I recently started using Glance as the primary dashboard for my homelab, and it has quickly become one of my most-used tools. Glance allows me to monitor all my Docker containers, network devices, and services at a glance (pun intended), all within a clean, minimalist interface. It’s lightweight, fast, and extremely customisable, giving me real-time visibility into my entire environment. What Is Glance? Glance is a self-hosted dashboard that you can configure entirely through a simple YAML file. It’s designed for speed, clarity, and ease of maintenance while giving you total control over layout and content. You can display container statuses, system metrics, bookmarks, RSS feeds, or even pull live data from APIs. It offers a clean, centralised view. of the information that matters most, keeping everything organised and accessible.

Automation has always fascinated me for its ability to simplify complex processes and free up time for creative work. That curiosity naturally led me to explore new tools and that’s how I discovered n8n, a workflow automation platform that has quickly become one of my favourite tools. I kept seeing videos and articles about n8n pop up and it was one of those tools that never quite left my “must-try” list. As someone who’s passionate about automation, I was curious to see what made it stand out. Once I started digging deeper, I quickly realised how powerful and flexible it was.

When I first started exploring the world of homelabs, I thought it had to involve racks of hardware, blinking lights, and endless tinkering. I even wrote about my early experiments here. At that time, I repurposed an old desktop PC and dived head-first into virtualisation with Proxmox, containers, and self-hosted services. It was fun, but I quickly realised that what really interested me wasn’t the hardware - it was the software and services. I loved spinning up tools, learning how they worked, and making them accessible on my own terms. The hardware side, while interesting, left me feeling stuck in “decision paralysis”, what’s the perfect setup? What hardware should I buy next? Should I build a Kubernetes cluster? Instead of enjoying the process, I was constantly second-guessing.

I love using Projects to organise my chats. Aside from the organisational aspects of Projects, it is such a powerful way to interact with ChatGPT because it allows you to add custom instructions and files specifically related to the project. This is very important as it provides context for the model, and context is key when interacting with Large Language Models. Last weekend, I sat here trying to create the perfect custom project instructions and, despite my best efforts, I was not entirely satisfied with the output. I realised I was spending way too much time manually drafting custom instructions for my ChatGPT Projects. I kept running into the same problem: prompt structure. Then the penny dropped: I realised I could just use ChatGPT to help me build this, and so I built a Prompt Generator GPT. I worked iteratively with GPT-5, asking the model to ask me clarifying questions to help me design a prompt which will allow me to build project instructions for a wide range of subjects.

GPT-5 arrived with an enormous amount of expectation attached to it. By the time it launched, OpenAI had already set a precedent with GPT-4, GPT-4o, and the reasoning models that followed. Each release raised the bar, not just technically, but emotionally. As users, we have come to expect clear leaps forward, and GPT-5 seemed to miss the high benchmark mark for the majority of users. From a purely technical standpoint, GPT-5 is undeniably powerful. It improves on reasoning, long-context handling, and multimodal capability. Yet the initial reaction across the AI community was mixed, and in some cases openly critical. That contrast between capability and perception is what makes GPT-5 such an interesting release to reflect on.