I write about software, AI, systems, and whatever else I can't stop trying to understand. Everything here is researched, reasoned through, and written by me.https://engineering-notes.pages.dev/https://engineering-notes.pages.dev/articles/engineering-teams-have-feedback-loops-too/https://engineering-notes.pages.dev/articles/engineering-teams-have-feedback-loops-too/The same feedback-loop analysis engineers apply to systems — latency, signal delay, damping — applies just as directly to the teams that build those systems, and it's a more useful lens than most process advice.Tue, 21 Jul 2026 00:00:00 GMTEngineering Organizationsengineering-orgfeedback-loopssystems-thinkinghttps://engineering-notes.pages.dev/articles/caching-is-a-consistency-problem/https://engineering-notes.pages.dev/articles/caching-is-a-consistency-problem/A cache isn't a performance feature that happens to need invalidation. It's a second copy of the truth, and every caching decision is really a decision about how wrong that copy is allowed to be, and for how long.Tue, 14 Jul 2026 00:00:00 GMTSystems Engineeringcachingdistributed-systemsconsistencyhttps://engineering-notes.pages.dev/articles/why-retrieval-and-reasoning-should-be-separate/https://engineering-notes.pages.dev/articles/why-retrieval-and-reasoning-should-be-separate/Retrieval-augmented generation collapses two very different failure modes into one system when retrieval and reasoning aren't treated as distinct stages with distinct contracts.Thu, 02 Jul 2026 00:00:00 GMTAI / Software Architectureragarchitectureai-engineeringhttps://engineering-notes.pages.dev/articles/designing-deterministic-boundaries-around-probabilistic-ai/https://engineering-notes.pages.dev/articles/designing-deterministic-boundaries-around-probabilistic-ai/LLMs are probabilistic components. Reliable systems are built by deciding, explicitly, which parts of the system are allowed to be probabilistic and wrapping everything else in code that behaves the same way every time.Thu, 25 Jun 2026 00:00:00 GMTAI / Software Architecturearchitecturereliabilityai-engineeringhttps://engineering-notes.pages.dev/articles/what-is-a-vector-database/https://engineering-notes.pages.dev/articles/what-is-a-vector-database/What a vector database actually adds on top of raw embeddings — approximate nearest neighbor search at scale — and the trade-offs that come with the word "approximate."Tue, 16 Jun 2026 00:00:00 GMTAI Engineering Foundationsvector-databaseretrievalai-engineeringhttps://engineering-notes.pages.dev/articles/what-are-vector-embeddings/https://engineering-notes.pages.dev/articles/what-are-vector-embeddings/How text becomes a point in space, why "similar" ends up meaning something precise and measurable, and where that precision quietly breaks down.Tue, 09 Jun 2026 00:00:00 GMTAI Engineering Foundationsembeddingsvector-searchai-engineeringhttps://engineering-notes.pages.dev/articles/what-is-an-llm/https://engineering-notes.pages.dev/articles/what-is-an-llm/A precise mental model for what a large language model actually computes, why that computation is useful, and where its limits come from structurally rather than incidentally.Tue, 02 Jun 2026 00:00:00 GMTAI Engineering Foundationsllmfoundationsai-engineering