In theory , yes we could, but would it yield "good enough" results for a "testing" agent- Probably not. The LLM here is actually not just responsible for tool calling, its also doing other intricate things such as planning the next steps based on the input feature file, and generating the browser/API automation code. In our experiments we found that OpenAI 4o performs best, followed by Haiku or Grok.

Deepak I would suggest give it a try check this https://github.com/test-zeus-ai/testzeus-hercules/blob/main/...

I also suggest that you join our slack group so that we can discuss this in one on one and try to solve this for your case. https://join.slack.com/t/testzeuscommunityhq/shared_invite/z...