Archived: early DPAIA wall-clock table

Historical only — not current evidence. This early DPAIA wall-clock table was removed from the homepage. Review (issue #251) found the measured runs did not meaningfully exercise the intended product, so these numbers should not be read as a current performance claim. It is kept here for the record only. For results backed by re-executable tests, see Experiment Findings.

The table below compared AI Agents with IDE-native semantic actions vs. file-only workflows on a selection of DPAIA tasks. It is retained unedited for transparency.

CaseTaskWith MCPWithout MCPΔ
dpaia_jhipster_sample_app-3Rename ROLE_ADMIN across JHipster app (9 files)202s440s−54%
dpaia_empty_maven_springboot3-1JWT auth from scratch (5+ new files)288s396s−27%
dpaia_feature_service-25Parent-child JPA & Flyway (10 files)382s523s−27%
dpaia_feature_service-125Multi-layer JPA+service+controller (15 files)788s1002s−21%
dpaia_spring_petclinic_rest-14Simple URL prefix replace (7 files)188s181s+4%
dpaia_train_ticket-1Extend OrderRepository JPQL (4 files)727s633s+15%