Logistics and retail EDI
Convert EDI 850 purchase orders to JSON, your systems understand.
A big trading partner sends 850s. Your systems speak JSON. The usual answers are an expensive EDI platform or weeks of custom parsing. Describe your target schema instead, or upload the partner spec, and Data Shepherd writes transparent scripts that map BEG, PO1, and N1 loops into the exact JSON your API expects. Run them by API inside your pipeline, with no data sent to a model.
Free plan available. No card required.
BEG*00*SA*PO4510**20260605~ N1*ST*ACME DISTRIBUTION*92*DC-12~ PO1*1*48*EA*9.25**VP*SKU-100~ PO1*2*12*CA*31.50**VP*SKU-205~
{
"po_number": "PO4510",
"ship_to": "DC-12",
"lines": [
{ "line": 1, "sku": "SKU-100", "qty": 48, "uom": "EA", "price": 9.25 },
{ "line": 2, "sku": "SKU-205", "qty": 12, "uom": "CA", "price": 31.5 }
]
}How it works
From a messy file to a tested pipeline, in minutes.
Describe it and bring your spec
Plain English, plus a sample, a spec, or a data dictionary. Cannot share data at all? Build from the spec alone.
AI writes transparent scripts
You get reviewable, versioned Python, never a black box. Inspect every line and preview the output on a sample.
Run it anywhere, with no AI
Trigger by API, schedule, or click, or pull from SFTP, S3, or Azure Blob. The sealed script does the work; nothing goes to a model.
The AI builds it. A sealed script runs it.
Most AI data tools push records through a language model on every run. We keep the model in the build phase only, so production never sends your data to a model.
Full data-flow table and sub-processor list in our Trust Center →
Common questions
EDI 850 to JSON, answered.
Does it handle EDIFACT as well as X12?
Yes. ORDERS and other EDIFACT documents work the same way: describe the mapping or upload the message guide, review the generated scripts, and run them on real files.
How does this fit into an automated pipeline?
Trigger the saved transformation by API with the file in the request, poll the job, and download the JSON, or let a webhook tell your system the output is ready. Scheduled SFTP and S3 pickups cover partners who drop files instead.
Is our order data processed by an AI on each run?
No. The model writes the scripts once, during build, from a sample or the partner spec. Every production run executes the sealed script in an isolated sandbox: deterministic, repeatable, and with nothing sent to a model.
Describe it once. Run it forever.
Build the transformation on a sample in minutes, review the scripts line by line, and let the sealed runs handle every file after that.