ListenFoxBot is the reader behind the knowledge base. It visits a website only when a ListenFox customer adds that site as a knowledge source, or asks us to read it again. It never crawls the web on its own.
What it reads
- robots.txt first, then the sitemap, then up to 25 pages that say the most about the business: prices, services, hours, policies, FAQ, about and contact.
- Public pages only, on the same site. It sends no login, follows no links to other sites and skips anything that points at a private network.
- One page at a time, at least half a second apart, and slower when robots.txt sets a crawl delay (up to 2 seconds).
The text it collects goes into that customer’s knowledge base, so their team can check what was said on calls against what the website says. It isn’t shared with anyone else or used to train AI models.
How to block it
It identifies itself as “ListenFoxBot/1.0” and obeys robots.txt. It answers to both ListenFoxBot and its old name, CallIntelBot, so a rule written for either keeps working. To keep it off the whole site, add “User-agent: ListenFoxBot” followed by “Disallow: /”.
Questions or problemsEmail [email protected] with your domain and what you saw, and we’ll look into it.