Lectures

Morning starts with a phone. In the chat with Tom2036 — a fresh image, with not a single line of text, as always.

Hey, so how do I prove anything at all? Well, I’ll fix it. I’ll open the game, make three in a row, and look at the scoreboard. If it shows three, it means it’s fine.

Tommy really wants to tell the agent, “something is wrong with the score in the game, fix it.” But he stops himself—Alex has drilled in a discipline: the thought “something is off” is not input for a fix.

Tommy gives Sam a precise clue — a log, a line, a setup — and asks him to fix the cause. Sam takes it and fairly quickly reports back: the scoring bug is fixed, the test is green, everything is great.

The conversation, the screenshots, and one caught trap — that was just now. Tommy already has everything he needs: the spec with four separated columns, the log up to line 9, the understood green trap, and the rule of honest testing.

Two level articles in one list: what a command, a log, a diff and a screenshot each confirm and how to put them into an EVIDENCE_LOG, and how to check an agent's claim about an unfamiliar project against the code and the app's behavior.