Wirewalk Instituteof AI
hls-275 Intermediate Available

Building AI into Practice Management and EHR Workflows

For practice IT leads, PM/EHR analysts, operations managers and compliance officers who connect, test and govern AI in ambulatory practices, one queue at a time.

Level
Intermediate
Study time
16 hours
Lessons
18 in 6 modules
Exam
20 questions

About this course

This is a builder's course for the ambulatory practice. One composite organization runs through it: Ashcombe Medical Group, 16 providers in family medicine and orthopedics across three Pennsylvania sites, whose partners approved a $720,000 AI plan on a managing partner's promise of $1.2 million a year in net benefit. Each module solves one of Ashcombe's problems and ends in a Decision Lab: deciding how four vendors connect to the PM and EHR (a certified FHIR API reads but cannot book; a shared login is the fast option and the wrong one); answering every call with an AI voice agent and scoring its log by caller language; extracting faxed referrals without filing them to the wrong patient, and routing 42 CFR Part 2 pages; choosing between an EHR-native and a third-party ambient scribe on the practice's own notes, in a state that requires every party's consent to record; keeping eligibility summaries, AI code suggestions and the post-scribe E/M shift honest; and running an AI inventory that finds the features nobody switched on knowingly.

Real products (athenahealth, Epic, eClinicalWorks, NextGen, ModMed, Microsoft Dragon Copilot, Assort Health, Phreesia, Tennr and others) are compared the way practices choose them in October 2026, with every vendor figure treated as a claim, and the randomized trials of ambient scribes used as the evidence. The controls are taught where they bite: HIPAA business associate, minimum-necessary, audit-control and risk-analysis rules; the certified API criterion and information blocking; the TCPA and the FCC's ruling on AI voices; Section 1557 language access and decision-support duties; 42 CFR Part 2; No Surprises Act good-faith estimates; ICD-10-CM, NCCI, the 60-day overpayment rule and the False Claims Act. The capstone is a go/no-go package for the partners, including the value bridge that separates cost removed, measured collections and capacity. Claims, denials and prior authorization in depth are in hls-255. Status is as of October 2026; the course is educational, not legal or coding advice, and no vendor endorses it.

What you will be able to do

  • Evaluate how an AI tool should connect to a practice's PM and EHR given what it must read and write, and specify least-privilege scopes, an attributable service account, audit logging and business associate terms
  • Evaluate whether an AI patient-access agent is ready to go live and to place outbound calls, against gates set in advance and scored by caller language, with each call type's TCPA consent basis set by its purpose
  • Build and test a document-AI design for faxed referrals with source-page links, field-level accuracy, a patient-match gate, 42 CFR Part 2 routing and an exception queue sized to its staff
  • Evaluate ambient documentation and portal-message triage tools on the practice's own notes and messages against gates fixed before results are seen, weighing contract terms and cost, and design the per-visit recording-consent workflow an all-party-consent state requires
  • Analyze revenue-cycle AI output for integrity risk and evaluate the review gate and overpayment response each finding requires under that payer's rules
  • Evaluate a practice AI program's value by separating cost removed, measured incremental collections and capacity, netting run and review cost, and treating vendor ROI figures as claims
  • Build and run a practice AI inventory and quarterly review covering EHR-native features and staff chatbot use, with owner, BAA, risk-analysis entry, Section 1557 screen, a monitoring metric and a retirement trigger
  • Create a go/no-go package for one practice AI use case that partners can act on, with evidence against preset gates, consent controls, monitoring, rollback and an honest value line

Syllabus

6 modules · 18 lessons · about 16 hours

Module 1: Four Vendors, One Chart: Deciding How AI Connects to the PM and EHR

Setting a connection standard, a minimum-necessary scope and the contract terms before any AI vendor touches the practice's data.
3 lessons
  1. Mapping Ashcombe's AI Surface: Where Schedules, Charts, Faxes and Claims Actually Live
  2. What a Certified FHIR API Will and Will Not Do: Reading Patient and Coverage, and Why Booking Needs a Proprietary API
  3. Service Accounts, Audit Trails and the Contract: Write-Back Design, BAAs and Information Blocking
  • Decision Lab · 12 minThe Vendor Wants a LoginDecide how an AI voice agent connects to the practice's PM/EHR, what data it gets and on what contract terms, then live with those choices when the vendor's subprocessor has an incident.

Module 2: Answering Every Call: An AI Voice Agent for Scheduling and Reminders

Specifying, scoring and launching a phone agent that books into the PM, escalates anything clinical and places outbound calls only with the right consent.
3 lessons
  1. Writing the Booking and Escalation Specification for 3,600 Calls a Week
  2. Scoring the Pilot Call Log: Correct Bookings, Missed Red Flags, Wrong-Patient Writes and Silent Failures
  3. Outbound Reminders and Waitlist Backfill: AI-Voice Consent Under the TCPA and an Equity Check on No-Show Overbooking
  • Decision Lab · 14 minGo-Live Week on the PhonesLaunch an AI voice agent into a busy call center: choose its scope, its red-flag protocol and how you will measure it, respond when the first week goes wrong, then decide which outbound calls it may make.

