When does class start/end?
Class hours may vary, please reach out to contact@ascendientlearning.com if you have any questions.
Practical Development of Agentic AI Applications
Build durable AI agents with PydanticAI through structured outputs, tool integration, and observability. Agent anatomy and structured outputs cover design principles, type-safe frameworks, system...
Read More
$3,000USD
Duration
3 days
Course Code
GAI-2109
Available Formats
Classroom
Overview
Course Description
Build durable AI agents with PydanticAI through structured outputs, tool integration, and observability. Agent anatomy and structured outputs cover design principles, type-safe frameworks, system prompts, model backend configuration, Pydantic result types, validators, and retries on validation failure. Tool integration, dependencies, and runtime context cover the tool lifecycle, registration, dependency injection, scoping, state sharing across tools, and clean architecture patterns. Conversations, memory, evaluation, and guardrails cover multi-turn history, sliding-window and hybrid memory patterns, state persistence, human-in-the-loop confirmation, automated evaluation, input and output guardrails, and hallucination detection. Workflow orchestration, multi-agent systems, and production deployment cover sequential, parallel, and conditional patterns, directed graphs, error propagation, retry and fallback, delegation, observability tracing, and serving agents as REST endpoints. Hands-on labs produce working agents, an evaluation pipeline, multi-agent workflows, and a deployed REST API. The course is designed for software developers, data scientists, and AI engineers with Python experience.
Skills Gained
By the end of this course, participants will be able to:
- Build reliable AI agents with structured outputs, tools, and dependency injection
- Manage multi-turn conversations with memory, streaming, plus human-in-the-loop patterns
- Evaluate agent quality through input plus output guardrails
- Orchestrate multi-step plus multi-agent workflows with error recovery
- Test agents in production with simulated backends and observability tracing
Who Can Benefit
This course is designed for:
- Software Developers
- Data Scientists
- AI Engineers
Prerequisites
Participants should enter this course with:
- Practical Python experience
- GAI-1101 or equivalent
Organizational Objectives
This course assists organizations to:
- Lower agent error rates through type-safe outputs and explicit guardrails
- Reduce time-to-production for agent applications through tested deployment patterns
- Build reusable agent patterns that compound across projects through dependency injection
- Establish a shared discipline for agent observability and continuous monitoring
Software
All attendees must have a modern web browser and an Internet connection.
Course Details
Course Details
Module 1 - Anatomy of an AI Agent
By the end of this module, you will be able to describe agent design principles, configure type-safe agent frameworks, create and run a basic agent with static and dynamic system prompts, and apply synchronous and asynchronous execution patterns.
- 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
- Hands-on Lab: Build and run your first PydanticAI agent across multiple model backends and execution patterns.
Module 2 - Structured Outputs and Result Validation
By the end of this module, you will be able to define result types with Pydantic models, constrain agent responses with validators, handle validation failures with retries, and apply union types for multi-format responses.
- 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
- Hands-on Lab: Build a document classifier that produces validated structured outputs from unstructured input.
Module 3 - Tool Integration and Design
By the end of this module, you will be able to register and discover agent tools, pass runtime context, handle errors with graceful degradation, and apply tool-design patterns for common integrations.
- 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
- Hands-on Lab: Build a multi-tool agent that connects to a database and an external API for retrieval and action.
Module 4 - Dependencies and Runtime Context
By the end of this module, you will be able to apply dependency injection to agents, manage database connections and configuration, scope dependencies to agent runs, and apply clean architecture patterns to agentic applications.
- 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
- Hands-on Lab: Build a configurable agent with swappable backends through dependency injection.
Module 5 - Conversations, Memory, and State
By the end of this module, you will be able to manage multi-turn conversations with message history, apply sliding-window, summary, and hybrid memory patterns, persist state across runs, and stream responses with structured output and human-in-the-loop confirmation.
- 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
- Hands-on Lab: Build a streaming conversational agent with persistent history and a memory-management strategy.
Module 6 - Evaluation and Guardrails
By the end of this module, you will be able to define agent success criteria, build automated evaluation patterns, apply input and output guardrails, detect hallucination and drift, and operate continuous monitoring and feedback loops.
