AI is going to fundamentally change the fabric of our society. Dr. Eric Schmidt suggests that within a year the vast majority of programmers will be replaced by AI programmers. Satya Nadella shared that Microsoft engineers are using AI to help write software (up to 20-30%) in a recent chat with Mark Zuckerburg. Even DARPA is creating exploratory models of Human-AI teams to understand how Humans+AI will work together. AI is forcing us to reflect on the work we do and ask ourselves the question of whether it has value or not. ...
From Prompts to Agents - Understanding the 4 Levels of AI Patterns
AI, Agents, Workflows, LLMs - it all gets a bit confusing in today’s AI landscape around what all these mean. I want to break this down into a fairly simple framework to think about 4 distinct ways of using LLMs that get increasingly more complex. 1. Standalone LLM (Prompt in, Information Out) Standalone LLM This is the simplest and easiest way to engage a LLM. You enter a prompt into an LLM and it will respond based solely on its training data and the input you gave it in the prompt. This is most useful when you want a quick, self-contained answer that doesn’t require up-to-date data, personalization, or external reasoning, e.g. summarizing a paragraph, rewriting text, generating titles, or writing social media copy. You can also give it in-prompt context to help improve the answers - a concept often referred to as one/few-shot learning. ...
Model-Context-Protocol (MCP) Explained, Simply.
Model-Context-Protocol, or MCP as it’s more commonly referred to, came about in November 2024 when Anthropic introduced it to the world. But what is it really, why do we need it and how to get started? What is it? In its name, there are 3 elements: Model: This is the brain (the AI). It understands the question, figures out what it needs and when to ask for help. Context: Context of the situation (e.g. historical chat transcript) ...
UK Government AI Insights with M365 Copilot
The UK government recently released a report on their cross-department adoption and usage of M365 Copilot with some interesting results. It was an experiment that ran for 3 months across 20,000 government employees (Sept 2024 - Dec 2024) with a main goal being to understand how AI could impact productivity. Top-Level Insights From a positive persective, the key findings are as follows: Average Time Saved: Users reported saving an average of 26 minutes per day using M365 Copilot—equivalent to 13 working days per year. ...
8 Tips Plus A Bonus To Supercharge Your Development With ChatGPT
The amazing leaps and bounds in the past few months with generative AI have changed the landscape for how AI will drive faster efficieny. ChatGPT is going to revolutionize development. Don’t believe me? Well here are 8 ways to interact with ChatGPT to super charge your development right now! Get started right here - https://chat.openai.com 1. Generate boiler plate code Ever sat down to start your next project and then had to go do a bunch of searching to figure out the right starting point. I have. Every. Single. Time. Probably because I am not coding everyday anymore but still, its a pain. ChatGPT makes this so much more efficient. Not only giving you the starting point but also a recommended structure too. ...
Inbox Zero - Efficiently Efficient
The Beauty of Low Code
Platform Engineering - the new paradigm
I have been exploring a bit around platform engineering. Its a new paradigm in software development, an evolution of DevOps. ...
3 Interesting Finds and Some Thoughts
Thought of the week Don’t make things unnecessarily complex. In many conversations I have with customers, colleagues and others, it is this strange desire to make things more complex than they need to be that causes a lot of headaches. You are not Netflix. Bleeding edge for the sake of bleeding isn’t the right strategy. Start with the end in mind and march towards it in the simplest path, you might save yourself a lot of trouble along the way. ...
What On Earth Is Moldable Development
Chances are you have never heard of moldable development. And that is OK. But it is an interesting approach to try to solve the biggest time sink in development, namely understanding the current system. Developers spend over 50% of their time trying to figure out the system - can we make this more efficient? Enter Moldable Development. ...