Overview
Integration with the Make platform for advanced workflow automation
Note
The Make integration allows you to connect meinGPT with Make workflows and orchestrate in both directions.
Two Core No-Code Interaction Modes
1. No-code tool -> meinGPT
No-code tools like Make, n8n, or Power Automate can call meinGPT to:
- execute assistants
- start workflows
- process and route AI outputs in broader automations
Running an assistant with a file attachment
To trigger an assistant run via API and pass along a file, your no-code tool calls POST /assistants/v1/{assistantId}/run as a multipart/form-data request:
messages- the message(s) as a JSON stringfiles- the file(s) as binary data (max. 50MB per file, max. 10 files)
See the Assistants API reference for full details and an example.
meinGPT makes the attached files available to the assistant in two ways:
- Full inline content: for text-based formats (JSON, CSV, plain text, XML, YAML), the entire file content is inlined into the assistant's context - regardless of file size.
- Document Engine lookup: the assistant is also told the file is stored in Document Engine and can be fetched with a tool. This fallback only works if the assistant has Code Sandbox enabled as a tool.
Note
For assistants that process large file attachments through automations like Make, n8n, or Power Automate, enable Code Sandbox on the assistant even if it isn't asked to run code. This gives the model a working fallback tool in case the inlined content ever isn't enough.
Non-text formats (images, PDFs, Office documents) follow the same native-file handling described in Code Sandbox - attach Code Sandbox to the assistant if the automation needs to process these formats.
2. meinGPT -> No-code tool
No-code platforms can provide tools/actions that are then used by assistants, for example to:
- trigger downstream actions in third-party systems
- orchestrate business processes
- expose no-code capabilities as assistant-usable tool calls
Returning downloadable files from assistants in Make
When Make calls a meinGPT assistant through the API, the assistant can return downloadable files if it uses Code Sandbox file tools. This is separate from the Make MCP setup where an assistant calls Make as a tool.
To use file downloads in a Make scenario:
- Enable Code Sandbox on the assistant.
- In the prompt or Make module input, explicitly ask the assistant to create a downloadable file, for example: "Analyze the attached Excel file and return a downloadable CSV summary."
- Call
POST /api/assistants/v1/{assistantId}/runfrom Make, optionally with uploadedfiles. - Read the response field
files. If the assistant exported a sandbox file, the first file is available atfiles[0].downloadUrl. - Map
files[0].downloadUrlinto Make's HTTP Get a file module, or directly into a downstream Make field that accepts a file URL.
If the assistant only answers with text, files is returned as an empty array. meinGPT does not create a document from the final text automatically; the assistant must export a file through Code Sandbox.