While LLMs can parse tables in files like Word or PDF, for important information it is best practice to convert tables into a specifically LLM-friendly format called markdown. This ensures the structure is as clear and readable as possible for the AI, leading to more accurate results.
____

Madgwick uses two distinct systems to remember information: permanent Knowledge for foundational facts and evolving Memory for conversational context. Understanding how to use both is key to building more effective and reliable AI assistants. The most important rule is simple: if you want an assistant to always know something, add it to its Knowledge files.
____

Madgwick assistants are designed not just for individual use, but for collaboration. Sharing a well-crafted assistant allows your colleagues to benefit from your work, either by using the tool you have built or by cloning it to create their own version. This is a simple way to distribute effective workflows and share expertise across your team and the university.
____

A practical innovation from UNE's PASS team demonstrates how thoughtful change management can turn AI fear into adoption success. The project tackles a common challenge across the university: managing high-volume administrative queries while empowering users to embrace new technology.
____

Madgwick’s AI platform includes a screen-sharing feature that enhances your workflow by giving the AI assistant real-time visibility of your screen.
____

Get started on creating your custom AI Teaching Assistant – without even leaving Word. This new approach offers an easy entry to an efficiency-enhancing assistant designed by UNE staff for our use.
____

A manual process that once consumed hours of recruitment team time has been transformed through AI-powered automation. UNE's Position Descriptors Assistant demonstrates how targeted AI solutions can address specific operational challenges, while maintaining the precision required for critical processes. 
____

Google's latest and fastest model - Gemini 2.5 Flash - is the latest cutting edge model  available for all staff in the Madgwick AI platform. Designed to be the ideal ‘balanced workhorse’ for your daily tasks, Gemini 2.5 Flash delivers a massive 1 million context size, and ups inference speed significantly, while retaining high-quality reasoning. For the majority of professional and academic work in Madgwick, Gemini 2.5 Flash offers a faster experience without a noticeable trade-off in output quality.
____