Module 3: The Fax Pile: Referral Intake Without Wrong-Patient Indexing

Turning faxed referral packets into verified, source-linked work items with an audited match gate and correct handling of Part 2 pages.
3 lessons
  1. Extracting 30 Synthetic Referral Packets: Schema, Source-Page Links and Field-Level Accuracy
  2. Patient Matching and Completeness Rules: Why Every Auto-Match Is Audited During the Pilot
  3. Part 2 Pages, Exception Queues and Who Works Them: Routing Sensitive Records and Staffing the Human Step
  • Decision Lab · 12 minNine Percent Never ScheduledChoose a referral-intake tool, decide how packets are matched to charts, handle a packet with Part 2 records, and decide when the staffing saving is real.

Module 4: Notes After Midnight: Ambient Documentation and the In-Basket

Choosing, consenting and auditing an ambient scribe on the practice's own notes, and triaging portal messages with tested red-flag routing.
3 lessons
  1. Native or Third-Party Scribe: A Bake-Off on Ashcombe's Own Notes, Audio Terms and Cost
  2. Recording Consent and Note QA in an All-Party-Consent State: A Rubric for Fabricated Findings and Missed Medication Changes
  3. Portal Message Triage and Drafted Replies: Red-Flag Sensitivity, Clinician Review and Machine Translation
  • Decision Lab · 14 minThe Scribe Pilot and the Resignation LettersChoose and roll out an ambient scribe with two resignations pending, decide how to get recording consent in an all-party-consent state, and respond when a fabricated finding and a billing spike arrive the same week.

Module 5: Revenue Integrity: Eligibility, Coding Suggestions and the Value Bridge

Keeping eligibility, coding and the post-scribe E/M shift honest, and building the value bridge the partners can trust.
3 lessons
  1. Eligibility Summaries That Never Invent a Benefit: 271 Responses, Insurance Selection and Good-Faith Estimate Timing
  2. E/M Drift After the Scribe: Review Gates for AI Code Suggestions and the False Claims Act
  3. The Value Bridge: Separating Cost Removed, Measured Collections and Capacity From the Vendors' ROI Decks
  • Decision Lab · 13 minThe Level-Five SpikeCut eligibility denials without letting a tool silently change accounts, decide how AI code suggestions are reviewed after an E/M spike, respond to a payer's records request, and write your line of the partners' slide.

Module 6: Running It: The Practice AI Inventory, Monitoring and the Partners' Decision

Finding every AI use, giving each an owner and a metric, retiring what does not earn its keep, and taking a go/no-go package to the partners.
3 lessons
  1. Building the AI Inventory: Native Features Nobody Decided On, Missing BAAs, Shadow Chatbots and Section 92.210 Screens
  2. The Quarterly AI Review: One Metric per Use Case, Audit-Log Checks Under 164.312(b) and Retirement Triggers
  3. Capstone: The Go/No-Go Package for the June Partners' Meeting
  • Decision Lab · 12 minThe Quarterly ReviewBuild the practice's AI inventory, deal with staff chatbot use, respond when an EHR release switches on a patient-facing AI feature by default, and apply a retirement trigger you wrote months ago.
  • Capstone simulation · 35 minAshcombe's AI YearRun Ashcombe's AI program from approval to the partners' renewal vote: sequence the projects, set the integration standard, launch the phones, face the coding spike, choose what number to show, and make the recommendation.

Exam and certificate

The exam unlocks once you have completed every lesson and played each Decision Lab to an ending. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by athenahealth, Epic, eClinicalWorks (healow Sunoh.ai), NextGen Healthcare, ModMed, Microsoft, Nabla, Assort Health, Phreesia, or Tennr. Product and company names are trademarks of their respective owners.

More in AI in Health and Life Sciences

All 21 courses in this track
hls-001 Free intro Available

AI in Health and Life Sciences: A Practical Introduction

A free introduction built on eight healthcare jobs: auditing an ambient-scribe note, answering a portal message from an AI draft, acting on a sepsis alert, reading a triage-flagged CT worklist, reviewing a prior-authorization request, checking AI-suggested codes, and triaging drug and device safety reports. Each lesson shows where AI helps, where it must not decide, and the rule that governs that exact task.

3 h · 8 lessons Free intro
hls-110 Basic Available

AI for Nursing and Care Team Professionals

Use a synthetic US care-team case to check AI drafts against source records, preserve nursing judgment and coordinate accountable follow-up. Build a practical evidence packet without patient data or a model account.

10 h · 18 lessons See price at checkout
hls-210 Intermediate Available

Building and Deploying AI in Healthcare Delivery

Evaluate clinical AI through a fictional US health-system case: procurement, source audits, silent validation, monitoring, privacy and integration. Produce a bounded evidence portfolio using synthetic materials and branching decisions.

16 h · 24 lessons See price at checkout