GPT-4 powered internal tools
Hey HN, I’m Brad, one of the founders of Superblocks, a programmable cloud IDE for internal tools. This week we launched a deep integration with OpenAI, giving developers a tightly integrated app layer for GPT-4 powered internal tools (components, integrations, permissions, audit logging, SSO, observability etc.). Imagine you want to create an AI chat copilot for your support team that gives them answers to customer questions from your company’s corpus of information. With Superblocks, you can directly query a vector database like Pinecone or Weaviate, feed the results into OpenAI using our…
In plain words
Superblocks is a cloud IDE for building internal tools with integrated GPT-4 capabilities. Developers can create AI-powered applications by connecting vector databases, OpenAI APIs, and UI components, then deploy directly through git. The platform includes built-in features for permissions, audit logging, SSO, and observability, enabling teams to build tools like support chatbots that answer customer questions using company data.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I’m Brad, one of the founders of Superblocks, a programmable cloud IDE for internal tools. This week we launched a deep integration with OpenAI, giving developers a tightly integrated app layer for GPT-4 powered internal tools (components, integrations, permissions, audit logging, SSO, observability etc.). Imagine you want to create an AI chat copilot for your support team that gives them answers to customer questions from your company’s corpus of information. With Superblocks, you can directly query a vector database like Pinecone or Weaviate, feed the results into OpenAI using our integration with a custom prompt, hook the response from OpenAI to a Chat component in the UI and click deploy with git. Fun fact: We did this flow ourselves and demoed it at an OpenAI hackathon a few weeks ago! Our AI app layer helps developers access every OpenAI API: - use an intuitive UI on top of the API, eliminating the need to decipher API references and handle hyperparameters - prompt engineering fields that let you integrate any data using variables in code right within the Prompt and System Instruction fields - cost optimization via static or dynamic token limits, effectively managing API usage to ensure avoid runaway costs 5-min video: https://cdn.superblocks.com/videos/superblocks-build-ai-powe... Would love to hear feedback from the HN community! PS. We hear that lots of developers want to use private LLMs for their sensitive data so they don’t have to send to OpenAIs servers, this is something we’re working towards. We also plan to add more LLMs too
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2023
the whole month →
- G4
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
AI · 2023 · phind.com
