Shark Puddle

Got a Startup Idea? Pitch it to the Sharks! At Shark-Puddle.com, you can bring your business or startup idea and pitch it to our panel of AI-generated Puddle Sharks—each with a unique personality. Whether you’re seeking validation, advice, or a reality check, we’ve got a Shark for you: • Skeptical Shark: Known for its sharp critiques, this Shark doesn’t hold back. (Fair warning, it can be a bit mean!) • Supportive Shark: Feeling vulnerable? Supportive Shark offers you a confidence boost and an ego massage. • Constructive Shark: Ready for real feedback? Constructive Shark gives you actionable insights to improve your pitch. We built Shark-Puddle.com in just a few days to put our platform, LLMasaService.io, through its paces. What is LLMasaService.io? LLMasaService.io is a robust API and tool suite designed to make it easy for app developers to integrate AI-based features into their applications. Whether you’re building a new product or enhancing an existing one, LLMasaService has you covered with essential features like: • Routing between Multiple LLMs and Providers: Automatically switch between different AI models (public or private) based on cost, quality, or response time. • Multi-Turn Conversations with Streaming: Enable complex, back-and-forth interactions with smooth, real-time updates. • Prompt Safety: Keep your AI prompts clean and free from toxic content. • Cost Containment: Manage and control expenses by setting budgetary limits. • Customer Token Management: Effortlessly handle user data and tokens with security in mind. • Security and PII Redaction: Ensure sensitive data is protected with built-in redaction features. • Geographic Routing: Optimize AI model selection based on your user’s location for faster response times or compliance (like for EU customers) • High Response Quality: Deliver clear, coherent, and helpful responses every time. Do Us a Favor! Test your craziest ideas at Shark-Puddle.com and see how the Sharks respond. And if you’re an app developer looking to integrate AI into your own applications, explore LLMasaService.io to learn how we can help you streamline the process and scale your project. Let the (Puddle) Sharks put your ideas to the test!

What if my business idea is another AI panel of puddle sharks? 😜

Hello, Thank you for stopping by! I'm one of the technical team behind Shark-Puddle and LLMAsAService.io, and I'd like to share some details and requests with you in addition to what @indomitabelehef commented on earlier. If you have any questions about implementation ,just reply to me here. 1. Shark-Puddle is Open Source You can find the source code here: https://github.com/Predictabilit... 2. Built with Next.js on AWS Amplify (Gen 2) The application is a Next.js app hosted on AWS Amplify's second generation. 3. All Streaming LLM Services via LLMAsAService.io In the source code, you'll notice there are no direct calls to OpenAI, Anthropic, or Google Gemini. Instead, all streaming LLM services are centrally managed through LLMAsAService.io, which handles: a) Failover Management Provides failover to one of the eight defined vendors and models. b) Customer Token Tracking and Allowance We monitor token usage and allowances (we appreciate your support, but it's currently on my credit card). c) Safety Guardrails for PII and Toxic Requests Feel free to test this by attempting to input "bad" things and see how the system responds. d) Prompt Complexity Routing We analyze your prompts and route them to either "simple/fast" or "slow/high-power" models. Tip: if you click "Try Again," we use a stronger model. 4. Streaming Responses and Backend Testing You might notice streaming responses, sometimes multiple at once. We're aiming to push our backend to its limits, so please give it a good workout! Our component, `llmasaservice-client` (available on NPM), includes our `useLLM` hook, which supports all these features and has a callback when a response is finally complete. ------------------------------- Calling LLM Implementation: ------------------------------- The only code used to call LLMs is the following. Step 1: Create the hook instance (configures the LLM service with a customer so we can keep track of token usage): import { useLLM } from "llmasaservice-client"; const { response, idle, send } = useLLM({ project_id: process.env.NEXT_PUBLIC_PROJECT_ID, customer: { customer_id: idea?.email ?? "", customer_name: idea?.email ?? "", }, }); Step 2: Make a streaming call. Use `send` to send the prompt, and `response` is what is displayed: const handleSubmit = () =>; { const prompt = `Summarize the following idea in one or two sentences Idea: "${ideaText}."`; send(prompt); }; And that's it! We manage the keys, services, monitoring, security, and customer onboarding—all from a control panel. Nothing in the code needs to change—even when OpenAI adds a new model, like the o1 model a few days before launch :) Adding it was easy for us (it's in the premium model group!). So, while you're having fun and getting solid feedback on business ideas, please take a look at how we built it and share any suggestions on how we can improve. Best regards, Troy

A great idea for demonstrating how AI can easily be added to any product.... A fun and useful app in it's own right :)