DD-02 — Aider: The Benchmark Creator
Aider: The Benchmark Creator
3 years of iteration. Git-first. The thin-medium reference. +7 over Pi via git-as-substrate.
60
minutes
3
artifacts
Git-as-substrate: one infrastructure choice gives Aider 5 rubric modules — state, memory, verification, permission, observability. This is the +7 over Pi. No other harness gets this much from a single decision.
Rubric Score
32/60 (+7 vs Pi) · Git is the multiplier
After This Module
01
Apply the 6-phase methodology to Aider; produce a scored card.
02
Explain Aider's git-first philosophy as a distinct architectural bet.
03
Compare Aider (thin-medium) against Pi (thin) — what does the medium thickness buy?
04
State why Aider's benchmark creation makes it the field's reference for coding-agent performance.
Artifacts