Weavel automates prompt engineering, delivering the best prompts 50x faster than humans. Simply input your prompt and receive optimized prompts with highest accuracy. Boost your prompt's accuracy by an average 20% in less than 5 minutes.
@mwseibel thank you for the hunt!
Hi Product Hunt makers 👋
I'm Andrew, co-founder of Weavel. I'm excited to introduce our prompt engineering automation platform for LLM apps @junpark_314 @hyunjiejung @tobykim .
As foundation models get smarter, more and more tasks can be solved by prompting LLMs in the right way. But going from 80% to 100% is hard and requires days, even weeks of prompt engineering. We are building Weavel to help makers ship fast and with confidence, by automating the hassle of manual trial-and-error of prompt engineering with LLM-based algorithms.
Weavel is designed for developers, data scientists, and AI enthusiasts who need to maximize efficiency and accuracy in their LLM apps. Weavel delivers the prompts with highest accuracy, 50x times faster than humans - optimized prompts surpasses DSPy-optimized prompts by 4% and CoT by 7%.
We are rethinking prompt engineering to make the process fast, accurate, and reliable. Here's how we help the engineering cycle:
💾 Dataset curation:
- Add one line of code to log LLM calls in your product. We automatically curate datasets from the logs - user representative dataset and out-of-distribution dataset for edge cases.
- Enrich your dataset with LLM call logs from production.
🧪 Prompt optimization:
- From your base prompt and provided dataset, Ape (our AI prompt engineer) will iterate on diverse prompts, and find the mixture of instructions and few shot examples with the highest scores.
- It takes only 4 minutes, and improves accuracy by an average 20% 🚀
We'd love to hear your thoughts and feedback. Thanks for checking out Weavel!
PS1: The code that powers Ape (AI prompt engineer) is open source at https://github.com/weavel-ai/Ape
PS2: We are working on a prompt engineering playground that also automatically curates datasets from the runs - will launch soon! Real soon!!
I like the focus on real-world data and continuous improvement. It seems like a smart approach to keep things optimized and relevant.
I’m curious about how user feedback is incorporated in real-time. While automation is great, it’s important to ensure that human input isn’t lost in the process.
It seems like a huge help for managing LLM applications. The tool's ability to auto generate evaluation code and continuously optimize prompts is a major plus.
The prompt engineering automation looks impressive. It's great to see how efficiently it handles prompt optimization and evaluations.
Great! Congratulations! Many systems optimise assistant, RAG, and other frequent use situations, but few optimise AI Agent instructions and prompts.
The automated evaluation and prompt generation are standout features here. This tool seems like it will make a big difference in how efficiently LLM applications are handled. I appreciate the innovative approach to prompt engineering with this tool.
Really impressed with how this tool automates complex tasks like prompt origination and evaluation. It’s clear that a lot of thought went into its development. It’s a great addition to the AI toolset!
I have used other prompt optimization tools, but this one’s speed and accuracy improvements are particularly impressive. It seems like a big leap forward in prompt engineering.
A colleague of mine who works extensively with AI prompts would really benefit from this. I’m definitely going to let them know about this tool. it seems like a perfect fit for their needs.
The performance metrics for this tool are fantastic. The way it automates prompt engineering and evaluations can definitely save time and enhance accuracy. Its ability to integrate CI/CD and handle data effortlessly is impressive
Thanks for creating a tool that makes prompt engineering so much faster and more accurate. This could really streamline the workflow for many AI practitioners.
I appreciate the emphasis on automating evaluations and integration with existing tools. It makes the process more streamlined and less manual. However, I wonder about the learning curve for new users who might not be familiar with this kind of setup.
Great launch! The features for prompt optimization are promising looking forward to future updates and enhancements.
That's great! Congratulations! Many solutions aim to optimize prompts for assistant, RAG, and other typical use cases, but fewer offer help with optimizing AI Agent instructions and prompts. Do you have any opportunities to use it for the Agent?
Speed and accuracy are crucial how does it adapt changes in language models to keep prompts effective
The dataset curation feature is intrguing how does it ensure the quality of the data collected from users logo
Looks good! 🔥 Love the way Weavel speeds up prompt engineering! The dataset curation feature sounds super useful. I can see it saving lots of hours for LLM devs. How do you plan to handle edge cases in prompts? Keep it up! 👍
