Healthcare data workflows
Convert EDI 837 claims to CSV, without PHI touching an AI.
An 837 is a hierarchical X12 document, and most teams flatten it by hand or with brittle one-off code. Describe the rows you need in plain English, with your companion guide if you have one. Data Shepherd writes a transparent Python script that parses the loops and segments into clean columns. You review it line by line, and every run after that executes the sealed script with no AI involved.
Free plan available. No card required.
CLM*PT1001*1250.00***11:B:1*Y*A*Y*Y~ NM1*QC*1*DOE*JANE****MI*MRN000123~ SV1*HC:99213*125.00*UN*1***1~ SV1*HC:85025*45.00*UN*1***2~
claim_id,patient_id,cpt,charge,place_of_service PT1001,MRN000123,99213,125.00,11 PT1001,MRN000123,85025,45.00,11
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 837 to CSV, answered.
Does my claims file go through an AI model?
Not at run-time. The model is involved once, while the scripts are written, and it sees only what you choose to share: a de-identified sample, or just your companion guide or layout spec. Production runs execute the sealed script in an isolated sandbox with no network and no AI.
Can it handle both 837P and 837I?
Yes. You describe the loops and fields you need, professional or institutional, and the generated script parses them accordingly. The live preview shows the output on a sample before you run a full file.
How do repeating service lines come out in CSV?
You decide the shape: one row per service line with the claim fields repeated, or one row per claim with aggregated line values. Describe what you want and review the script that produces it.
Working with claims or clinical data? See the dedicated healthcare page →
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.