This repository contains the source code for a presentation on Agentic AI in Software Engineering. This presentation explores best practices for modern development using AI-powered tools and advanced language models.
A live version of this presentation can be viewed here.
The presentation covers the paradigm shift in software engineering towards intelligent, autonomous systems. It delves into practical strategies for leveraging Agentic AI to enhance development workflows, improve code quality, and accelerate project timelines.
- Introduction to Agentic AI: Understanding the move from traditional automation to intelligent, autonomous systems.
- Prompt Engineering: Best practices for creating effective prompts to guide AI models.
- Model Context Protocol (MCP): A universal standard for connecting AI systems with external tools and data sources.
- The Evolution of Claude Models: An analysis of the significant performance leap from Claude 3.5 to Claude 4.0.
- Test-Driven Development (TDD): Using TDD as an evolutionary fitness function to guide AI code generation.
- Hybrid AI Architectures: Combining the strengths of Large Language Models (LLMs) and classical AI for robust solutions.
This presentation was developed using an Agentic AI-driven workflow:
- Initial Research & Design: Conducted using Perplexity.ai.
- Code Implementation & Refinement: Done with the assistance of Cursor AI.
The code in this repository is a practical example of the concepts discussed in the presentation.
Feel free to explore the code, and check out the live presentation!