Weavel - Automate prompt engineering & get best prompts 50x faster

@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!!

Congrats on the launch, @aschung01 and the team! Automating prompt engineering can truly streamline the AI development process. I’m intrigued by the 20% accuracy boost—how does the platform ensure consistency across different datasets and models? Can't wait to see the playground feature in action!

Great! Congratulations! Many systems optimise assistant, RAG, and other frequent use situations, but few optimise AI Agent instructions and prompts.

This sounds really interesting! How does Weavel handle different languages or contexts for prompts? I'm curious if it's as effective across various domains or just limited to specific ones. Any insights on the user experience too?

Hey Andrew, How does the platform adapt to different LLM models, or is it focused on specific ones? Congrats on the launch!

This is a fantastic solution, @aschung01! Automating the tedious trial-and-error of prompt engineering could significantly speed up development. I’m especially interested in the dataset curation feature—how does it ensure the datasets are comprehensive and representative? Are there any plans to integrate more advanced features like real-time optimization or interactive tweaking?

Nice project @aschung01 and the team. Good luck with launch today!

This is a game changer! Weavel's automation for prompt engineering is impressive. Getting optimized prompts 50x faster is huge for productivity. Excited to see how this boosts accuracy and efficiency! Upvoted!

Comment Deleted

This is a really innovative solution, Andrew! Automating prompt engineering can save so much time and effort for developers. The 20% boost in accuracy is impressive, especially with those benchmarks against DSPy and CoT. Excited to see how Weavel can change the landscape for LLM apps. Kudos to you and your team for tackling such a crucial challenge in AI! Looking forward to the playground launch as well! 💡

Congrats @Andrew, Weavel looks like a game-changer in prompt engineering automation. The ability to automatically curate datasets of production, and enhance prompt accuracy by 20% in just 4 minutes is impressive. How does Weavel handle edge cases in dataset curation, and what specific metrics do you use to measure prompt performance?

Congrats on the launch! 🎉 Will be trying this out..

Congrats! Will check it out!

Best of luck with the launch! Automating prompt engineering is a fantastic idea, and I hope it helps many people streamline their workflows.

Good luck with the launch! It’s great to see a tool that can optimize prompts so quickly and effectively.

I’m wishing you all the best with this launch! It’s exciting to see how much time this tool can save developers.

The dataset curation feature is intrguing how does it ensure the quality of the data collected from users logo

definitely is promising/ do you have a community feature so everyone shares?

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?

The prompt engineering automation looks impressive. It's great to see how efficiently it handles prompt optimization and evaluations.