Print this page Private AI: Use AI Safely on Your Own Laptop

Artificial Intelligence can be an incredibly powerful tool, but many popular AI services require users to upload information to cloud-based platforms. For professionals, small business owners and privacy-conscious individuals, this raises important questions about security, confidentiality and control over sensitive information. This practical, hands-on workshop shows you how to install and use your own private AI directly on your laptop, allowing you to explore the benefits of AI without sending your data to external services. Working step-by-step in a supportive environment, you'll install a free AI application and a powerful open-source AI model that can run entirely offline.

Discover how local AI systems work, why they are becoming increasingly popular, and how they differ from cloud-based services. Learn how to securely analyse your own documents, summarise reports, extract information from PDFs and Word documents, draft responses and interact with AI while keeping your data under your control.

DELIVERY MODE

Face to face

COURSE RESOURCES

• LM Studio https://lmstudio.ai/
• Ollama https://ollama.com/
• "The Coming Wave: Technology, Power, and the Twenty-first Century's Greatest Dilemma" by Mustafa Suleyman (2023)
• "The Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence" by Kate Crawford (2021)
• "Co-Intelligence: Living and Working with AI"" by Ethan Mollick (2024)
• "Verified: How to Think Straight, Get Duped Less, and Make Better Decisions about What to Believe Online" by Mike Caulfield & Sam Wineburg (2023)

Bring a laptop (Windows 10/11, macOS 12+, or Ubuntu 20.04+). Tablets/Chromebooks won't work. Must have admin rights to install software. Specs: Minimum 8GB RAM (16GB+ highly recommended for smooth performance). 15GB+ free disk space required. Apple Silicon (M1+) or newer Intel/AMD CPUs (with AVX2 support) required. No dedicated GPU needed.

COURSE OUTLINE

• Module 1: The Privacy Problem: Explore the hidden data risks of cloud AI platforms and the specific compliance obligations for Australian businesses.
• Module 2: The Open-Source Revolution: Understand how ""local LLMs"" work, why they don't need the internet, and what to expect from models like Llama 3 and Mistral.
• Module 3: Hands-on Deployment: Step-by-step installation of a free, graphical local AI tool (LM Studio) on personal laptops.
• Module 4: First Offline Chat: Execute a true offline AI conversation (airplane mode test) to verify data sovereignty and understand critical settings.
• Module 5: Local Document Analysis: Hands-on practice loading and querying personal or sample PDFs/Word documents securely using local Retrieval-Augmented Generation (RAG).
• Module 6: Governance & Next Steps: A framework for evaluating AI use cases, managing hardware expectations, and planning future scalable deployments (like local AI servers).

LEARNING OUTCOMES

By the end of this course, students should be able to:

• Explain Data Sovereignty Risks: Articulate why public cloud AI tools pose security risks, specifically regarding Australian privacy compliance and sensitive data.
• Understand Local AI Concepts: Describe the function of open-source Large Language Models (LLMs) and how quantization allows them to run without internet access.
• Deploy Local AI Software: Successfully install, configure, and operate a no-code local AI application (such as LM Studio) on a personal computer.
• Execute Offline AI Interactions: Conduct private, offline conversations with local models and effectively adjust settings like temperature and context limits.
• Analyze Private Documents: Securely load personal or business documents (PDFs, Word docs) into a local AI system to extract information, summarize content, and draft responses without data leaving the device.
• Evaluate AI Use Cases: Objectively assess workflow requirements to determine when local, privacy-first AI is necessary versus when cloud-based AI is acceptable.