Richard Gall

1 month ago | thoughtworks.com | Richard Gall

What are the security risks of AI agents? So, what are the risks of AI agents? There are a number of ways of thinking about it, but there are two that are primarily technical and one that’s social. Let’s take a look. A potentially more serious risk is leaking data. AI agents depend on accessing different sources of information. They need to interface with various services and collect and share data where necessary in order to carry out the tasks with which it has been prompted.

1 month ago | thoughtworks.com | Richard Gall

Although the genealogy of infrastructure as code (IaC) can be traced back to very early configuration management tools, the concept only really took the form it has today with the emergence of cloud, as engineering teams had to grapple with scale in ways they previously had not. In the couple of decades since it has evolved rapidly, keeping pace with both new technological thinking and organizational needs.

1 month ago | thoughtworks.com | Richard Gall

AI-assisted software developmentAI-assisted software development was a significant area of discussion for this Technology Radar — and that’s borne out in the blips that feature. We included a number of coding assistants, including Cursor, Cline and Windsurf [all three Tools/Trial]. Clearly the field is much richer than just GitHub Copilot and we’d encourage software developers to explore what’s available.

1 month ago | thoughtworks.com | Richard Gall

Self-RAGSelf-RAG is closely related to corrective RAG. The “self” in its name refers to self-reflection, which, as we saw above, is a feature of corrective RAG. However, it goes further than evaluating each instance of retrieval by expanding self-reflection: first to the decision to actually retrieve additional data, and then actually learning from its evaluations in an iterative manner. It does this by using three models in training: a retriever, a critic and then a generator.

Feb 3, 2025 | thoughtworks.com | Richard Gall

Andrew Harmel-Law: It seems to have just been how it evolved. A very long time ago (i.e. back when I first started writing code) there were memories of architecture being something people did as opposed to a job title that people held. Perhaps the separation of roles into different people came about because the speed of development increased so rapidly, and the number of people working on systems increased so rapidly too.