Try VEP free

Improved

Your AI employee's claims are checked against what it did

When your AI employee tells you in its chat that it did something or that it will do something later, that statement is checked against what it actually did. A check that is busy now runs again a few minutes later instead of leaving the reply unchecked.

  • AI employees
  • Reliability

What you get

  • In your chat with your AI employee, a statement that it did something, such as sending an email, or that it will do something later, such as reminding you, is checked against what it actually did while answering: the actions it took, the tasks it set up and the mail it handled.
  • If a statement does not hold, a short note is added at the end of the reply, in the language of the reply, saying what it can and cannot confirm. When a promised follow-up is not set up, the note says so and offers to set it up.
  • The check runs right after the reply arrives, so a note can appear a little later.
  • When the check is busy or cannot finish, it runs again a few minutes later instead of leaving the reply unchecked. Before, a busy check could leave a reply unchecked.
  • Each check now gets more time, the same for short and long answers, and each thing it reads about what your AI employee did is whole rather than shortened, so a cut-down record no longer misleads it.
  • A check that runs later uses the record of your AI employee's tasks saved when the reply was written, so a change made afterwards does not make a kept promise look broken or a broken one look kept. If that record is missing, it leaves promises unjudged rather than risk a wrong note.

More updates

  1. Fixed

    Reports on team tasks are checked against the tasks themselves

    When your AI employees work as a team, they hand tasks to each other. Until now, the check of what an AI employee says could not see those tasks, so a correct report that it took or closed a task could get a note saying it could not be confirmed. Now the check reads the tasks themselves.

  2. Fixed

    Learning from your chats now waits instead of being dropped

    Your AI employee learns from what you ask it and what it answers in your chat with it. When that cannot happen right away, because of a usage limit, a sign-in problem, an outage or a busy moment, the question and answer now wait and are tried again instead of being dropped, so your AI employee learns them once the problem is gone.

  3. Fixed

    Something learned late no longer replaces your correction

    Your AI employee sometimes learns from your chat later than it happened, for example after waiting out a usage limit or an outage. Now what you said last in the chat stays current: an older statement learned late is kept in its history and no longer replaces a newer correction.

  4. Improved

    Big spreadsheets read faster and more safely

    Spreadsheets you give your AI employee are read faster and more reliably.