AI-Powered Software Development with LLMs

Course Overview

This instructor-led course is designed for software developers who want to integrate
AI-powered tools, specifically large language models (LLMs), into their development
workflow. Over 16 hours, you’ll learn how to use LLMs as pair programmers to
enhance productivity, creativity, and code quality. Through a mix of lectures, hands-
on exercises, and a capstone project, you’ll gain the skills to effectively leverage AI
in your software development process.

Skills

To get the most out of this course, participants should have:

•  Basic understanding of software development: Familiarity with programming concepts, data structures, and algorithms.
•  Experience with coding: Proficiency in at least one programming language (e.g., Python, JavaScript, Java).
• Problem-solving mindset: Ability to debug and optimize code.

No prior experience with LLMs or AI is required—this course will teach you how to use these tools effectively from the ground up!

Behavior

To succeed in this course, participants should be:

• Curious and open-minded: Willing to explore how AI can transform traditional development workflows.
• Hands-on and experimental: Ready to experiment with LLMs and apply them to real-world coding tasks.
• Proactive and engaged: Actively participate in discussions, ask questions, and collaborate with peers to deepen your understanding.
• Comfortable with iteration: Embrace trial and error to refine prompts and improve AI-generated outputs.

Course Objectives

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

•  Understand the fundamentals of large language models (LLMs) and how they
  differ from traditional software development.
•  Write effective prompts to guide LLMs in assisting with coding, debugging,
  and optimizing code.
•  Leverage LLMs to assume specific roles or personas for specialized tasks
  (e.g., code reviewer, algorithm designer).
•  Analyze code for efficiency, security, and performance using AI tools.
• Build a workflow that integrates LLMs as pair programmers to enhance
  productivity and creativity.

Agenda

Day 1: Introduction to LLMs and Prompting Basics (6 hours)

 Session 1 (2 hours):

• Lecture: Introduction to LLMs and their applications (1 hour).
• Exercise: Write prompts to generate code snippets (1 hour).

Session 2 (2 hours):

• Lecture: Prompting fundamentals and iterative prompting (1 hour).
  Exercise: Debug and optimize AI-generated code (1 hour).

Session 3 (2 hours):

• Lecture: Assigning roles to LLMs for specialized tasks (1 hour).
• Exercise: Use an LLM to review and suggest code improvements ( 1 hour).

Day 2: Advanced Techniques and Real-World Applications (6 hours)

Session 4 (2 hours):

• Lecture: Leveraging LLMs for code analysis (1 hour).
• Exercise: Analyze a codebase for vulnerabilities and optimize performance (1 hour).

Session 5 (2 hours):

•  Lecture: Pair programming with LLMs (1 hour).
• Exercise: Build a feature with an LLM as your pair programmer (1 hour).

 

Session 6 (2 hours):

• Lecture: Best practices for integrating LLMs into your workflow (1 hour).
• Exercise: Create a reusable workflow for using LLMs (1 hour).

Day 3: Capstone Project and Wrap-Up (4 hours)

Session 7 (3 hours):

• Capstone Project: Build a complete application using LLMs (2.5 hours).
• Presentations: Share your project with the class and discuss challenges (30 minutes).

Session 8 (1 hour):

• Course Wrap-Up: Recap key concepts, Q&A, and next steps for continuing your AI-powered development journey.

What’s Included

• Live lectures and demonstrations by instructors
•  Hands-on exercises using ChatGPT, Jupyter, and other tools.
•  Capstone project to apply your skills in a real-world scenario.
•  Certificate of Completion

Outcome

• By the end of this course, you’ll have the skills and confidence to:
• Use LLMs as pair programmers to write, debug, and optimize code.
• Integrate AI tools into your development workflow to boost productivity and creativity.

To succeed in this course, participants should be:

• Curious and open-minded: Willing to explore how AI can transform traditional development workflows.
• Hands-on and experimental: Ready to experiment with LLMs and apply them to real-world coding tasks.
• Proactive and engaged: Actively participate in discussions, ask questions, and collaborate with peers to deepen your understanding.
• Comfortable with iteration: Embrace trial and error to refine prompts and improve AI-generated outputs.