TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Prompt Engineering Studio – Toolkit for deploying AI prompts at scale

2 点作者 retrovrv2 个月前
Hey HN! Long-time reader, occasional commenter here. I wanted to share something my team and I have been building to solve our own frustrations.<p>We&#x27;ve all seen the explosion of prompt engineering tools lately. While playing around in playgrounds is fun, when we tried to take our AI prompts to production, we hit a wall. I&#x27;m guessing many of you have experienced similar pain points.<p>We kept hitting questions nobody seemed to be answering: How do you version control thousands of prompts? How do you handle multiple production deployments? How do you scale from prototype to millions of requests per day? How do you collaborate across hundreds of engineers without stepping on each other&#x27;s toes?<p>So we built Portkey&#x27;s Prompt Engineering Studio - a complete toolkit designed specifically for productionizing AI prompts across 1600+ models.<p>Some technical details that make our approach different:<p>- High-performance infrastructure: We&#x27;ve deployed prompts as large as 500,000 tokens with production-level latency - Git-like version control with instant rollbacks for prompt deployments - Mustache templating system for parameterization and reusable snippets - Publish&#x2F;release flow with proper dev&#x2F;staging&#x2F;prod environments - Real-time analytics tracking prompt performance, latency, and token usage - Native integrations with Langchain, Llamaindex, and Promptfoo<p>The scaling capabilities have enabled some impressive use cases:<p>- A content company running 500+ prompts across 700+ websites - A tech firm that cut deployment times from 3 days to near-instant - Education platforms with hundreds of non-technical creators building AI workflows<p>Our platform has processed hundreds of millions of prompt completion requests already, with over 10,000 prompts deployed to production environments.<p>We think the HN community will especially appreciate our approach to bringing software engineering best practices to AI development!<p>You can try it yourself at prompt.new<p>I&#x27;d genuinely love to hear how others in the community are handling these challenges, what you think of our approach, or any other feedback you might have. This community has been invaluable in shaping how we think about developer tools.

2 条评论

veilgen2 个月前
This looks like a powerful step toward making prompt engineering more scalable and production-ready. The version control approach, along with staging environments and real-time analytics, seems particularly useful for teams handling high-volume AI workloads.<p>One question: How do you handle prompt drift over time? As models evolve, prompt effectiveness can degrade—do you provide any automated testing or monitoring to detect when a deployed prompt needs adjustment?<p>Looking forward to exploring Portkey’s capabilities.
评论 #43397423 未加载
JTyQZSnP3cQGa8B2 个月前
&gt; How do you version control thousands of prompts?<p>Kill me now.<p>&gt; How do you collaborate across hundreds of engineers<p>What do you mean by that? This only targets a few big companies.<p>&gt; A tech firm that cut deployment times from 3 days to near-instant<p>That&#x27;s a process and maybe CI issue, I don&#x27;t see how AI would improve any of that but I&#x27;ll be gladly proven wrong.<p>&gt; You can try it yourself at prompt.new<p>All I see is a login page from another company. Don&#x27;t you have a web site with all those serious prompting you do?
评论 #43397376 未加载