How do you choose top-k and the context budget for RAG, given recall, noise, and cost all pull against each other?
More chunks means higher recall but also more noise, more cost, and more lost-in-the-middle. The right k is an empirical tradeoff, not a default of 5. Here is how to find it.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
More chunks means higher recall but also more noise, more cost, and more lost-in-the-middle. The right k is an empirical tradeoff, not a default of 5. Here is how to find it.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
