Building AI Agents with Python – Blended Learning

Blended Learning – the best of both ways to learn.

This course blends the flexibility of self-paced learning with the structure of live, instructor-led sessions. You'll learn from world-class industry experts and gain practical skills to drive meaningful results in your workplace. Our digital platform also empowers you to track your progress and manage your learning journey effectively.

By the end of this course, learners will be able to:

• Build single AI Agent and multi-agent systems using LangGraph
• Extend multi-agent systems with integrated tools to perform real-world actions, for example, for Customer Service
• Make your agentic system safe, ethical, and responsible
• Improve agentic system performance
• Complete a project to design, build, govern, test, and evaluate a working agentic AI system with a simple front end – take your project with you to demonstrate the art of the possible within your organization

Participants should have:

• Experience with base Python including collections and experience with common packages for data handling such as NumPy or Pandas.
  • If participants do not yet have the expected prior knowledge this can be gained through QADHPYTHON Data Handling with Python
• Desirable experience with Machine Learning development processes
  • If participants do not yet have this prior knowledge this can be gained through either QAIDSDP Introduction to Data Science for Data Professionals or QADSMLP Data Science and Machine Learning with Python

Target Audience

This course is designed for:

• Data Scientists
• Software Developers
• Machine Learning Engineers
• AI Engineers
• DevOps Engineers

01 The World of Agents

• Define AI agents and their components in a modern context
• Describe how agents can solve organisational problems
• Outline the current tech stack used to build agents
• Build your first AI agent with a low-code solution
• Discuss real-world agentic AI use cases

02 A Practical Introduction to Language Models

• Define what a language model is
• Describe the evolution of language models
• Distinguish between different types of language models based on architecture, scale, and modality
• Interact with a language model via a hands-on demo
• Reflect on how prompt design affects model outputs

03 Working with Multiple Agents

• Design a multi-agent system using LangGraph for agent orchestration
• Plan the roles and interactions among multiple agents for a collaborative task
• Apply coordination features for agent communication and task delegation
• Discuss the strengths, limitations, and potential issues of multi-agent systems
• Explore other frameworks for building multi-agent systems (AutoGen and CrewAI)

04 Equipping Agents with Tools

• Discuss what actions and tools are in the context of AI agents
• Learn how to define and customize your own tools
• Explore how to connect tools to agents and enable action-taking
• Handle tool errors and execution limits
• Try out pre-built tools for rapid prototyping

05 Building AI Agents for Good: Ethics, Risk, and Responsibility

• Explain why governance is essential in agentic AI systems and what can go wrong without it
• Identify the core ethical principles that should guide AI agent behavior
• Recognize key risks at the agent level and governance strategies
• Discuss what programmatic guardrails are and how they help enforce responsible behavior in AI agents
• Evaluate real-world use cases of agentic systems and debate the ethical, legal, and practical implications from different perspectives
• Connect global AI governance frameworks to the practical design of agentic systems

06 Improving Agentic Systems with RAG and Prompt Engineering

• Discuss why prompt structure and content is important and develop effective prompts to improve agentic responses
• Discuss how chain of thought and tree of thought prompting can iteratively build an optimal agent response
• Implement a RAG system which is capable of grounding an agent to a knowledge base

07 Tracing, Observability, Monitoring, & Evaluation in Agentic Systems

• Discuss why tracing is important and how it helps us see what our AI agents are actually doing behind the scenes
• Use LangSmith to monitor your agents, so you can catch bugs, see how they make decisions, and understand their outputs better
• Give your agents a score by setting up ways to evaluate their answers – using human feedback or automatic checks
• Build feedback loops so your agents can keep getting better based on how users interact with them
• Try different ways to improve your prompts and test changes before making them live
• Get your agents ready for the real world by setting up alerts and making sure they’re working well for users

08 End of Course Project

• Design a complete agentic system using LLMs, tools, memory, and multi-agent coordination
• Apply ethical principles, safety checks, and tracing and evaluation strategies to an open-ended real-world task
• Integrate RAG and prompt engineering to improve relevance and performance
• Optionally, deploy a minimal frontend using Streamlit to demonstrate the system as a working prototype

Exams and assessments

Learning outcomes are assessed through activities within this Instructor-Led course.

Delivery Method

This Blended Learning course consists of two key stages.

Self-Paced Learning

• Up to 1 hour, completed over a 4-week period prior to the live event.
• It is recommended that the self-paced learning is completed prior to joining the live event.
• It is recommended that learners have a minimum of 4 weeks between the course booking and the instructor-led live event to complete the necessary hours of learning.
• The self-paced learning is available 4 weeks prior to the live event and for 12 months following the live event.

Instructor-Led Live Event

• This course has a 3-day live event.