Automate new patient record entry
Registration and intake re-keying — demographics from a referral, a form, or an existing structured source entered into the EMR or PMS — demonstrated once by your team, compiled, and replayed per patient with the fields as parameters.
This is a workflow shape, not a canned connector: you compile it from a recording of your own team in your own applications. The execution and verification mechanics it relies on are proven on the linked reference templates.
Runs on
Your clinic’s own EMR or practice management system, from a recording of your team entering one record. The write-verification mechanics are proven on OpenEMR, the open-source EMR, where a compiled note write is confirmed against the patient record itself — and a fault that paints “Saved” on screen while dropping the write is caught and halted.
The demonstrated steps
- 1Open the new-patient or registration form in your EMR or PMS
- 2Enter the demographic fields — each one a parameter, substituted per patient at replay
- 3Enter coverage or referral details as demonstrated
- 4Save the record
Parameters: the demographic and coverage fields your team demonstrated — one parameter each — recorded values are the defaults; every replay can override them.
How the outcome is verified
Write-shaped steps are auto-classified as irreversible at compile time, which arms the low-confidence refusal: the program halts rather than saving into ambiguity. lint reports any step that acts without an identity check before you deploy, and certify can refuse the bundle under a strict policy. Where your EMR exposes a database, API, or export, the save is bound to an effect contract and confirmed against the record — the OpenEMR reference demonstrates exactly this, including catching a silent dropped write behind a “Saved” screen.
- irreversible-write classification and refusal arming
- lint coverage gate before deploy
- effect contract on the saved record where a system of record exists
Proven on
Try it from the command line
The compiler and runtime are open source and MIT licensed. Healthy runs are local and make no model calls.
pip install openadapt-flowInstall the open-source compiler and runtime.
openadapt-flow record --url https://your.app --out recOpen a headed browser on your app and demonstrate the workflow once; Ctrl-C to finish.
openadapt-flow compile rec --out bundle --name my-taskCompile the recording into a deterministic bundle with auto-classified risk per step.
openadapt-flow lint bundle && openadapt-flow certify bundle --policy permissiveSurface coverage gaps, then gate the bundle against a policy before it ever deploys.
openadapt-flow replay bundle --url https://your.app --param name=valueReplay against your app; recorded values are defaults and --param overrides them.
Put this workflow into production
Bring your version of this workflow and the record that proves its outcome. We'll map the deployment, verification, shadow run, and supervised rollout.