Portkey is a fantastic tool for any product that relies a lot on LLMs. It's great for creating automatic failovers and custom LLM routing based on variables we can send from the app.

Insanely fast AI gateway that helps power our LLM calls and observability.

Model proxy on serveless infrastructure.

👋 Hey Product Hunt! I’m Ayush, Co-Founder and CTO of Portkey AI We're very excited to introduce Portkey's Prompt Engineering Studio on Product Hunt After seeing teams struggle with inconsistent prompt performance and scattered tooling, we built the solution prompt engineers have been waiting for. Today we're launching the world's most advanced prompt engineering toolkit at prompts.new 🚀 Why we built this: Working with AI models requires precision in prompting, but existing solutions leave teams guessing with slow, manual processes and no version control. What makes our Portkey’s Prompt Studio special: - Powerful playground with side-by-side model comparison - Test across 1600+ AI models instantly - Version control with labeled deployments - Collaborative prompt libraries - Mustache templating and reusable partials - A-powered prompt optimization - Native support for LangGraph, CrewAI and other agent frameworksI Our platform helps teams craft, optimize, and deploy AI prompts 75% faster, from experimentation to production. We've put a lot care into building Portkey, and we really hope you like the product ! Check it out at prompts.new and let us know what you think! P.S. we call the IDE for Prompt Engineers

@ayush_garg_xyz Portkey’s Prompt Studio solves so many pain points like side-by-side model comparison, version control, and AI-powered optimization. Congrats on the launch

@ayush_garg_xyz Do you support APIs for data import as part of the prompt eval process?

@ayush_garg_xyz Finally, a proper toolkit for prompt engineers! Working with AI models has always felt a bit like trial and error, so having a dedicated studio with version control and real testing tools is a game-changer. Love the focus on collaboration too

@ayush_garg_xyz @jontronic Hey Jonathan, no that is not supported at the moment - we are building a better Evals feature on top of this now.

This looks amazing @vrv18 and @ayush_garg_xyz ! Love how Portkey streamlines prompt engineering with powerful comparisons and collaboration.

How does your version control system handle prompt iterations? Can teams see performance changes over time and easily roll back to the best-performing versions?

@ayush_garg_xyz @harkirat_singh3777 Thank you Harkirat! We don't have a polished evals product right now - you can run tests on prompts with our API but not in the UI. However, of course all prompt iterations are versioned and you can rollback, use any of the versions easily.

Very excited to launch Portkey's Prompt Engineering Studio today. We have helped hundreds of companies to move their complex prompting workflows to Portkey and radically supercharge their iteration and deployment times.

There is one company that manages publications across 700 websites through Portkey's prompt platform -and this is just the tip of the iceberg!

Please check it out and tell us if you have feedback!

Just head to https://prompt.new to experience this

Portkey Prompt Engineering Studio

Build, Test & Deploy AI Prompts across 1600+ models at scale

Do you use Portkey Prompt Engineering Studio?

Review Portkey Prompt Engineering Studio?

Maker reviews of Portkey Prompt Engineering Studio

Reviews of Portkey Prompt Engineering Studio