- 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
- Hands-on Lab: Build an evaluation pipeline with input and output guardrails for one agent.
Module 7 - Workflow Orchestration
By the end of this module, you will be able to compose sequential, parallel, and conditional workflow patterns, build directed graphs, propagate errors with recovery, and apply checkpointing and retry strategies.
- 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
- Hands-on Lab: Build a research-and-report workflow with branching, recovery, and checkpointing.
Module 8 - Multi-Agent Systems
By the end of this module, you will be able to recognize when to use multiple agents over a single one, apply delegation and escalation patterns, choose between shared and isolated context, and design coordination and handoff protocols.
- 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
- Hands-on Lab: Build a multi-agent data-processing workflow with explicit delegation and handoff protocols.
Module 9 - Testing and Production Deployment
By the end of this module, you will be able to test agents with simulated model backends, write deterministic tests for non-deterministic systems, capture and inspect agent runs, integrate observability and tracing, and serve agents as FastAPI endpoints.
- 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
- Hands-on Lab: Unit-test an agent with mocked models and tools, then deploy it as a REST API.
Schedule
FAQ
Does the course schedule include a Lunchbreak?
Classes typically include a 1-hour lunch break around midday. However, the exact break times and duration can vary depending on the specific class. Your instructor will provide detailed information at the start of the course.
What languages are used to deliver training?
Most courses are conducted in English, unless otherwise specified. Some courses will have the word "FRENCH" marked in red beside the scheduled date(s) indicating the language of instruction.
What does GTR stand for?
GTR stands for Guaranteed to Run; if you see a course with this status, it means this event is confirmed to run. View our GTR page to see our full list of Guaranteed to Run courses.
How do I find an Ascendient Learning training location?
We have training locations across the United States and Canada - View a complete list of classroom training locations.
Which delivery formats are available?
At Ascendient Learning, we offer training that is Instructor-Led, Online, Virtual, and Self-Paced.
Does Ascendient Learning deliver group training?
Yes, we provide training for groups, individuals and private on sites. View our group training page for more information.
What does vendor-authorized training mean?
As a vendor-authorized training partner, we offer a curriculum that our partners have vetted. We use the same course materials and facilitate the same labs as our vendor-delivered training. These courses are considered the gold standard and, as such, are priced accordingly.
Is the training too basic, or will you go deep into technology?
It depends on your requirements, your role in your company, and your depth of knowledge. The good news about many of our learning paths, you can start from the fundamentals to highly specialized training.
How up-to-date are your courses and support materials?
We continuously work with our vendors to evaluate and refresh course material to reflect the latest training courses and best practices.
Are your instructors seasoned trainers who have deep knowledge of the training topic?
Ascendient Learning instructors have an average of 27 years of practical IT experience and have also served as consultants for an average of 15 years. To stay current, instructors spend at least 25 percent of their time learning new, emerging technologies and courses.
Do you provide hands-on training and exercises in an actual lab environment?
Lab access is dependent on the vendor and the type of training you sign up for. However, many of our top vendors will provide lab access to students to test and practice. The course description will specify lab access.
Will you customize the training for our company’s specific needs and goals?
We will work with you to identify training needs and areas of growth. We offer a variety of training methods, such as private group training, on-site of your choice, and virtually. We provide courses and certifications that are aligned with your business goals.
How do I get started with certification?
Getting started on a certification pathway depends on your goals and the vendor you choose to get certified in. Many vendors offer entry-level IT certification to advanced IT certification that can boost your career. To get access to certification vouchers and discounts, please contact info@ascendientlearning.com.
Will I get access to content after I complete a course?
You will get access to the PDF of course books and guides, but access to the recording and slides will depend on the vendor and type of training you receive.
How do I request a W9 for Ascendient Learning?
View our filing status and how to request a W9.
Reviews
It is very good and very simple instructions. almost to much hand holding.
The format of the class was concise. I learned new skills to use at my workplace.
This course gave me a clearer understanding of the AWS cloud architecture.
Good training material and good instruction. More time needs to be provided for the lab work.
I thought the course was informative and the tools to go over the material were very nice.
