Example processhealthcareNCQA

Provider credentialing automation software

An example of provider credentialing as a governed process: agents do the 7 steps, and a person signs 2 gates before anything irreversible happens. Download it, import it into your workspace, and adapt it to your systems.

Download example · JSONImport into Minctrl →

minctrl.process/v1 · hash 66089e1ebdd0…ed90

The graph7 agent steps2 human gatessigns: Credentialing committee (MSO)

Provider-credentialing autopilot

Credentialing is months of repetitive primary-source verification, and a negligent-credentialing miss is direct liability — every clinician is re-verified by every payer. Licenses, education and history are primary-source verified and payer enrollments submitted straight-through; the committee signs the privileging decision and every adverse finding.

The governed flow · branches, parallel work & a human on the irreversible step
discrepancy / missing data — reworkclean or adverse finding to ratify
Start
agent · low risk
Collect the provider profile from CAQH and intake documents (education, licensure, DEA, work history, malpractice history, liability insurance, peer references per NCQA); validate completeness before proceeding
parallel · fan-out / join
Fan out independent primary-source checks
agent · low risk
Primary-source verify licenses, DEA and education with state boards, education institutions, and DEA registration
agent · low risk
Primary-source verify malpractice and work history via NPDB (National Practitioner Data Bank) and direct employer verification
agent · low risk
Screen OIG LEIE, SAM.gov, state Medicaid exclusion lists, OFAC SDN (Office of Foreign Assets Control Specially Designated Nationals), and NPDB (National Practitioner Data Bank) for malpractice history and sanctions (Joint Commission MS.01.01; NCQA Accreditation 2025-2026)
agent · medium risk
Join check results, produce discrepancy list and practitioner risk profile, and reconcile adverse findings before committee review (NCQA, Joint Commission gap-reconciliation requirement)
decision
Verification clean or adverse / discrepant?
gate · human sign-off
Credentialing committee (composed of active medical staff members per Joint Commission MS.02.01) reviews all verification materials, signs the privileging decision and every adverse finding, and documents rationale; practitioner notified of decision within SLAsigns: Credentialing committee (MSO) chair — active medical staff members per Joint Commission MS.02.01
gate · human sign-off
MSO lead verifies eligibility and authorizes submission of credentialing package to payers (Medicare PECOS, Medicaid, commercial) — distinct from privileging approval; this is the payer-enrollment authorization gatesigns: Medical Staff Office (MSO) lead or Credentialing coordinator
agent · high riskirreversible
Submit the payer enrollments (Medicare PECOS, state Medicaid, commercial insurers)
agent · low risk
Run continuous exclusion monitoring (monthly OIG, SAM, OFAC, state board, NPDB, license-expiration checks per NCQA 2025-2026) and trigger recredentialing cycle every 2–3 years per payer requirement (CMS FTCA deeming: 2-year cycle)
Done
low riskmedium riskhigh riskbranch / reworkgate · human sign-off
What it is modelled on

Granting or denying clinical privileges is a peer-review decision with patient-safety and legal weight, so the credentialing committee or medical director signs off before a provider is approved or denied.

RuleWhat it requires
NCQA credentialing standardsCredentialing relies on primary-source verification (PSV) of license, board certification, education/training, DEA and work history, within NCQA's look-back and timeliness expectations.
Primary-source verificationQualifications must be confirmed directly with the issuing source (e.g. state board, ABMS, NPDB) rather than from a copy the applicant provides.
NPDB / OIG-SAM sanctions checksThe National Practitioner Data Bank and OIG/SAM exclusion lists are checked so an excluded or sanctioned provider is not credentialed.
Credentialing committee / peer reviewThe approval to grant or deny privileges is a peer-review decision made by a credentialing committee or medical director, not clerical staff.

A summary for orientation, not legal advice.

Use this example
01

Download the file

A minctrl.process/v1 document: the graph and the hash of the process it becomes.

02

Import it in Processes

Import into Minctrl opens this example in your workspace; one click stores it as your first version. Import JSON does the same with the file, and a file changed after download is refused.

03

Connect your systems

Every connector starts in shadow: steps run, nothing leaves Minctrl until you configure a connector and switch it live.

04

Adapt it

Change signers, time limits and steps on the canvas. Each save is a new version; a running case stays on the version it started with.

Questions
How does the provider-credentialing example handle NCQA primary-source verification?

The example models primary-source verification: license, board certification, education, DEA and work history are confirmed with the issuing source, and each verification is timestamped and logged with a tamper-evident audit hash. Whether your program meets NCQA standards depends on your policies, your sources and your own accreditation review. Minctrl holds no certification, and this is not legal advice.

How are excluded or sanctioned providers caught?

The AI agent screens the NPDB and OIG/SAM exclusion lists as part of the file. A hit is escalated rather than auto-cleared, so an excluded or sanctioned provider cannot slip through to a privileges decision.

Who actually approves or denies privileges?

The credentialing committee or medical director. Granting or denying clinical privileges is a peer-review decision with patient-safety and legal weight, so it parks at a human sign-off gate; the AI assembles and verifies the file, a person makes the call, and the rationale is recorded.

More examples