Practice · 2023–now · AI Present
RAG as default architecture
Retrieval-augmented generation as the answer to every knowledge problem — then "just stuff the window" as the counter-fad. Often right; often Postgres with pgvector would suffice.
How RAG as default architecture mutated
RAG-as-default mutated because grounding models in private data is real value, but the cargo cult ships embedding pipelines for FAQs that fit in context — or abandons chunking for long-context cargo cult. It failed when chunk quality and eval gaps produced confident hallucinations with citations. What sticks is retrieval with evals; what fades is RAG on every slide.
Cost of the fad
What RAG as default architecture cost
Teams stood up vector pipelines, chunking strategies, and rerankers before asking if fine-tuning or a SQL query would answer the question. Retrieval infra became the product.
Patterns
Compare with
Related
Platform · 2022–now
Vector DB gold rush
Specialized embedding stores sold as the default. Mid-market folded back into Postgres — after the vendor tour.
Framework · 2023–now
LLM app frameworks
LangChain-class glue mutated into MCP clients and thin wrappers around vendor APIs. The durable pieces are still boring: evals, retrieval, and product UX.
Practice · 2023–now
LLM eval pipelines
Regression tests for nondeterministic models that actually fail the build. The unglamorous CI that separates demos from products.
Practice · 2023–now
Embed everything
If it is text, vectorize it. Semantic search cosplay for problems that needed a better filter.
$ Embedding pipelines for tickets, PDFs, Slack, and the cafeteria menu — then nobody measured retrieval quality. Vector bills and reindex jobs became the product.
Practice · 2024–now
Long-context cargo cult
Million-token windows as a substitute for retrieval design. Stuffing PDFs until the model shrugs.
$ "Just put it in the window" replaced chunking, RAG, and information architecture until token bills and lost-in-the-middle hallucinations arrived.