1:36Healthcare
Agentic Healthcare Eligibility Framework
Four agents scan insurance cards, verify coverage, resolve exceptions and flag prior authorizations, with staff working in Workato GO or Teams.
- Workato
- Microsoft Azure
- Epic
- Microsoft Teams
AI Agent · Healthcare · Revenue cycle
Eligibility Verification
Confirm coverage and patient responsibility before the visit, not after the denial.
Validated POC
Tested against the Optum eligibility API using X12 270/271 transactions.
Outcome
Checks insurance eligibility and benefits for upcoming appointments and flags gaps to front-desk staff before the patient arrives.
- Intended user
- Patient access and front-desk teams in provider organisations.
- Status
- Validated POC
- Inputs
- Upcoming appointment schedule
- Patient demographics and insurance member ID
- Payer eligibility endpoint (X12 270/271)
Workflow
Today, and with the agent.
Current workflow
- Staff log in to payer portals one patient at a time
- Coverage problems surface after the visit, as denials
- Rework lands on billing teams weeks later
Assisted workflow
- Eligibility is checked for the whole schedule ahead of time
- Staff start the day with a short list of exceptions
- Coverage questions are resolved with the patient before the visit
Capabilities
What the agent does.
- Sends eligibility requests for scheduled visits
- Reads active coverage, plan and benefit details from the response
- Flags missing, inactive or mismatched coverage for staff review
- Summarises results in Microsoft Copilot Studio for the desk team
What it does not do
- Change coverage or demographic data in the EHR without staff approval
- Give patients a final bill or a guaranteed cost
- Decide whether a visit goes ahead
Architecture
How information moves.
Inputs are read with scoped access. The agent prepares the work. A person decides before anything is written back.
Inputs
Upcoming appointment schedule
Agent
Sends eligibility requests for scheduled visits
Human decision
Coverage exception
Systems
Microsoft Copilot Studio, Optum eligibility API
Human oversight
Where a person decides.
These decision points are part of the design, not an optional setting.
Coverage exception
Patient access staff
A person decides how to resolve inactive or mismatched coverage with the patient.
Record update
Registration lead
Any change to the patient record is approved by staff, not written by the agent.
Security, evaluation and deployment
Security controls
- Least-privilege payer credentials held in a secrets store
- No protected health information retained in agent logs
- Every request and response recorded in an audit trail
Evaluation measures
- Share of scheduled visits checked before arrival
- Exceptions confirmed as real by staff
- Eligibility-related denials, measured against a baseline
Deployment options
- Client Microsoft 365 tenant
- Client cloud account with managed service
Technologies
Built with, and connects to.
Tested means used in the proof of concept. Designed for means the connection is designed but not yet tested with live data.
Integration
- Optum eligibility APITested
AI
- Microsoft Copilot StudioTested
Standards
- X12 270/271Tested
Demo
See Eligibility Verification work.
From the POC Library
1:36FAQ
Common questions.
Which payers does it support?
The proof of concept was tested against the Optum eligibility API. Other payers and clearinghouses are scoped during a pilot.
Does it work with our EHR?
The agent reads the schedule and writes nothing back without approval. EHR connection is agreed during pilot scoping.
Request an Agent Pilot
Pilot Eligibility Verification on your workflow.
Tell us about your systems and timeline. We will scope a pilot with agreed measures and the human decision points above.
More agents
Related agents.
Validated POC
AI Agent
ScheduleXM
- Problem
- Requests arrive by phone, portal and email.
- How it works
- An appointment scheduling agent that understands a booking request, finds suitable slots and prepares the booking for confirmation.
- Industry fit
- Healthcare · Patient access
- athenahealth
- Large language model
Validated POC
AI Agent
RefillXM
- Problem
- Refill requests arrive in several queues.
- How it works
- Reads incoming prescription refill requests, gathers the information a clinician needs and queues each request for review.
- Industry fit
- Healthcare · Clinical operations
- Large language model