Automate insurance eligibility and coverage checks
For agencies, billers, and back-office teams: the repeated carrier-portal lookup — member or policy number in, coverage answer out — demonstrated once, compiled into a deterministic program, and replayed per case with halting instead of silent wrong answers.
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 organization’s own carrier portals and systems, from a recording of your team performing one check. No canned carrier connectors are implied — each workflow is compiled from your demonstration and qualified against your applications. The underlying mechanics — policy resolution against a live insurance system and database-verified writes — are proven on the openIMIS reference.
The demonstrated steps
- 1Sign in to the carrier portal — credentials are secret parameters, redacted from the recording and injected from the environment at replay
- 2Look up the member or policy — the per-case parameters
- 3Open the coverage, benefits, or status view
- 4Read the fields your process needs
- 5Record the answer into your system of record or worksheet
Parameters: member or policy number · any per-case identifiers your team demonstrated — recorded values are the defaults; every replay can override them.
How the outcome is verified
The compiled program verifies target identity before every consequential action — the wrong policyholder on screen is a halt, not a wrong answer written downstream. Anything the demonstration never covered (an unexpected modal, a changed portal state) halts and asks. Where the answer is written into a system with a database, API, or file export, that write is bound to an effect contract and confirmed against the system of record.
- pre-action target-identity checks
- halt on undemonstrated state
- effect contract on the downstream write 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.