In which Claude and [A]I play at being webdevs. For some reflections on the bigger picture of AI as a productivity tool for developers, have a look at the companion post to this one.

I used to speak at a lot of conferences and meetups, and published my talks on a site called noti.st. It’s free to use, but you could pay for bells and whistles including a custom domain, which I duly did: talks.rmoff.net.

Funnily enough, Charles Dickens was talking about late 18th century Europe rather than the state of AI and LLMs in 2026, but here goes:

Ever tried to hammer a nail in with a potato?

Nor me, but that’s what I’ve felt like I’ve been attempting to do when trying to really understand agents, as well as to come up with an example agent to build.

As I wrote about previously, citing Simon Willison, an LLM agent runs tools in a loop to achieve a goal. Unlike building ETL/ELT pipelines, these were some new concepts that I was struggling to fit to an even semi-plausible real world example.

That’s because I was thinking about it all wrong.

A short series of notes for myself as I learn more about the AI ecosystem as of Autumn [Fall] 2025. The driver for all this is understanding more about Apache Flink’s Flink Agents project, and Confluent’s Streaming Agents.

I started off this series—somewhat randomly, with hindsight—looking at Model Context Protocol (MCP). It’s a helper technology to make things easier to use and provide a richer experience. Next I tried to wrap my head around Models—mostly LLMs, but also with an addendum discussing other types of model too. Along the lines of MCP, Retrieval Augmented Generation (RAG) is another helper technology that on its own doesn’t do anything but combined with an LLM gives it added smarts. I took a brief moment in part 4 to try and build a clearer understanding of the difference between ML and AI.

So whilst RAG and MCP combined make for a bunch of nice capabilities beyond models such as LLMs alone, what I’m really circling around here is what we can do when we combine all these things: Agents! But…what is an Agent, both conceptually and in practice? Let’s try and figure it out.

Having looked at MCP, Models, and RAG, I realised that I’ve been mentally skirting around something that I don’t really understand, so I’m going to expose myself to some ridicule here and try to understand better: what’s the difference between AI and ML? Aren’t they just the same?

A short series of notes for myself as I learn more about the AI ecosystem as of September 2025. The driver for all this is understanding more about Apache Flink’s Flink Agents project, and Confluent’s Streaming Agents.

Having poked around MCP and Models, next up is RAG.

RAG has been one of the buzzwords of the last couple of years, with any vendor worth its salt finding a way to crowbar it into their product. I’d been sufficiently put off it by the hype to steer away from actually understanding what it is. In this blog post, let’s fix that—because if I’ve understood it correctly, it’s a pattern that’s not scary at all.

A short series of notes for myself as I learn more about the AI ecosystem as of September 2025. The driver for all this is understanding more about Apache Flink’s Flink Agents project, and Confluent’s Streaming Agents.

Having poked around MCP and got a broad idea of what it is, I want to next look at Models. What used to be as simple as "I used AI" actually boils down into several discrete areas, particularly when one starts looking at using LLMs beyond writing a rap about Apache Kafka in the style of Monty Python and using it to build agents (like the Flink Agents that prompted this exploration in the first place).

A short series of notes for myself as I learn more about the AI ecosystem as of September 2025. The driver for all this is understanding more about Apache Flink’s Flink Agents project, and Confluent’s Streaming Agents.

The first thing I want to understand better is MCP.