Skip to main content
Build AI-powered features with a single prompt. Connect your OpenAI API key and describe what you want. Rocket handles all the API integration code automatically, so you can focus on defining what your AI features should do rather than writing boilerplate.You need:

What you can use it for

Add a conversational chatbot that answers user questions, provides recommendations, or guides users through workflows.Try this prompt:
Add an AI chat assistant to my app that answers questions about our product.
Use OpenAI GPT and store conversation history in Supabase.
Rocket creates: chat UI with message history, OpenAI API calls with context management, and conversation storage.
Let users generate blog posts, marketing copy, product descriptions, or social media content from simple prompts.Try this prompt:
Build a content generator where users enter a topic and tone,
then get a blog post draft powered by OpenAI.
Rocket creates: input form for topic and tone, OpenAI completion call, and formatted output display with copy-to-clipboard.
Upload documents or paste text and get concise summaries, key takeaways, or action items extracted automatically.Try this prompt:
Create a document summarizer where users paste text and get a
bullet-point summary and list of action items using OpenAI.
Rocket creates: text input area, OpenAI summarization call, and structured output with summary and action items.
Automate first-line support with a bot that answers FAQs, triages issues, and escalates complex requests.Try this prompt:
Build a customer support chatbot that answers common questions from a
knowledge base stored in Supabase. Escalate to a human if the bot cannot help.
Rocket creates: chat interface, OpenAI-powered response generation with knowledge base context, and escalation flow.

Get your OpenAI API key

Open the OpenAI dashboard to create or copy your API key.
Your API key gives you access to OpenAI’s GPT models. Keep it private and rotate it immediately if you believe it has been exposed.
Never paste your API key directly into Rocket chat. Always use the secure integration flow or the API key input in settings. If you believe your key has been exposed, rotate it immediately from the OpenAI Dashboard.

Detailed setup

Connect OpenAI to Rocket

There are two ways to connect OpenAI to Rocket:Method 1: Use Rocket Chat (fastest)
  • In any project, open the chat panel and type something like: Connect OpenAI to:
  • Add a GPT-powered chat assistant to my app.
  • Generate summaries of user-uploaded documents.
  • Rewrite user input with tone and clarity options.
  • You will see a popup appear where you can paste and save your API key instantly.
OpenAI integration popup in chatOpenAI integration popup in chat
Method 2: From your project settings
  • Open any project and go to Integrations.
Integrations tabIntegrations tab
  • Click the OpenAI card.
OpenAI integration cardOpenAI integration card
When you connect OpenAI from Project Settings, Rocket will not automatically create GPT features. After saving your key, describe what you want in chat and Rocket will build it for you.

Save your OpenAI API key

  • Paste your API key into the field.
  • Click Save to complete setup.
A green dot appears next to OpenAI in your integrations list when the connection is successful.

Update or disconnect

  • Click the OpenAI integration again.
  • Replace the existing key or click Remove to disconnect.
Remove OpenAI integrationRemove OpenAI integration

Prompt cookbook

Copy-paste these prompts after connecting OpenAI to build common AI features:
Use casePrompt
ChatbotAdd an AI chatbot to my app that answers user questions using OpenAI GPT.
Blog writerBuild a blog post generator where users enter a topic and get a full draft from OpenAI.
Email drafterCreate an email composer that generates professional emails from bullet points using GPT.
Code explainerAdd a code explainer tool where users paste code and get a plain-English explanation from OpenAI.
Content moderatorUse OpenAI to automatically flag inappropriate user-submitted content before it is published.
Quiz generatorBuild a quiz generator that creates multiple-choice questions from any topic using GPT.
Language translatorAdd a translation feature that converts user text between languages using OpenAI.
Sentiment analyzerAnalyze customer feedback sentiment using OpenAI and display results in a dashboard.
Meeting summarizerSummarize meeting notes into key decisions and action items using GPT.
Product description writerGenerate product descriptions from basic details like name, category, and features using OpenAI.

Tips and limitations

  • API key billing is separate. OpenAI charges based on usage (tokens processed). Monitor your spending in the OpenAI usage dashboard.
  • Rate limits apply. New OpenAI accounts have lower rate limits. If your app serves many users, check your rate limit tier and request an increase if needed.
  • Model selection. Rocket auto-selects the best available GPT model for your task. The latest models in the GPT-5 family offer significant improvements in reasoning, coding, and multimodal understanding over previous generations. You can specify a model preference in your prompt if needed.
  • Token costs vary by model. Longer prompts and responses cost more. Keep system prompts concise and set reasonable max token limits for responses.
  • OpenAI vs. Anthropic. GPT models excel at broad general-purpose tasks, function calling, and vision. Claude models are better suited for long-context analysis and tasks that benefit from more cautious, detailed responses.

What’s next?

Anthropic

Add Claude models for long-context analysis and detailed reasoning alongside GPT.

Gemini

Connect Google’s Gemini models for multimodal AI features.

Perplexity

Add real-time web search and up-to-date answers to your AI features.

Supabase

Store conversation history, user preferences, and AI-generated content in Supabase.