Blog · notes from shipping
Essays, field notes, and case studies on shipping AI for small businesses — written while the code ships, not after.
Retrieval-augmented generation is the most over-pitched AI technique of the last two years. Here's what a minimal, useful RAG setup looks like for a non-enterprise team.
Most AI engagements fail on timeline, not on specs. Fixing the delivery window forces smaller, shippable scopes — and surfaces the real constraint earlier.
Fine-tuning is a fine tool. It's also the wrong one for almost every small-business use case. Here's the decision tree we actually run through.
A short list of engagements Binjaw says no to — so the scope is clear before the first call. No hidden terms, no bait-and-switch.
Most small businesses can't run their own model infrastructure — and shouldn't. Here's how we handle privacy when the model lives on someone else's GPU.
No digest, no cadence — we write when something's worth saying. If you want a heads-up when a note lands, send a line. A human reads every one.
Drop a note →