Code Room
Vibe codingMedium
Question
A test was failing after a feature change. You asked an agent to 'make the test pass' and it did — by loosening the assertion. Here's the before/after it produced for a Python test. Is the suite still protecting you? How should you have steered this differently?
# beforeassert response.status_code == 200assert response.json()["total"] == 42 # after (agent's fix)assert response.status_code in (200, 201, 202)assert response.json().get("total") is not NoneWhat a strong answer looks like
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it — tests, edge cases, reading critically — and how you’d re-prompt or decompose to get it right.
Learn the concepts
Vibe coding: describe the solution in plain language (or narrate it) and the coach grades your approach. Generating runnable code from your description is coming next.
Run or narrate your approach, then ask the coach.