Copy.ai: Web Search, Page Scraping and Site Access
Copy.ai is an AI platform for sales, marketing and operations teams. Its Chat can search the internet, and its workflows can search the web and scrape web pages on demand or on a schedule. Copy.ai documents no user agent, IP range or robots.txt token for these requests, so you cannot target it by name.
Who makes Copy.ai
The Copy.ai website calls it a GTM AI platform. GTM means go-to-market, the work of sales and marketing teams. In October 2025, Fullcast announced the acquisition of Copy.ai. Fullcast makes software that automates go-to-market and revenue operations. The Copy.ai help center is now at support.fullcast.com/copy-ai.
Web search in Chat
Chat is the assistant in Copy.ai. Users choose a language model for each chat. The help article Getting Started With Chat says that Chat can search the internet in real time. When it does, it cites the online sources with links at the end of its message. The article does not name the search engine that Chat uses.
Web search and scraping in workflows
A workflow is a series of automated steps in Copy.ai. Two workflow actions use the web:
| Action | What it does, according to Copy.ai |
|---|---|
| Perform Internet Search | Runs a web search. It returns the URL, title and snippet of each result, up to 10 pages of results. |
| Scrape Webpage | Gets the text or the full HTML of one URL. A workflow can run it on demand or on a schedule. |
The Scrape Webpage article lists uses such as change detection for prices and product descriptions, SEO metadata extraction, review extraction and page summaries. It also says that the URL must be public and not behind a login. Pages that build their text with scripts can be impossible to scrape in full.
Allow or block Copy.ai
The Copy.ai help articles do not name a user agent, a robots.txt token or IP ranges for searches or scrapes. They also do not say whether the Scrape Webpage action follows robots.txt. So no documented rule targets Copy.ai alone.
Pages behind a login are out of reach, because the action works only with public URLs. If you see scraping traffic that you do not want, block it in your web server or firewall. Use the user agent and the IP addresses that your logs show.