Thoughts and ideas on how to build tools, automate workflows and speed-up the workplace.
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鈥檚 vital that we have a firm grasp of the key concepts that underpin it. Today, we鈥檙e 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鈥檙e used, and where they overlap.
Ronan McQuillan
May 30, 2025
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鈥檚 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鈥檙e using, our use case, and how widespread or varied the interactions we require are.
Ronan McQuillan
May 28, 2025
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
Agentic AI is probably the hottest topic in the world of enterprise IT. In fact, software vendors in just about every niche have added agentic AI features to their products over the past couple of years. However, in the real world, adopting AI agents isn鈥檛 such a straightforward process. On the one hand, many teams struggle to determine the right tools for their needs in a fast-evolving market. On the other hand, in their rush to roll out solutions, some companies lose sight of the need for provable ROI.
Ronan McQuillan
May 23, 2025
In the past few years, several tools have come to market, aiming to simplify and expedite the process of building AI agents. Flowise is one of the most successful entrants into this space, offering a primarily visual experience for creating, deploying, and managing agentic systems. This includes low-code tools that enable us to drag and drop configurable elements to determine agent behavior. This has helped to position Flowise as a popular option for developers and non-developers alike, as interest in agentic AI has exploded.
Ronan McQuillan
May 21, 2025
Currently, interest in agentic AI is exploding. IT teams in all industries are rushing to implement solutions that utilize autonomous agents to power workflows. This not only requires AI models that can perform reasoning, but ones that can also take action based on this. That鈥檚 where tool calling comes in. Tool calling, also sometimes referred to as function calling, is what enables an agentic AI system to interact with connected tools, services, and resources in order to perform tasks within workflows.
Ronan McQuillan
May 19, 2025
Zapier is one of the best-known automation tools on the market today. Offering a highly visual experience for connecting a wide range of external platforms, it powers all sorts of workflows in countless organizations. However, despite its popularity, Zapier isn鈥檛 suitable for all use cases. Today, we鈥檙e examining one of the most important segments of the workflow automation market by checking out some of the top open-source Zapier alternatives. Along the way, we鈥檒l check out some of the key decision points when selecting an integration and automation platform, as well as outlining the most prominent open-source vendors in this space.
Ronan McQuillan
May 15, 2025
With fast-advancing technology, running AI models locally is no longer the preserve of massive enterprises or researchers. Today, smaller businesses and even hobbyists are also leveraging self-hosted LLMs within development projects. Thanks to advances in model quantization, local runtimes and runners, and smaller yet highly capable models, it鈥檚 increasingly viable to run LLMs in cloud containers or even consumer hardware. But, of course, this introduces a range of challenges. One of the biggest is choosing the right model for our needs.
Ronan McQuillan
May 14, 2025