The original pipeline worked. The cost was fine. Nobody asked for a rebuild. But depending on a single provider for a core capability is a decision that compounds in ways you don’t feel until it’s too late.
Why I Built the Same Pipeline Twice Read More »
Everyone debates which AI model to use. Almost nobody talks about the retrieval layer that determines what the model actually sees — and why that engineering matters more than the model itself.
The Retrieval Layer Nobody Talks About Read More »
A generous context window lets you be lazy and still get results. An 8K token limit forced a 94% reduction in wasted context — and revealed that better engineering, not a bigger model, was the answer all along.
The 8K Constraint That Made Everything Better Read More »