You’re not alone AI enrichments can slow down when Clay’s OpenAI queue is busy or when there’s a large batch of rows running at once. If your table normally runs in a few hours but now takes 10+, it’s likely temporary performance throttling on Clay’s backend.
You did the right thing by contacting support — they usually prioritize these cases quickly. In the meantime, you can try:
Duplicating the table and running a smaller batch (e.g., 500–1,000 rows).
Switching the model to GPT-4o mini or Claude 3.5 Sonnet if available — they tend to process faster.
Checking that your “Run If” conditions aren’t rerunning all previous rows unnecessarily.
If you want, I can help you check what’s likely causing the bottleneck in your specific setup — want to share which AI column or model you’re using?
