This article is always guaranteed to answer the common question of "why did my agent say that?" CloseBot prompts are 100% open source. This makes troubleshooting things like this easy.

Learn exactly how the bot decides what to say by clicking the reasoning section for the message in question within the contact conversation. This reasoning overview gives you a quick rundown of what part of the job flow the agent was working on when it came up with an answer. See accomplished objectives and objectives needed here.

If the quick response reasoning shown above didn't provide clarity, click to See full log and click the top-most AI Log to see exactly what the prompting was that led to the AI response. This prompt is dynamically generated by us at CloseBot based on uploaded resources we found from your knowledge library, your settings for the job flow, persona settings and many other factors. Dynamically generating these prompts is what we do best and you can see exactly what we generate here.

Here are some of the most common areas people mess up that causes undesired behavior. Check these out to make sure you're not making a no-no update to your objectives.

If your agent is messing up on an objective, start by taking a look at your short description. This is the most important field for your objectives and you should follow the best practices defined HERE.

Any time you ask WHY your agent said something, you'll be directed to this article. This is the exact method support will use if you ask them why your agent said something as well. We even have a t-shirt in our store with the CloseBot Classic article link... that's how popular this article is 🤣

Get familiar with clicking to see the response reasoning... it's not scary!