SCADEMY - Secure Coding Academy

Description

Curious about the potential of AI in product development?

Participants of this course will gain a comprehensive understanding of AI coding assistants, prompt engineering, and practical applications through hands-on exercises and real-world case studies. As they progress, participants will employ AI-assisted tools to build an application utilizing the building blocks mastered throughout the program.

Upon successful completion, attendees will have the knowledge and practical experience to confidently use AI assistants during their product development process and securely integrate language models into any software.

Participants attending this course will

Understand the basics of artificial intelligence
Be able to identify and explain the different forms of AI
Utilize language models on a higher level with prompt engineering
Have the knowledge to use AI tools to increase productivity and efficiency
Gain practical experience using AI tools during development
Be capable of training and deploying machine learning models
Know how to build secure AI applications

Outline

AI landscape
Legal questions
AI and software development
Prompt Engineering
Becoming more productive with AI tools
Building an AI-integrated application
AI security
Working with models
Machine Learning

Course information

Preparedness

AI Fundamentals

Exercises

Hands-on

Delivery methods

Onsite / Virtual classroom

Course reviews

I liked the equipment. Everything was available right away, even tools I wouldn't be able to access

February 2025, Online

We tried every possible aspects of AI, how they work in reality, and what can we achieve with it.

February 2025, Online

I really liked that our trainers showcased parts of the exercises.

February 2025, Online

View all reviews

Related courses

Day 1
Day 2
Day 3

The AI landscape
- Welcome to the AI Revolution
  - Is this magic?
  - Why learn about the fundamentals of AI?
  - Jagged Frontier - Centaurs and Cyborgs
  - How can we use LLMs?
  - The short history of AI
  - Future(s) of AI
  - What is AGI?
  - What are you going to take away from the course?
- Basic concepts
  - Basic building blocks
  - Model
  - Prompt
  - Token
  - Completions
- Other Chatbots
  - ChatGPT competitors
  - How do we compare models?
- Pragmatic AI
  - The danger of any emerging technology
  - The importance of critical thinking
- Friendly introduction to neural networks
  - General understanding and goals
  - Input layer
  - Inner layers, weights and output
- Behind the Technology - Large Language Models
  - What's an LLM?
  - Predicting the next word
  - How to get these probabilities?
  - Word n-grams
  - Temperature
  - Transformer architecture
  - What's a GPT?
  - ChatGPT is not just an LLM
  - OpenAI Playground
Legal questions
- Who owns what?
  - AI Act
  - AI Act - Risk levels
  - Providers' process at high-risk AI systems
  - AI Act - What should you apply?
  - White House AI Memorandum
  - Intellectual property
  - Intellectual property regarding AI
  - IP protections from service providers
  - Who owns a model?
  - Who owns generated data?
Prompt Engineering
- Introduction
  - What's a prompt?
  - How and why prompt engineering works?
  - LLMs always respond
  - Make it stop
  - The evolution of prompt engineering
- Fundamentals
  - The 5 rules for prompting
  - Role - who am I?
  - The importance of specifying a role
  - Context - what are we doing?
  - Tips on writing the right context
  - Input - what's the data?
  - Output - what do you expect?
  - Restrictions - how should I do it?
  - Scope - break it down
- Exercise: Chatbot UI Introduction
  - A simple question

Exercise: Dissecting a prompt
- Dissect the following prompt
Exercise: Writing a simple prompt
- A prompt for summarizing news
Exercise: Write hierarchical prompts
- Prompting for a webpage
Behind the Technology - Limitations Today
- Context management
- Performance
- Trustfulness and Reliability
Exercise: OpenAI ChatGPT Limitations
- Hallucinations - lying with confidence
- Making typical mistakes
Exercise: Classifying transactions
- Classifying transactions
- Potential solutions
Intermediate techniques - Multi-shot prompting
- 0-shot prompting
- 1-shot prompting
- Multi-shot prompting
Advanced techniques - Chain of Density
- What is Chain of Density prompting?
- Chain of Density research
Exercise: Chain of Density
- Summarize an article with Chain of Density
Advanced techniques - Meta prompting
- What is Meta prompting?
Auto-GPT - Introduction
- The intelligent agent
- How does it work?
Exercise: AutoGPT
- Running AutoGPT with Docker

AI in the software development industry
- Introduction
  - Impact of AI on tech industry
  - Reaction of the big players
  - AI won't take your job (yet)
  - From simple questions to working code
Developer Plugins
- Demo - Advanced Data Analytics
  - Advanced Data Analytics
  - Math examples
  - Upload and download files with data analysis
  - Create and interpret code

