Skip to content
Mastering Claude

Home

Getting good work out of Claude11 lessons73 min
Three stacked blocks, role, context and task, snapping into an alignment frameGetting good work out of Claude
Path 2, module 3 of 5

Checking what it gives back

  1. 01A green result proves nothing until it has itself been proven7 min

    A check that has never been made to fail by a case it is actually supposed to catch has proven nothing, in the strict sense that proving requires a precise command to have run and its output to have been read: a broken detector returns zero problems, and that reads exactly like a success.

  2. 02Test the checker before trusting its verdict7 min

    A check that returns a plausible number may not return a correct one, and the gap almost never announces itself. Test the script before trusting its verdict: give it a fabricated input it must flag and a clean input it must not flag, covering the real quirks of your ground.

  3. 03The remedy against invention can invent too7 min

    A verification device is a deliverable like any other, produced by the same kind of mechanism as what it checks. Rerunning the same check does not make it independent, since a deterministic bug repeats identically: only a genuinely different method, one that could fail another way, counts as proof.

  4. 04Where you look determines what you find4 min

    A review pointed at the latest change tells you where you looked, never where the defects actually are: without having examined the rest with the same care, no conclusion about the relative danger of recent code versus old code holds up.

  5. 05A very rigorous review can still see nothing4 min

    A review, however disciplined, only judges what already exists: a screen never built or a function never written appears nowhere in its scope. What fills that gap is a different question, asked outside the code being reviewed, such as a complete user path handed to real use.

  6. 06Proven, or simply not yet refuted5 min

    Proven means you have run a precise command and can cite its output. Not yet refuted means only that nothing has caught a problem so far, a far weaker claim. A green preview or an absence of console errors therefore does not show that no defect exists.

  7. 07A form check never sees a false value8 min

    An automated check almost always verifies form and very rarely truth: a valid file, a correct encoding or a keyword on the page can all sit beside a false number. Validating a screenshot of the page that generates the document likewise does not prove what the person actually opens.

  8. 08Reopen every source before believing it8 min

    A research agent reports what an index shows, not what a live page contains today, and presents a dead link with the same confidence as a live one: any source meant to support a conclusion gets reopened before being cited.

  9. 09Count the whole population, and name the measure for what it captures7 min

    Measuring the few cases noticed by chance rather than the whole population produces a conclusion that is confident and yet wrong, and that same conclusion stays wrong if the name given to the result says something other than what the instrument actually captured.

  10. 10Three agents agree, one single source8 min

    Agents that return the same conclusion while citing the same page confirm nothing: the team holds one source, cited several times. Agreement is worth what the distinct sources behind it are worth, and a different address, or a copy under another domain, is not yet an independent source.

  11. 11What a check exempts disappears from its output8 min

    What a check exempts disappears from its output: the scope is decided once, then nobody rereads it. A compliant verdict covers the folder minus the exempted part, which can grow unnoticed. Give that part its own limit that weighs on the verdict; displaying its size is not enough.