Billing
ConversationalCPT/ICD-10 coding, E/M level, underpayment risk
Your AI staff
40 agents. 4 pods. Zero new headcount.
Every agent below is in the live registry. 19 are conversational — you talk to them in the AI Assistant — and 21 work inside specific workflows. Every agent drafts or proposes; a person approves. Each reports confidence on its output, routes anything uncertain to a human, and can be switched off with one switch — autonomy is yours to dial.
Meet your agents live →POD 1 · 10 AGENTS
Revenue pod
Denial Prevention
ConversationalPredict and prevent claim denials with CARC/RARC fixes
Revenue Cycle
ConversationalTriage claims lifecycle — clean, appeal, write-off
Prior Auth
ConversationalDraft PA packages with clinical justification
Financial Forecast
Conversational14-day and 90-day cash flow forecasting
Denial Appeal Drafter
In workflowSignature-workflow payer-appeal letters for denied claims
Underpayment Recovery
In workflowPayer dispute letters for claims paid below contract
Charge Capture Proposer
In workflowDraft charges + line items for completed encounters
Charge Capture Critic
In workflowAudit charge-capture drafts for missed add-on codes
Financial Counselor
In workflowPre-visit cost estimates as front-desk scripts
POD 2 · 8 AGENTS
Patient engagement pod
Smart Scheduling
ConversationalNo-show risk prediction and demand forecasting
Patient Outreach
ConversationalTCPA-compliant SMS/email outreach and recall sequences
Campaign Intelligence
ConversationalMulti-segment campaigns with A/B arms and ROI estimates
Intake Intelligence
ConversationalVerify demographics, insurance, and missing intake fields
Patient LTV
ConversationalLifetime value scoring and churn risk segmentation
Referral Manager
ConversationalDraft complete specialist referral packages
Outreach Targeting
In workflowDaily recall worklist ranking
FM Adherence Coach
Early accessDrafts supportive check-ins and replies about a signed functional-medicine protocol
POD 3 · 15 AGENTS
Clinical pod
Scribe
ConversationalFind today's appointment and open real ambient charting
Note Intelligence
ConversationalSummarize written notes and telehealth call recordings
Care Gap
ConversationalOpen HEDIS/MIPS gaps and closure recommendations
Risk Scoring
ConversationalChronic burden, HCC suspects, and polypharmacy flags
Compliance
ConversationalAudit documentation vs billed E/M codes
Compliance Monitor
ConversationalDetect anomalous PHI access and suspicious patterns
Quality / MIPS
ConversationalMIPS/QPP composite scoring and improvement planning
Staff Workflow
ConversationalProvider productivity, burnout scoring, staffing needs
Rx Assist
In workflowPre-prescribe safety checks and sig suggestions
Outcome Trends
In workflowInterpret PHQ-9/GAD-7 outcome-measure trends
Appointment Prep
In workflowPre-visit brief compressed into a 20-second read
Documentation Coder
In workflowPost-visit coding review: missed add-ons + time-banded CPT
Grounded Coder
In workflowTerm extraction for catalog-grounded ICD/CPT coding
FM Intake Summary
Early accessOrganises a submitted functional-medicine intake for clinician review
Cross-line Router
Early accessRoutes cross-line signals in functional-medicine records to the right team as tasks
POD 4 · 7 AGENTS
Platform pod
General Assistant
In workflowGeneral-purpose practice management assistant
Orchestrator
In workflowPlan-graph workflow orchestration across agents
Prompt Mutator
In workflowClosed-loop prompt-candidate generation meta-agent
Feedback Critique
In workflowDiagnose why an agent output was rejected
Reflection Critique
In workflowSelf-critique meta-agent for structured outputs
Review Reply
In workflowHIPAA-safe public replies to patient reviews
Review Insights
In workflowThemed sentiment analysis across patient reviews
Common questions
What practices ask about the agents
How many AI agents does MedOp have?
40 agents in the live registry, in 4 pods: Revenue 10, Patient engagement 8, Clinical 15 and Platform 7. 19 are conversational agents you can talk to in the AI Assistant; the other 21 work inside specific workflows as drafters, critics, coders and platform meta-agents. 3 of them work only in functional medicine, which is in early access, and are labelled "Early access". Agents that are switched off pending a review are not listed.
Do the agents make clinical decisions on their own?
No. Every agent drafts or proposes, and a person approves. Agents report a confidence score on their output and route anything uncertain to a human for review, and patient communication is draft-only by default. eRx changes specifically require TOTP-gated two-factor confirmation from a clinician — an agent cannot submit a prescription unsupervised.
Can I disable individual agents?
Yes. Every agent has its own kill switch, independent of the others in its pod. You can run Scribe and Grounded Coder while leaving Smart Scheduling or Review Reply off, and change that at any time.
How does the ICD-10 coding agent avoid hallucinated codes?
Grounded Coder retrieves from a verified 98,186-code ICD-10-CM catalog rather than generating codes from a language model. A code is always selected from the catalog, never invented, and every selection is logged in the audit trail.
What happens when an agent is not confident in its output?
Low-confidence outputs are routed to a human reviewer instead of being auto-submitted. This applies across every pod — a denial-prevention flag, a coding suggestion, or a drafted note can all be held for review rather than pushed through automatically.
See them work on your schedule
20 minutes. Your real workflows. Book a demo and we'll run your messiest visit type through MedOp live.
Book a live demo →