Classic Theory Meets Agent Practice

A row of dim review dimension slots with only one glowing, then fully lit after new modules are added, but the version on the right, weighed down by math symbols, has gone dark again

Dimension Experiments: Can a 36-Year-Old Book Fix Your Review Coverage?

Series: Classic Theory Meets Agent Practice (Part 3) Part 1: Dual-Pass Review: Why You Can’t Have Both Recall and Precision · Part 2: Strategy Genes: Pruning Review Prompts with Genetic Algorithm Thinking TL;DR: Two controlled experiments. Code review dimensions went from 8 to 11, and known-issue detection went from 1/6 to 6/6. Design review introduced Axiomatic Design dimensions, and detection also went from 1/6 to 6/6. But the version with a math formula proved that more dimensions are not always better: computation consumed review attention, and findings dropped 35%. Run controlled experiments with known issues as reference, and you learn which dimensions actually work. ...

A bloated prompt pruned into compact strategy genes, with redundant fragments removed and core constraints preserved

Strategy Genes: Pruning Review Prompts with Genetic Algorithm Thinking

Series: Classic Theory Meets Agent Practice (Part 2) Previous: Dual-Pass Review: Why Recall and Precision Cannot Both Win Next: Dimension Experiments: Can a 36-Year-Old Book Fix Your Review Coverage? TL;DR: A review prompt went from 317 lines to 135 lines (-58%), and review quality improved by 29%. What I removed was not useful procedure, but redundant content the model could infer on its own. What stayed were strategy genes: irreplaceable constraints, negative examples, and tone locks. ...

Two funnels side by side: the left one wide-mouthed catching many candidate issues, the right one narrow filtering only the valuable findings

Cascade Retrieval: A 15-Year-Old IR Trick Fixed My Design Review Agent

Series: Classic Theory Meets Agent Practice (Part 1) TL;DR: A design review agent needs to find every issue AND avoid false positives. One agent can’t do both. Borrowing cascade retrieval from information retrieval, a 15-year-old method, I split it into two: a Recall Pass that casts a wide net, and a Precision Pass that filters strictly. Real defects get caught earlier, and the risk of rework during development drops. This series is about one thing: how classic theoretical frameworks directly guide AI agent engineering. The first post starts with cascade retrieval, a 15-year-old method from information retrieval (IR), and the much older Recall vs. Precision tradeoff it sits on top of. The 1966 Cranfield II experiments proved these two goals fight each other. Applying that old problem’s newer solution to design review made a striking difference. ...