GTM teams often struggle with fragmented data and manual tasks that slow down their outreach efforts. As Kareem Amin, co-founder and CEO of Clay, explains, "All tools before LLMs tried to automate what Sales Development Representatives (SDRs) or Business Development Representatives (BDRs) were doing in terms of research but they would get stuck. Data providers could provide a maximum of 100 data points per company. Engineers were building scrapers but that was finicky and time-consuming.”

Clay recognized that the key to empowering these teams was to aggregate data from multiple sources and automate time-consuming research tasks. They chose to integrate GPT‑4 because it had the best language model on the market and its API documentation had plenty of examples showing tool calling in action.

Clay built Claygent, an AI web scraper that uses GPT‑4 to understand and extract highly specific information from websites. To make Claygent as efficient as possible, Clay optimizes the number of tokens passed to GPT‑4 and chooses the appropriate model for each use case.