Retrieval Is Eating Search: A Look Inside code execution
A field report on long-context workflows and what it changes for operators.
For most of the last year, the conversation around long-context workflows has been louder than the evidence. That is starting to change.
Eval harnesses, once an afterthought, are becoming the most important piece of code in many AI projects. Duolingo's team treats theirs the way an SRE team treats a runbook.
The cost curve matters here. Claude 4.5 Sonnet is roughly an order of magnitude cheaper per token than the equivalent model 18 months ago, and that changes which problems are worth automating at all.
Eval harnesses, once an afterthought, are becoming the most important piece of code in many AI projects. Atlassian's team treats theirs the way an SRE team treats a runbook.
The skeptical read is that we are watching a feature, not a platform. The optimistic read is that long context is exactly the kind of feature that becomes a platform when nobody is paying attention.
Teams that win with RAG-as-a-service tend to share a habit: they write the evals before they write the prompts. Everything else follows from that.
None of this guarantees a clean story. Inflection could ship a model next month that rearranges the assumptions in this piece. But the direction of travel, for now, is clear enough to plan around.