LLMs have become the obvious starting point for building AI-powered applications. If an application needs to understand natural language, summarize information, generate content, or interact with users conversationally, an LLM is usually a good fit. But there is a tendency to use LLMs for problems that don't really need one. A lot of software problems are not fundamentally about generating content. They are about finding a solution that satisfies a set of constraints, perform

Caching is one of the most common techniques used to make applications faster. Instead of fetching the same data from a database or API every time a user requests it, an application can temporarily store that data in a cache. The next request can then be served much faster. But this raises an important question: If the original data changes, how does the cache know that its copy is no longer correct? The short answer is: a cache usually does not magically know. The applicatio