AI AGENT ENGINEERING

What you'll cover

1. Introduction to AI

   Master Core AI concepts such as its types, evolution challenges and more.

2. Agentic AI

   Learn Fundamental agentic AI concepts such as the AI Model selection, The AI Stack, API Primitives and interacting with an AI Model using the Requests and the OpenAI Library.

3. Langchain

   Learn how to create Linear workflows with Langchain - the most popular and versatile library for creating intelligent applications

4. prompt Engineering

   Learn the techniques of crafting prompts that enable agent reliability and reduce hallucinations.

5. Retreival Augmented Generation

   Learn how to create context aware agents by integrating external knowledge sources using RAG techniques.

6. Tools and Model Context Protocol (MCP)

   Learn how to integrate AI agents with external systems, enabling agents to not just respond but take actions to achieve said objectives.

7. Langgraph

   Learn how to create non-linear agentic graph workflows with langgraph.

8. Agentic Interoperability

   Learn how to integrate agents built using disparate technologies using the Agent 2 Agent protocol.

9. Fine Tune AI Models

   Learn how to tailor small Language Models to your specific use case using the Unsloth Library.

10. Project

    Presenting projects, receiving feedback, and exploring opportunities for further development.

Course outcomes

• AI Agents:

  Develop AI agents that reason through tasks and respond to user requests.

• AI-Powered Applications

  Build applications that use AI models to solve real-world problems.

• Automated AI Workflows

  Build linear and conditional workflows that automate multi-step tasks using LangChain and LangGraph.

• Reliable AI Systems

  Design agents with structured prompts and outputs to improve consistency and reduce hallucinations.

• Tool-Using Agents

  Build agents that interact with external APIs, tools, and services to perform tasks beyond generating text.

• MCP-Enabled Applications

  Integrate AI agents with external systems using the Model Context Protocol (MCP).

• Knowledge-Based AI Applications

  Build RAG applications that answer questions using documents, databases, or other external knowledge sources.

• Multi-Agent Systems

  Develop collaborative AI systems in which specialized agents work together to accomplish complex tasks using CrewAI.

• Interoperable AI Agents

  Connect independently developed agents using the A2A protocol to enable communication and task delegation.

• End-to-End AI Project

  Design, implement, test, and demonstrate a functional AI application that addresses a real-world problem.