OpenAdaptOpenAdapt learns a task, then runs it as a program
A person or an agent shows OpenAdapt a data-entry task. It becomes a program that repeats the same steps with new details. At first, a person approves every entry. Once a workflow proves itself, OpenAdapt only asks about problems. After each save, it reads the record back, and says so when it can't. When something doesn't match, it stops.
Updated 2026-10-18
What you get
- A program for one task in one system, built with you and tested on test records.
- A plain result for every entry: Done and checked, Stopped before saving, Check the record, or Finished, not checked.
- A receipt for each entry that ends Done and checked (the result and each check it ran, without patient details), and a full run record of every entry on your computer.
- Upkeep: a tested fix when your system changes, approved by your staff before use.
Built for production: signed admissions, qualification against your normal and fault cases, a record check on every save, local or in your VPC, and a BAA on Enterprise. We qualify it on your system before it touches a real record. How it works · Pricing
The parts, for engineers
The open-source engine is openadapt-flow: it records a demonstration, compiles it into a program and runs it with checks of the record before typing and after saving. It also runs a program over a worklist, fills a workflow's inputs from a referral PDF, fax image or email, turns an AI agent's successful run into a program, and lets your AI agent hand it entries to make and check. The rest of the platform builds on it.
See it on your process
Bring one task your team types every day. We'll tell you whether it fits, and what a test on your own system would cover.