AI Training

Overview

A hands-on course covering the design and implementation of RAG systems that ground AI outputs in your own business data.

Target Audience

Developers and IT professionals building AI-powered information systems

Prerequisites

Basic Python programming knowledge; familiarity with APIs helpful

Lab Approach

Build a functioning RAG application using real data sources

Learning Objectives

• Understand RAG architecture and use cases
• Build end-to-end RAG pipelines
• Implement vector databases and embedding models
• Evaluate and improve RAG system quality

Topics Covered

Overview

Covers the design and development of autonomous AI agents capable of reasoning, planning, and executing multi-step tasks.

Target Audience

Developers and technical professionals building agentic AI applications

Prerequisites

Python programming experience; RAG fundamentals helpful

Lab Approach

Build and deploy functional AI agents using modern frameworks

Learning Objectives

• Understand AI agent architectures
• Build agents with tool use and memory
• Design multi-agent workflows
• Implement safety and guardrails for agentic systems

Topics Covered

Overview

A focused course on the Model Context Protocol — the emerging standard for connecting AI agents to external tools, data sources, and services.

Target Audience

Developers building integrations between AI systems and external tools or APIs

Prerequisites

Python experience; AI agent concepts helpful

Lab Approach

Build functional MCP servers and connect them to AI agent workflows

Learning Objectives

• Understand MCP architecture and design goals
• Build MCP servers and clients
• Integrate AI agents with real tools using MCP
• Apply MCP in practical business automation scenarios

Topics Covered

Overview

A practical course on applying AI to real business workflows — automation, classification, extraction, and operational efficiency.

Target Audience

IT professionals and business technologists implementing AI in business operations

Prerequisites

Basic Python; no deep ML knowledge required

Lab Approach

Hands-on automation exercises using real business scenarios

Learning Objectives

• Identify suitable business processes for AI automation
• Implement AI-powered document and data processing
• Build practical automation workflows
• Evaluate AI tool suitability and limitations for business use

Topics Covered

Overview

A foundational course covering the building blocks of modern AI application development — APIs, models, prompting, and deployment.

Target Audience

Developers entering the AI application development space

Prerequisites

Intermediate Python programming experience

Lab Approach

Build and deploy a complete AI-powered application from scratch

Learning Objectives

• Understand modern AI development concepts
• Work with LLM APIs and prompt engineering
• Build simple AI-powered applications
• Evaluate model capabilities and limitations

Topics Covered