👋 Hi Product Hunt community! I’m Petr, co-founder and CEO of Langtail. We launched Langtail into public beta six months ago, and today we're excited to introduce Langtail 1.0 — a major step forward for building and testing AI apps. Taking an LLM app from an exciting demo to a dependable product is hard work. Over the past year, we’ve heard a lot about the challenges: LLMs are unpredictable, prompt iteration is a mess, and traditional testing tools fall short. Langtail 1.0 is our answer to these problems. It’s all about control, consistency, and confidence. Here’s what’s new: 🧪 Spreadsheet-Like Testing Interface: Drop your test cases in with ease, get instant feedback, and iterate quickly—like using Google Sheets, but for LLMs. 🔧 Hosted Tools: Langtail now handles function execution directly within the app, making prototyping easier by running tools without needing to mock responses or set up external infrastructure. 🛠️ Test Configurations: Compare different models side-by-side with just a few clicks, making it easy to see which one works best for your app. 🔗 Shareable AI Apps: Create shareable links to let anyone interact with your LLM—no sign-up required. Perfect for getting feedback or showcasing to colleagues. 🤖 Assistants: Introducing stateful assistants that handle memory and conversation history automatically, reducing the overhead of prompt management. These assistants can be tested, deployed as APIs, and even integrated across models with ease. ✨ Magic Buttons: We've added Magic Buttons to streamline workflows—automatically generate new test cases, adjust prompts, or implement improvements with a click. 🔥 AI Firewall: Real-time protection for your app. Stop prompt injections, denial of service attacks, and data leaks before they happen. 🌟 New Redesign & Light Theme: A complete redesign to improve usability, including a new light theme for those who prefer it. 🚀 Self-Hosting Available: Full control over your data, entirely on your infrastructure. Perfect for larger teams and enterprises. See more here https://langtail.com/blog/introd.... We’d love for you to give it a try and let us know what you think!

Looks super interesting! The logs are a nice touch, but what got me truly hooked is the cost analytics to keep LLM cost under control. Well done!

We’ve been using Langtail for a while at Deepnote. It’s helped us improve the reliability of our text-to-SQL system, and let us quickly prototype potential new behaviors for Deepnote AI. The Langtail team’s been super responsive to our feedback, which is great. Excited for what comes next!

Very nice! I have used it already to polish some of my boring system prompts, so I am looking forward to your progress! Open-source when? I would find it useful (at least to have some parts) self/hosted to integrate into CI/CD pipelines <3 Good luck!

Nice product, solving a real pain point! How does integrate with a product in production? Is there a sdk that we put in our codebase in certain segments and it listens the outputs?

Nice work, everyone! I really like the Spreadsheet-Like Testing Interface. It's very cool.

Glad to launch Langtail 1.0 on Product Hunt! One feature I’ve been working hard on is AI Assistants. It allows you to create custom assistants for different tasks and share them publicly—it’s simple to set up and ready to use. Looking forward to hearing your thoughts and seeing how it works for you!

Cool - looking forward to trying it out!

Congrats on the launch, guys 🎉🙌🏼 Langtail looks awesome, great UI! And it's always nice to see & hear Ryan 😄

We've been using Langtail at Deepnote for over a year now and would highly recommend it to any team serious about shipping AI products. The ROI has been clear from day one!

Yo, I'm the Product Manager behind Langtail. Thanks for the support so far. We've put a lot into this, really curious what you think of the new serverless function handling and AI assistant support. Check it out and let us know what you think! 🚀

Saurav from Apify here, congratulations on the launch. Looking forward to see the growth <3

Congrats on the launch! A big fan of spreadsheets so this hits just right :)

I’m one of the engineers on this project! Very excited to launch 1.0 after months of working on it. Our team has thought deeply (and talked to other companies much larger than us) about testing LLM-based apps. AMA.

Hey! I'm Tomas, co-founder and CTO of Langtail. 🚀 Quick update on our LLM provider support! During beta launch, we only supported OpenAI. Now with Langtail 1.0, we've added all major providers: - Anthropic Claude - Google Gemini (includes video support!) - Open Source models like LLama on Groq - And more! 🤖 This means more flexibility for you to test and compare different models in one place. Looking forward to hearing your thoughts! 💬

Awesome product you've built with Langtail, @petrbrzek and Team! I think this has great potential as building apps based on LLMs is not that trivial. I hope this launch boosts you!

Testing AI powered apps is really challenging. Excited to try this!

Favourite thing: How the cost to performance metrics. Absolute Banger

Huge congrats to the Langtail team on the 1.0 launch! I love how you've simplified LLM testing with a spreadsheet-like interface - who wouldn't want to tame AI complexity with a familiar feel? Quick question: Can you share an example of a surprising insight or optimization that a beta tester achieved using Langtail's analytics?

I think this could be a valuable tool, but the pricing model will be crucial for many users.