*New users get 50 credits* Simplify automating critique, reflection, and improvement, aka getting the model to 'think before it speaks', for far superior gen AI outputs. Choose from pre-built multi-agent templates or create your own with the help of Claude.
I built this app for myself because I was getting bored of having to hunt down my prompt templates and copy/paste them to take advantage of the chain-of-thought / critique / reflection / improvement boost from LLMs. It automates the multi-agent process as well as making it easy to add and refine prompt templates. Each agent is 'dedicated' to a task, e.g. accuracy verification, improvement suggestions, polishing off, and each one displays so you can see the AI 'showing its' working'. I use it constantly for tasks where I want the best results and I personally can't get enough of it. It's expensive ($0.75 for the best quality 4-agent run *** UPDATE following feedback, I've cut pricing by 33% so now the best quality run is $0.50) because it absolutely demolishes tokens, but for me it's a no brainer. Had a few people see it and basically demand I make it available publicly, so that's why it's here!
Congrats on the 50 credits! Now simplify automating critique, reflection, and improvement for superior AI outputs with pre-built or custom multi-agent templates using Claude.
I built this app for myself because I was getting bored of having to hunt down my prompt templates and copy/paste them to take advantage of the chain-of-thought / critique / reflection / improvement boost from LLMs. It automates the multi-agent process as well as making it easy to add and refine prompt templates. Each agent is 'dedicated' to a task, e.g. accuracy verification, improvement suggestions, polishing off, and each one displays so you can see the AI 'showing its' working'. I use it constantly for tasks where I want the best results and I personally can't get enough of it. It's expensive ($0.75 for the best quality 4-agent run *** UPDATE following feedback, I've cut pricing by 33% so now the best quality run is $0.50) because it absolutely demolishes tokens, but for me it's a no brainer. Had a few people see it and basically demand I make it available publicly, so that's why it's here!
*UPDATE! 33% off credit price, all new users get 50 free credits when they sign up*
This experience has been awesome, I've had 30 new users in the past day so I'm very glad I found about about Product Hunt! The in-app feedback after each task has been loud and clear: everybody agrees that the results from the final agent are superior, but most think the cost is too expensive. All new users now get 50 credits free when they sign up, and I've now set the prices to be $0.10 (from $0.15) per credit. Pricing is now:
-Steak-tier (4 agents, recommended when you want the best results): $0.50 / £0.39
-Ribs-tier (3 agents): $0.30 / £0.24
-Burger-tier (2 agents): $0.20 / £0.16
-Draft template with Claude: $0.10 / £0.08
Nice job on the launch! Combining automated critique with AI is a smart move. It would be interesting to see if there are any built-in analytics to track the improvements made by using these templates.
This approach to enhancing generative AI by adding a layer of thoughtful critique is very interesting. The ability to use or create templates seems like a great way to streamline the process.
This looks promising! The idea of automating critique and reflection for AI models could really improve their output. Looking forward to seeing how the pre-built templates and custom options perform in real-world use.
I’m excited to see how this tool enhances generative AI. Does it offer any features for tracking the effectiveness of the critiques and improvements made by the AI?
This tool sounds fascinating for automating critique and reflection. How flexible is the process for adapting the templates to different needs or industries?
Love the idea of using multiple agents to refine LLM outputs. The different quality levels are a nice touch.
What a useful tool for improving AI interactions! The option to use pre-built templates or customize your own is a smart touch. Great work on this!
Sounds cool! Automating how AI thinks and improves before it speaks could really up the game. Excited to see how it works out!
Are the prompt templates built for a specific domain or are they generalized?
Congratulations on the launch!
This is a fantastic initiative, @leemager! The way you've simplified the automation of critique and reflection in generative AI could be a game-changer for anyone looking to enhance their output. Love the idea of having dedicated agents for specific tasks like accuracy verification and improvement suggestions; it really mimics a more interactive and thoughtful creative process.
I can see how this would seriously save time for many Makers and help elevate the quality of content generated. Plus, the transparency of seeing the AI 'show its working' is such a clever touch—definitely aligns well with the principles of iterative improvement! While the cost may seem high at first glance, the ROI on quality results and enhanced efficiency might just make it worthwhile for a lot of users. Excited to see more feedback once it's live!
I appreciate the effort you have put into making this app. The idea of having dedicated agents for different tasks sounds incredibly useful.
Hi Lee and the team!
Huge congratulations on launching your app! 🎉
Simplifying the automation of critique, reflection, and improvement for generative AI is a brilliant idea. The pre-built multi-agent templates and the ability to create custom ones with Claude Sonnet 3.5 are fantastic features. It's great to see how you've streamlined the process of refining prompt templates and enhancing the output quality.
Thank you for making such a valuable tool available to the public. Looking forward to seeing the impact it has on the AI community!
Best,
Konstantinos Choutos
Honestly, while this seems like it might save time, the cost is pretty steep for what it does, I'm not sure everyone will be willing to pay that much just for a more automated prompt process, plus the whole token thing sounds like it could get really expensive real fast, so feels kinda risky to me
