Build & deploy MVPs from text prompts with AI, GitHub & Vercel
Needs changesWhat this workflow does
This AI workflow has 52 nodes and runs manually, when you click “Execute workflow” (plus 2 other triggers). Along the way it connects OpenAI Chat Model, GitHub and HTTP Request.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 2 other triggers).
- Code: runs custom JavaScript code
- Parse Input (Code): runs custom JavaScript code
- Chat Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (create_mvp); memory: Window Buffer Memory
- Generate From MVP Template (HTTP Request): calls an HTTP API
- Respond to Webhook: sends the response back to the webhook caller
- Variables (Code): runs custom JavaScript code
- Images to generate (Code): runs custom JavaScript code
- TDD Code Maker (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (get_file, get_image); output parser: Structured Output Code
- Generate Image (HTTP Request): calls an HTTP API
- Parse Output (Code): runs custom JavaScript code
…plus 30 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
2 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- AI Agent v1 (old agent modes) in Chat Agent (v1.6), TDD Code Maker (v1.8), Code Reviewer (v1.8)…: replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- HTTP Request Tool (legacy) in get_image: replace with HTTP Request node connected to the AI Agent's Tool input.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Chat Agent (v1.6), TDD Code Maker (v1.8), Code Reviewer (v1.8), Vercel Fixer (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
| HTTP Request Tool (legacy) get_image | HTTP Request node connected to the AI Agent's Tool input |
Nodes used (17)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Respond to Webhook
n8n-nodes-base.respondToWebhook - HTTP Request
n8n-nodes-base.httpRequest - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Code
n8n-nodes-base.code - Manual Trigger
n8n-nodes-base.manualTrigger - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Github Tool
n8n-nodes-base.githubTool - GitHub
n8n-nodes-base.github - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - Wait
n8n-nodes-base.wait - Merge
n8n-nodes-base.merge - If
n8n-nodes-base.if
From the author
⚡ Instant MVP Builder Idea, Build, and Deploy — in Minutes, with AI by Varritech Technologies --- 🏗️ What Is It? Instant MVP Builder is a plug-and-play n8n workflow that takes a plain-English app idea and turns it into a fully deployed web application —…