AI is changing the way we think about databases

"Developers have spent the past decade trying to forget databases exist. Not literally, of course. We still store petabytes. But for the average developer, the database became an implementation detail; an essential but staid utility layer we worked hard not to think about. We abstracted it behind object-relational mappers (ORM). We wrapped it in APIs. We stuffed semi-structured objects into columns and told ourselves it was flexible."

"We told ourselves that persistence was a solved problem and began to decouple everything. If you needed search, you bolted on a search system. Ditto for caching (grab a cache), documents (use a document store), relationships (add a graph database), etc. We thought we were being clever but really we were shifting complexity from the database engine into glue code, pipelines, and operational overhead."

"In an AI-infused application, the database stops being a passive store of record and becomes the active boundary between a probabilistic model and your system of record. The difference between a cool demo and a mission-critical system is not usually the large language model (LLM). It is the context you can retrieve, the consistency of that context, and the speed at which you can assemble it. AI has made the database visible again."

Developers abstracted databases behind ORMs, APIs, and semi-structured columns, treating persistence as solved and decoupling systems. Search, caching, document, and graph systems were bolted on, shifting complexity into glue code, pipelines, and operational overhead. AI exposes the fragility of this approach by making the database the active boundary between probabilistic models and systems of record. Reliable AI systems depend more on retrieving consistent, adequate context quickly than on the raw model. AI memory equates to a database problem, requiring rethinking how context is assembled and how multiplicity of stores affects consistency and hallucinations.

Read at InfoWorld