AI Application and Agent Development
Published by Pearson
Master development techniques for building and optimizing AI apps and agents
- Learn how modern developers actually build AI apps and agents.
- Explore vibe coding and AI-augmented development as a disciplined workflow.
- Understand how agentic systems are constructed using real tools like Claude Code.
In this 4-hour live course, you’ll learn how professional developers integrate LLM APIs, structure AI-enabled workflows, and use modern tooling to build AI agents and applications.
The course focuses on AI-augmented development as an engineering discipline, not ad-hoc prompting. You’ll learn structured vibe coding workflows that combine human judgment with AI coding tools to accelerate design, implementation, debugging, and refactoring while maintaining code quality and control.
You’ll also gain practical exposure to the modern AI developer ecosystem, including Hugging Face, CI/CD pipelines for AI, and agent-centric tools such as Claude Code. Through concrete examples and live demonstrations, you’ll see how agentic applications are assembled, how tools and APIs are orchestrated, and how developers reason about agent behavior in real-world systems.
What you’ll learn and how you can apply it
- Design and build AI applications and agents using modern LLM APIs, agent frameworks, and developer tooling.
- Implement AI-augmented development workflows, combining human judgment with AI coding assistance to increase productivity and code quality.
- Use the Hugging Face ecosystem effectively, including models, datasets, and tooling, as part of real application pipelines.
- Develop and reason about agentic systems, using tools like Claude Code to create agents that plan, act, and interact with external systems.
This live event is for you because...
- You are a software developer, engineer, or technical professional who wants to build AI systems, not just experiment with prompts.
- If you are integrating LLMs into applications, exploring agent-based designs, or looking to adopt AI-augmented development practices such as vibe coding, this course provides a practical, modern approach grounded in real developer workflows.
- This course is ideal for practitioners who want to understand how AI tools fit into everyday software development and how agentic systems are actually built using today’s ecosystems.
Prerequisites
- Basic understanding of Generative AI systems, such as ChatGPT
- Coding experience with Python is beneficial, but not required
Course Set-up
- No specific setup required
- Course files available here: https://github.com/robbarto2/Oreilly-AI-Application-and-Agent-Foundations.git
Recommended Preparation
- Attend: Mastering AI and ML Fundamentals by Robert Barton and Jerome Henry
- Attend: Gen AI Foundations – Architecture, Inference, and Optimization Essentials by Robert Barton and Jerome Henry,
- Read: Demystifying Generative AI: A Practical and Intuitive Introduction by Robert Barton and Jerome Henry
Recommended Follow-up
- Watch: AI & ML Foundations by Robert Barton and Jerome Henry:
- Attend: Build Your Own AI Lab by Omar Santos
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Segment 1: Welcome and Overview (10 min)
- Course objectives and learning outcomes
- Where this course fits in the end-to-end LLM and agent development lifecycle
- How modern developers build AI-powered applications and agents
- Tools, workflows, and techniques you will apply throughout the course
Segment 2: An Introduction to AI Application Development (15 min)
- What makes AI applications different from traditional software
- Common architectural patterns for LLM-powered applications
- The role of prompts, APIs, tools, and agents in modern systems
- Moving from experimentation to repeatable development workflows
Segment 3: Working with LLM APIs (30 min)
- Overview of major LLM API providers and platforms (OpenAI, Claude, etc.)
- Request/response patterns and authentication models
- Developing with FastAPI and Pydantic
- Building API wrappers and backend services
- Understanding rate limits, throttling, and retry strategies
- Monitoring usage, latency, and cost in API-driven applications
Break (5 min)
Segment 4: Optimization Strategies & CI/CD Pipelines for LLM Apps (25 min)
- Why LLM applications require different optimization strategies
- Managing prompts, configs, and evaluations as versioned artifacts
- Testing and validating LLM behavior across environments
- Integrating LLM workflows into CI/CD pipelines
- Preventing regressions in quality, cost, and performance
Segment 5: Working with the Hugging Face Ecosystem (30 min)
- The Hugging Face platform and open-source ecosystem
- Discovering, evaluating, and selecting models from the Model Hub
- Understanding model cards, licensing, and intended use cases
- Tokenizers, datasets, and supporting tooling
- Running and experimenting with open-source models locally
- How Hugging Face fits into modern AI application pipelines
Break (5 min)
Segment 6: The AI-Augmented Developer Workflow (25 min)
- How AI tools change the software development lifecycle
- Iterative development with AI assistance
- Using AI for design, implementation, debugging, and refactoring
- Balancing human judgment with AI-generated code
- Avoiding common failure modes of AI-assisted development Segment 7: Vibe Coding: AI Development Tools and Techniques (30 min)
- What “vibe coding” really means in practice
- An introduction to Cursor
- Structuring prompts and interactions for reliable results
- Using AI tools to accelerate development without sacrificing quality
- Practical techniques for steering, correcting, and refining AI output
- Turning informal experimentation into disciplined engineering workflows
Break (5 min)
Segment 8: Using Claude Code for Agentic AI Development (50 min)
- Overview of Claude Code and its role in agentic development
- Designing agent behaviors and tool interactions
- Building an AI-powered application using Claude Code
- Constructing an agentic or RAG-based workflow end-to-end
- Lessons learned, best practices, and common pitfalls
- How agentic development fits into larger production systems
Course wrap-up and next steps (5 minutes)
Your Instructors
Rob Barton
Rob Barton is a Distinguished Engineer with Cisco. Rob has worked in the IT industry for over 27 years, the last 25 of which have been with Cisco. Rob Graduated from the University of British Columbia with a degree in Engineering Physics. Rob is a published author, with titles on subjects of Generative AI, Quality of Service (QoS), Wireless Communications, and IoT. Additionally, he has co-authored many peer-reviewed research papers and leads Cisco’s academic research partnership program. Rob holds numerous patents in the areas of AI, wireless communications, network security, cloud networking, and IoT. His current areas of work include network automation and Agentic models for IT management.
Jerome Henry
Jerome Henry is a Distinguished Engineer in the Office of the Wireless CTO at Cisco Systems. His main field of research is around optimization of performances in unlicensed wireless networks, which includes aspects of QoS, IoT, privacy, indoor location, but also AI/Machine Learning and LLMs centered on network languages. Jerome has more than 25 years of experience teaching technical courses in more than 15 different countries and 4 different languages, to audiences ranging from graduate degree students to networking professionals and technical support engineers. Jerome joined Cisco in 2012. Before that time, he was consulting and teaching heterogeneous networks and wireless integration with the European Airespace team, which was later acquired by Cisco to become their main wireless solution.
Skills covered
- Generative AI
- GPT
- Application Programming Interface (API)