← The Clair Blog

    The pre-send check: five things to look at before AI writing leaves your screen

    AI's confident mistakes cluster in five predictable places. Scan those five before you hit send and you catch most of what matters in under a minute.

    A note before the check. Tools change constantly, but the places they get things wrong have stayed stable across every model and every update. That stability is exactly what makes a fixed check worth having, whether you draft in ChatGPT, Claude or Gemini.

    There is a particular hover that happens over the send button when AI helped write the thing underneath it. The report reads well and the email sounds right, but somewhere in the back of your mind is the knowledge that one detail in there might be wrong. So you either reread the whole piece with narrowed eyes, which defeats the point of the help, or you send it and carry a low hum of doubt into the afternoon.

    There is a better option than either, and it rests on one useful fact about how these tools fail. The prose is almost never the problem. ChatGPT writes fluent, sensible sentences all day long, and the errors hide inside them in the same five places every time.

    The short answer. AI's confident mistakes cluster in five predictable spots: numbers, names, dates, citations and quotes. Before anything AI helped write leaves your screen, scan just those five against what you know or can check. It takes under a minute for a normal email and a few minutes for a report, and it catches most of what could genuinely hurt you without proofreading everything twice.

    Why these five

    They share three properties that make them dangerous together. They are the load-bearing parts of any document, the bits a reader will act on, repeat or forward, so an error there travels. They are checkable, which means someone will eventually notice when one is wrong, and that someone is rarely you.

    And they are exactly where the tool fills gaps by inventing, because a plausible figure or reference is easy to generate and hard to spot at a glance. The sentences around them stay innocent. The details do the lying.

    The check itself

    Look at What tends to go wrong What to do
    Numbers Totals and percentages produced by prediction rather than calculation, or figures copied slightly wrong Check every figure against the source, or redo the sum in a spreadsheet
    Names People, companies and products swapped for similar ones, or spellings drifting mid-document Confirm each against the original, especially where two similar names exist
    Dates Deadlines shifted by a day or a year, or "next Friday" resolved to the wrong Friday Check any date someone will act on against a calendar or the source
    Citations References that look perfect and do not exist, or exist and say something else Open every link and confirm it says what the text claims
    Quotes Words attributed to people who said something adjacent, or nothing at all Verify against the transcript, word for word if it will be repeated

    How hard to check, and when

    The scan scales with where the writing is going. A Slack message to a colleague gets a glance at whichever of the five it contains. A figure heading into a board pack gets checked against the source before it goes anywhere, because a wrong number that gets forwarded is the most expensive kind of error.

    For the fuller version of that judgement, how to tell when ChatGPT is making it up covers how hard to check based on stakes, and how to fact-check AI output covers the methods for verifying a specific claim. The pre-send check is the everyday habit that sits in front of both.

    Make the tool do some of the work

    One line added to any request shifts part of the burden back where it belongs. Ask it to flag anything it is not certain of and to say what you should double-check, and you will often get an honest map of the soft spots. Treat that map as a starting point rather than a guarantee, because the tool has no reliable sense of its own errors, but it narrows the search and costs nothing to ask.

    The habit, in one sentence

    Before anything AI touched leaves your screen, find the numbers, names, dates, citations and quotes, and look at each one for as long as it deserves. That single pass is the difference between using these tools with a low hum of anxiety and using them with your judgement in charge. It also takes less time than rereading the first paragraph suspiciously ever did.

    Not sure where to start?

    The right tool makes the check shorter.

    The free finder tells you which AI to open for the task in front of you, in about 60 seconds, and the full "AI, sorted." reference lands in your inbox.

    Try the free finder →

    One question in, one answer out.


    Clair helps non-technical professionals know when to trust their AI, when to check it, and when to skip it.

    Common questions

    What should I check in AI writing before sending it?

    Five things: numbers, names, dates, citations and quotes. AI errors cluster in those spots because they are easy to invent plausibly and hard to notice at a glance, while the surrounding prose is usually fine. Scanning just those five against the source catches most of what could genuinely hurt you.

    How long should checking AI output take?

    Under a minute for a normal email and a few minutes for a report, provided you scan the five error-prone spots rather than rereading everything. Scale the effort to where the writing is going. Internal messages get a glance, and anything a reader will act on or forward gets a proper source check.

    Why does AI get numbers and citations wrong so often?

    Because it produces text by predicting what looks plausible rather than calculating or looking things up. A convincing figure or a perfectly formatted reference is easy to generate, and the result reads exactly like a correct one, which is why those details need checking even when the writing around them is flawless.

    Can I ask ChatGPT to check its own work?

    You can ask it to flag anything it is unsure of and to list what you should verify, and the answer is often a useful map of the soft spots. It is a starting point rather than a guarantee, because the tool has no reliable sense of which of its own claims are invented. The final pass stays yours.

    Do I need to check AI writing that stays internal?

    Lightly, yes. A message to a colleague still deserves a glance at any figure or date they might act on, because internal errors travel too. The full source-check effort belongs to anything client-facing, board-facing or public, where a wrong detail is expensive to walk back.

    The AI Starter Kit

    Set up ChatGPT and Claude properly. Once.

    The workflows, rules and habits that hand the boring recurring work to your AI and give you your evenings back.

    Get the Kit →