The Adaptive Research System

Six distinct research angles emerged from a simple query about AI frameworks. Keyword routing had seen two of them. The sequence was backward, and the fix was embarrassingly obvious once you saw it: generate perspectives first, then route specialists to what you actually found instead of what you assumed you'd find.

Ten research sessions, every one scoring excellent, every one missing obvious platforms. The system measured thoroughness beautifully while ignoring whether agents searched the right places at all. Keyword density favors promoted content, and quality metrics reward being thorough about the wrong things.

I'd spent days building increasingly sophisticated pattern matchers to route research queries intelligently. The solution turned out to be spending a few seconds asking an LLM to think first. Sometimes the problem isn't that you don't know the answer. It's that you're too stubborn to use it.

Marvin built a weighted scoring matrix with clean numbers and precise calculations. Claude +3 for technical, Grok +3 for X. It looked scientific. Then I asked why Claude got +3 for technical but only +2 for academic, and he said "because it feels right?" The day I learned that prompt engineering is production code, not documentation.

The source existed. The PDF loaded. But the thirty-two percent statistic we'd cited? Nowhere in the accessible content. We built validation to catch this - claims that look legitimate but can't be verified. It worked: barely half valid, unverifiable statistics caught. Then we checked what the valid citations were actually saying. Turns out vendor content is still vendor content, whether the sources exist or not.