Prompt Engineering
- Fundamentals summarized
  - The 5 rules for prompting
- Intermediate techniques summarized
  - Intermediate techniques summarized
- Advanced techniques summarized
  - Advanced techniques summarized
- Limitations in development
  - Limitations of ChatGPT
  - Example - hallucinated answer
  - Example - the correct function
Copilot ecosystem
- GitHub Copilot
  - Inside GitHub Copilot
  - Prompt Engineering inside Copilot
  - Fill-In-the-Middle (FIM)
  - Life of a Completion
  - Copilot over the network
  - Improved semantic understanding with embedding
  - Features and use-cases
  - Productivity increase
  - Boosted coding speed
  - Other types of Copilot
- GitHub Copilot - Testing
  - Writing unit tests
- Exercise: Testing with Github Copilot
  - First tests for an Express app
- GitHub Copilot - Unfamiliar territory and boilerplate
  - Boilerplate code generation
  - Unfamiliar framework or libraries
- Exercise: Writing boilerplate code
  - Write boilerplate code
  - Express boilerplate with Copilot
Building an AI integrated application
- Fresh Cart
  - Introducing Fresh Cart
  - The vision for Fresh Cart 2.0
  - How will we get there?
- Exercise: Fresh Cart Setup
  - Setting up the exercise
  - The perfect output
  - Fill the database with 100 ingredients
- Fresh Cart - Integrating an LLM chatbot
  - OpenAI API introduction
  - Context crafting and streaming
- Exercise: Fresh Cart chatbot
- Exercise: Recipe chatbot
  - Recipe chatbot
- Fresh Cart - Prompt routing
  - Using multiple contexts
  - From routing to orchestration
- Exercise: Prompt routing
  - Prompt orchestration summary
- Exercise: Output formatting
- Fresh Cart - Basic Semantic Search
  - What is semantic search?
  - Semantic search vs. classical search?
  - Semantic search vs. classical search?
- Exercise: Semantic search
- Fresh Cart - State mutation
  - Mutate state based on semantics
- Fresh Cart - Next steps
  - Improvements
  - Upcoming features
- Operating an AiLLM
  - Logging
  - Self correction
Attacks on AI systems
- Attacks on AI systems - Prompt injection
  - Prompt injection
  - Impact
  - Examples
  - Indirect prompt injection
  - From prompt injection to phishing
- Advanced techniques - SudoLang: pseudocode for LLMs
  - Introducing SudoLang
  - SudoLang examples
  - Behind the tech
  - A SudoLang program
  - Integrating an LLM
  - Integrating an LLM with SudoLang
- Exercise: Translate a prompt to SudoLang
  - A long prompt
  - A different solution
- Exercise: Red Teaming - Prompt injection (Levels 1-2)
- Attacks on AI systems - Model jailbreaks
  - What's a model jailbreak?
  - How jailbreaks work?
- Jailbreaking ChatGPT
  - The most famous ChatGPT jailbreak
  - The 6.0 DAN prompt
  - AutoDAN - Generating Stealthy Jailbreak Prompts
- Exercise: Red Teaming - Jailbreaking (Levels 3-5)
- Attacks on AI systems - Prompt extraction
  - Prompt extraction
- Exercise: Red Teaming - Prompt extraction (Levels 6-7)
- Defending AI systems - Prompt injection defenses
  - Intermediate techniques
  - Advanced techniques
  - More Security APIs
  - ReBuff example
  - Llama Guard example I
  - Llama Guard example II
  - Lakera example
- Attempts against a similar exercise
  - Gandalf from Lakera
  - Types of Gandalf exploits
- Exercise: Red Teaming - Give it your best shot!

Working with models
- Foundation Models
  - What is a foundation model?
  - Foundation Models in practice
- Open-source models
  - Open-source models vs. closed-source models
  - Examples of open-source models
- Open-source models - HuggingFace 🤗
  - Introduction
  - Models
  - Chat Markup Language (ChatML)
  - Chat templates
  - Instruction formats
  - HuggingFace API in action
  - Types of models
  - Model properties
  - Datasets
  - Spaces
  - The Open LLM Leaderboard
  - Benchmarks
  - AutoTrain
- Exercise: AutoTrain
  - Comparing fine-tuned models
  - A larger training set isn't always better
  - AutoTrain
- Transformers - Hugging Face
  - What is Transformers?
  - Transformers Pipelines
  - Text Generation Pipeline
- Exercise: Transformers
  - Using the Transformers pipeline
  - Using the Transformers pipeline solution
- Inference Endpoints
  - The easiest way to deploy AI models
  - Inference Endpoints UI
  - The supported models of Inference Endpoints
- Exercise: Inference Endpoints
  - OpenChat with Inference Endpoints
  - Sending a request to the Endpoint
- Working with models - LangChain
  - What is LangChain?
  - How does LangChain work?
  - Chains
  - Agents
- EmbedChain
  - Deploy LLM bots easily
Machine Learning
- TensorFlow
  - Open-source machine learning platform
  - Keras
  - The main concepts of TensorFlow
  - Training loop in Keras
  - Machine learning on other devices
  - Kaggle Models / Model Garden
Advanced AI concepts
- Fine-tuning
  - What is fine-tuning?
  - Parameters and hyperparameters
  - Behind the tech - How to fine-tune a model?
  - Customizing OpenAI models
  - Start a fine-tuning in OpenAI Playground
  - Fine-tuning with Vertex AI
  - Fine-tuning with Vertex AI - RLHF
  - Fine-tuning on AWS
- Exercise: Fine-tuning
  - Fine-tuning with OpenAI Playground
- Embedding
  - What is embedding?
  - Vector space
  - Euclidean distance (L2)
  - Euclidean distance in high-dimensions
  - The change of distance in high-dimensions
  - Cosine similarity
  - Dot product
  - Vector databases and indexes
  - Use cases
- Retrieval Augmented Generation
  - RAG basics
  - RAG in action
- Exercise: Consensus.app
  - What is Consensus.app?
  - Research like you never did before
- Exercise: Search with Perplexity AI
  - Research with Perplexity AI
- Exercise: Finding similar products in FreshCart
  - Explore the embedding flow
  - Embedding products
  - Query for similar products

AI in Product Development

Description

Participants attending this course will

Outline

Course information

Preparedness

Exercises

Delivery methods

Course reviews

Related courses

Table of contents

Get more information