All activity
Juan Pablo Isazaleft a comment
Back in December, the handit team and us tried this methodology. They ingested around 40k calls to a given prompt and then handit A/B tested the prompt with an improved version. We tracked the performance and it went from 40% to 70%. Amazing work!!! keep it up!
Handit.aiThe open-source engine that auto-improves your AI agents
PeakU offers a real-time dashboard that tracks each developer’s performance. This empowers CTOs, product owners, and tech leads to make informed decisions quickly.
PeakU Tech KPIsMeasure devs productivity and code quality with AI insights