Practice · 2023–now · AI Present
RAG as default architecture
Retrieval-augmented generation as the answer to every knowledge problem. Often right; often Postgres with pgvector would suffice.
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. 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
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.
Context
The stack gets a co-pilot
AI pair programming is already changing how code is written. Agent frameworks and vector stores are still sorting winners from demos. The durable layer will look familiar: evals, retrieval quality, product UX, and ownership. Autopilot rewrites without tests are just big-bang migrations with better slides.
Compare with
Related
Platform · 2022–now
Vector DB gold rush
Specialized stores for embeddings. Many workloads are folding back into Postgres extensions — after the vendor tour.
Framework · 2023–now
LLM app frameworks
Chains, agents, and prompt wrappers shipping weekly. The durable pieces will be boring: evals, retrieval, and product UX.
Practice · 2023–now
LLM eval pipelines
Regression tests for nondeterministic models. The unglamorous infrastructure that separates demos from products.