Healthcare data workflows
Convert 835 remittance to CSV, ready for posting.
Electronic remittance advice is dense: CLP claim payments, CAS adjustment groups, PLB provider-level adjustments. Describe the posting rows your AR workflow needs, and Data Shepherd writes reviewable scripts that map payments and adjustment codes into clean columns. Every production run executes the sealed script, with no PHI sent to a model.
Free plan available. No card required.
CLP*PT1001*1*1250.00*980.00*200.00*12*CK123456~ CAS*CO*45*70.00~ CAS*PR*1*200.00~
claim_id,billed,paid,patient_resp,adj_group,carc,adj_amount PT1001,1250.00,980.00,200.00,CO,45,70.00 PT1001,1250.00,980.00,200.00,PR,1,200.00
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 835 to CSV, answered.
Can it map CARC and RARC codes to our own categories?
Yes. Describe the mapping, or upload it as a reference table, and the generated script encodes it deterministically. The same 835 always produces the same posting rows, which is what your auditors want to hear.
Does the ERA file reach an AI model?
Not at run-time. The model writes the scripts during the build phase, from a de-identified sample or from the 835 spec alone. After that, runs are sealed: no network, no AI, no PHI to any model.
Can this run automatically for every ERA we receive?
Yes. Pull files from SFTP, FTP, S3, or Azure Blob on a schedule, or trigger the saved transformation by API and get a webhook when it completes. API access is included on Growth plans and above.
Working with claims or clinical data? See the dedicated healthcare page →
Related conversions
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.