Registration and Discovery
• Passing Runtime Context to Tools
• Error Handling and Graceful Degradation
• Tool Design Patterns for Common Integrations

Dependencies and Runtime Context

• Dependency Injection for Agents
• Managing Database Connections, API Clients, and Configuration
• Scoping Dependencies to Agent Runs
• Sharing State Across Tools
• Separating Business Logic from Agent Logic
• Clean Architecture Patterns for Agentic Applications

Conversations, Memory, and State

• Managing Multi-Turn Conversations with Message History
• Memory Patterns — Sliding Window, Summary, and Hybrid
• State Persistence Strategies
• Streaming Responses and Structured Output
• Building Interactive Agent Loops
• Human-in-the-Loop Confirmation Patterns

Evaluation and Guardrails

• Defining Success Criteria for Agent Outputs
• Automated Evaluation Patterns
• Input and Output Guardrails
• Detecting Hallucination and Drift
• Cost-Quality Trade-offs
• Continuous Monitoring and Feedback Loops

Workflow Orchestration

• Sequential, Parallel, and Conditional Patterns
• Graphs and Directed Workflows
• Passing Context Between Workflow Steps
• Error Propagation and Recovery
• Checkpointing and Resumption
• Retry and Fallback Strategies

Multi-Agent Systems

• When to Use Multiple Agents vs. a Single Agent
• Agent Delegation and Escalation Patterns
• Shared vs. Isolated Context
• Coordination and Handoff Protocols
• Designing Agent Roles and Responsibilities
• Debugging Multi-Agent Interactions

Testing and Production Deployment

• Testing Agents with Simulated Model Backends
• Writing Deterministic Tests for Non-Deterministic Systems
• Capturing and Inspecting Agent Runs
• Observability and Tracing Integration
• Serving Agents as FastAPI Endpoints
• Usage Tracking and Cost Management