Coding with AI

(C) Copyright Elephant Scale

October 9, 2024

Course Description

  • AI opens ways to building smart applications as never before.

    • As Andrew Ng says, AI will not replace programmers; rather, programmers that use AI will replace those programmers that do not use AI.
    • In this course, the students learn how build systems using AI.
    • Rules of sending questions to AI

  • In addition, many use cases require implementing AI in a secure, responsible manner, including but not limited to:

    • Not sending your data to third-party online AI services
    • Keeping control over the data used for training
    • Controlling actions taken by AI
    • Secure AI implementations using local models or networked local copy of the model
    • Best practices for cloud architecture

After the course, you will be able to do the following tasks

  • Talk to an AI in a correct way.
  • Script talking to AI for a programmatic implementation.
  • Organize your private documents for the implementation and break them into meaningful fragments for storing in the semantic search engine
  • Structure the flow of conversation with AI about your private documents.
  • Implement the system in production.
  • Architect testing, and continuous improvements.

Audience

  • Developers, data scientists, team leads, project managers

Skill Level

  • Intermediate to advanced.

Duration

  • Three to five days

Prerequisites

  • General familiarity with machine learning
  • Exposure to coding in any language
  • Familiarity with Python helpful

Format

  • Lectures and hands on labs. (50% – 50%)

Lab environment

  • Zero Install: There is no need to install software on students’ machines!
  • A lab environment in the cloud will be provided for students.

Students will need the following

  • A reasonably modern laptop with unrestricted connection to the Internet. Laptops with overly restrictive VPNs or firewalls may not work properly.
    • A checklist to verify connectivity will be provided
  • Chrome browser

Detailed outline

Prompt Engineering

  • Introduction to AI
  • Iterative development
    • How to iteratively analyze and refine your prompts to generate marketing copy from a product fact sheet.
  • Chatbot
    • How to use an AI to have extended conversations with chatbots personalized or specialized for specific tasks or behaviors.

Architecture, testing, and continuous improvements

  • Overview of Amazon, Azure, and Google clouds for RAG implementation
  • Evaluating and debugging Generative AI
  • Practical examples and demos

Labs

  • GitHub Copilot for code development
  • Claude 3.5 Sonnet for better coding
  • ChatGPT complete plan of architecture, approach, implementation, and test creation
  • How not to send your code to competition by using Llama use for extra privacy

Notes