Conrad Chu

@heycesr I'm curious, how do you handle batch evaluations that run into the hundreds of test cases? Do you have built in throttling/delay when running in batch? We find that we typically run into rate limits when evaluating prompts on large datasets,

At Headline, we have our investment processes deeply embedded in Attio via their APIs. The new Automations AI feature really helps us shelve a number of integrations we made with GPT-4 that we cobbled with Google Sheets. Kudos to the Nic and the team and a very polished feature out of the gate!