Prompt Engineering Studio - Build, test & deploy AI prompts across 1600+ models at scale

We are heavy users of Portkey at our startup, AdamX (adamx.ai). They fit our needs so well and have thought about the needs of a company like ours in almost all possible ways. Kudos on a great job done!

We built this to help AI teams ship prompts to production faster—from experimentation to deployment, all in one place.

Seeing companies manage millions of AI calls, optimize costs, and deploy seamlessly with Portkey has been incredible. Can’t wait for you all to try it!

Would love your thoughts & feedback—let’s push prompt engineering forward together!

👉 Check it out: https://prompt.new

Love how simple it is! Was looking for a prompt management and evaluation product.
If there was a feature to evaluate prompts/agents/tools on a small dataset, maybe with my custom metrics, that would be killer feature! When we write prompts, we have to run evaluation metrics every time and it's unclear how a single line change would influence UX.

Congratulations on launching Portkey's Prompt Engineering Studio! The ability to test across 1600+ AI models instantly while maintaining version control is incredibly valuable for teams trying to streamline their AI workflows. I particularly love the side-by-side model comparison feature - such a time-saver when optimizing prompts. The inclusion of mustache templating and reusable partials shows you truly understand the pain points of serious prompt engineers. Cutting development time by 75% is no small achievement! Brilliant work, Ayush and team!

nice! is this also open source?

Finally a prompt management tool, excited to give it a try

Thanks for the product and congrats on the launch!

Amazing product! This addresses a critical pain point in the AI workflow! The version control with labeled deployments is what's missing in most prompt engineering processes. As someone who constantly tweaks prompts for different use cases across product, business, and content, the ability to compare models side-by-side would save countless hours of guesswork.

Have you considered adding a prompt performance analytics feature that tracks which versions perform best across different contexts or user segments? That kind of data-driven insight could help teams standardize on proven patterns rather than relying on individual intuition.

Cool, I want to build agent to trading..

Awesome product and awesome team! It's always pleasure to use your product - such sleek UI!