Automation library · AI assistants

Build & deploy MVPs from text prompts with GitHub and Vercel

Started by someone opening a chat with it, and works across GitHub. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 52 steps, 3 branches, 3 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
52 stepsLarge: read it before trusting it with anything live
3Branches: places the flow splits
3Loops or waits
1Service it connects to

The flow

Starts it 5Model 12Logic 22Service 13

The steps in the order they run, from what starts it.

  1. 1When chat message receivedChat triggerStarts it
  2. 2OpenAI Chat ModelLm Chat Open AiModel
  3. 3Window Buffer MemoryMemory Buffer WindowModel
  4. 4create_mvpTool WorkflowModel
  5. 5create_mvp triggerExecute Workflow triggerStarts it
  6. 6When clicking ‘Test workflow’Manual triggerStarts it
  7. 7test inputCodeLogic
  8. 8OpenAI Chat Model1Lm Chat Open AiModel
  9. 9Structured Output CodeOutput Parser StructuredModel
  10. 10get_fileGithub ToolService
  11. 11HTTP Request1Http RequestService
  12. 12get_imageTool Http RequestModel
  13. 13CodeCodeLogic
  14. 14OpenAI Chat Model2Lm Chat Open AiModel
  15. 15Code2CodeLogic
  16. 16OpenAI Chat Model3Lm Chat Open AiModel
  17. 17Fetch Latest DeploymentHttp RequestService
  18. 18Chat AgentAgentModel
  19. 19Parse InputCodeLogic
  20. 20Code3CodeLogic
  21. 21test pos-creaetionCodeLogic
  22. 22TDD Code MakerAgentModel
  23. 23Code ReviewerAgentModel
  24. 24Vercel FixerAgentModel
  25. 25Code1CodeLogic
  26. 26Respond to WebhookRespond To WebhookStarts it
  27. 27Generate From MVP TemplateHttp RequestService
  28. 28Parse OutputCodeLogic
  29. 29Parse Output1CodeLogic
  30. 30Parse Code-FixCodeLogic
  31. 31VariablesCodeLogic
  32. 32Images to generateCodeLogic
  33. 33GitHubGithubService
  34. 34Loop-CodeCodeLogic
  35. 35GitHub Commit FixGithubService
  36. 36Generate ImageHttp RequestService
  37. 37Vercel DeployHttp RequestService
  38. 38MergeMergeLogic
  39. 39Wait2WaitLogic
  40. 40If IfLogic
  41. 41WaitWaitLogic
  42. 42Vercel Deploy1Http RequestService
  43. 43HTTP RequestHttp RequestService
  44. 44Vercel CheckHttp RequestService
  45. 45Wait1WaitLogic
  46. 46If 200IfLogic
  47. 47If READYIfLogic
  48. 48GH Upload FileGithubService
  49. 49return URLCodeLogic
  50. 50Vercel LogsHttp RequestService
  51. 51Respond to Webhook1Respond To WebhookStarts it
  52. 52Error LogsCodeLogic

How it's built

Starts on
Someone opening a chat with it
Steps
52, with 3 branches, 3 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
GitHub
Model
OpenAI
Retrieval
Answers are drawn from documents you supply, not from the model alone

Questions

What does it need to run?

An n8n account, plus your own GitHub account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 52 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 52 steps before you point it at anything that matters.