Think fast
Thoughts and ideas on how to build tools, automate workflows and speed-up the workplace.
Retrieval Augmented Generation (RAG) vs Fine-Tuning
Retrieval augmented generation (RAG) and fine-tuning are two of the key techniques that we can use to improve the output of AI-powered tools within a specific domain. However, they are far from interchangeable. Indeed, each one is a distinct technique, with its own use cases, benefits, challenges, and requirements. Today, we’re exploring what each one is, where they differ, and how we can leverage them within our own development projects.
Ronan McQuillan
Jun 25, 2025
9 AI Agent Tools for 2025
AI agents are one of the most transformative new technologies we’ve seen in decades. Because of this, teams in all industries are rushing to implement agentic solutions. At the same time, a huge number of vendors have come to market with tools for building and managing AI agents. However, these can vary greatly. On the one hand, there are highly developer-focused platforms and frameworks, while on the other, there are no-code tools, aimed at non-technical colleagues.
Ronan McQuillan
Jun 23, 2025
Chatbot APIs vs WebSockets
With the ongoing rise of generative AI, chatbots are becoming more and more prevalent. This includes a huge range of use cases across all industries. Chatbots are also becoming more sophisticated, including taking autonomous actions based on conversations with users. So, developers must be familiar with the tools and techniques that are required to output chatbot solutions. Today, we’re diving deep into an important subtopic within this, by checking out two of the most common communications techniques we’re going to encounter - Chatbot APIs and WebSockets.
Ronan McQuillan
Jun 13, 2025
AutoGen vs LangChain: In-Depth Guide
Agentic AI is probably the most exciting new technology in the world of enterprise IT. However, successful implementation is dependent on having the right tools in place. Choosing tools can be an incredibly tricky process, as this is a fast-moving space, with several prominent vendors offering distinct approaches to building AI applications and agents. These vary widely in terms of target users, ideal use cases, and the scope of what’s possible.
Ronan McQuillan
Jun 12, 2025
Glean vs Moveworks: In-Depth Guide
Enterprise search, AI agents, and intelligent, LLM-powered automations are some of the top priorities for IT managers right now. The promise of fast, secure, and accurate internal processes is driving a huge amount of interest in this space. However, many teams are also struggling to establish ROI. Part of the trouble here is that a huge number of vendors have brought solutions to market over the past few years, including both dedicated platforms and agentic features in existing SaaS tools.
Ronan McQuillan
Jun 10, 2025
Generative AI vs Agentic AI | Use Cases, Tool Stacks & Benefits
Agentic AI is one of the hottest topics in the world of enterprise technology. This is leading businesses in all industries to rush to adopt AI agents, in pursuit of efficiency gains and enhanced accuracy within workflows. However, as with any other new technology, it’s vital that we have a firm grasp of the key concepts that underpin it. Today, we’re exploring one of the most important elements to this by examining the relationship between generative AI and agentic AI, including what each one is, how they work, when they’re used, and where they overlap.
Ronan McQuillan
May 30, 2025
How to Connect an AI Model to MySQL in 4 Steps
AI is fast becoming an integral part of all kinds of development projects. At the most basic level, this requires us to know how to connect various elements of our applications to AI tools and models. As you might expect, interactions between our app’s data layer and LLMs are probably the most important component to this. The challenge is that this can take a number of different forms. This depends on what kind of data we’re using, our use case, and how widespread or varied the interactions we require are.
Ronan McQuillan
May 28, 2025
How to Connect an LLM to Postgres in 4 Steps
AI is forming a key part of more and more internal tools. At a basic level, this requires us to have the tools and techniques available to connect different layers of our applications to AI models, in order to perform functions. Naturally, the database is probably the most important component to this. However, this also poses some key challenges. For one thing, certain database engines have been quicker to adopt AI-ready functionality than others.
Ronan McQuillan
May 27, 2025