What is the difference between Calvient AI agents and a chatbot?

A chatbot responds to questions. Calvient's agentic AI agents take action. They monitor for conditions, execute defined sequences of tasks (verifying, routing, chasing, notifying), make rule-based decisions, and escalate or hand off when judgment is needed. They handle the repetitive operational middle of healthcare workflows — the administrative tasks that happen dozens of times a day but do not require clinical expertise.

Agents Skilled in
Every Tedious Task

Calvient's agentic AI agents — purpose-built AI workflow automation agents for healthcare operations — handle the administrative work between task creation and human decision. They trigger on conditions, run defined action sequences, and hand off with full context when judgment is needed.

See the Agents Book a Demo

The Four-Phase Model

How every agent works

Every Calvient agent follows the same four-phase model from detection to handoff.

Trigger

Every agent watches for a specific condition — a new fax, a missed deadline, an unsigned form, or an eligibility mismatch. When the condition is met, the agent activates automatically.

Analyze

The agent evaluates context: patient data, payer rules, workflow state, and prior history. It applies configured logic to determine which action sequence fits the situation.

Act

The agent executes its action sequence — routing a document, sending a follow-up, submitting an authorization, verifying eligibility — completing the repetitive middle work without staff involvement.

Handoff

When a case exceeds its SLA, contains ambiguity, or requires clinical judgment, the agent stops and surfaces the item to staff with the full task history, communications log, and extracted data attached.

Special Agents

Meet the agents

Each agent is designed for a specific workflow — with a defined trigger, a set of autonomous actions, and a clear handoff condition. They handle the repetitive middle so staff can focus on what requires judgment.

Browse by workflow

Front Office Automation

Every Visit, Handled End to End

Agents that handle reminders, intake paperwork, and post-visit follow-up so the front desk can focus on patients in the room.

Reminder Agent

automated appointment reminder and outreach agent

Replaces

Manual phone call reminder lists and voicemail follow-up

Trigger

An appointment is scheduled and the first configured reminder interval is reached based on appointment type and patient risk profile.

Actions

Sends an initial reminder via the patient's preferred channel (SMS, phone, or email)
Runs follow-up sequences based on appointment-type cadence
Detects confirm, cancel, or reschedule responses and updates the schedule accordingly
Flags high-risk appointments for enhanced outreach (new patients, complex procedures)

Intake Concierge

digital intake form delivery and completion agent

Replaces

Paper packets handed to patients at the front desk

Trigger

A new appointment is confirmed and digital intake forms are required before the visit.

Actions

Sends the intake packet to the patient via their preferred channel
Tracks completion status against appointment timing
Sends follow-up prompts with a direct link for incomplete forms
Flags specific missing items and escalates when forms remain incomplete within 24 hours

Follow-Up Sentinel

post-visit follow-up and care gap closure agent

Replaces

Spreadsheet tracking for no-shows and post-visit tasks

Trigger

An appointment ends as a no-show, or a post-visit follow-up window opens based on the visit type.

Actions

Sends post-visit survey to confirmed appointments
Initiates no-show outreach with reschedule options
Sends lost-to-follow-up notices at configured intervals
Records all outreach attempts and responses in the visit history

Inbound Referral Automation

Intake to Consult, No Gaps

Agents that verify coverage, match capacity, and close the referral loop — from the moment a referral lands to the consult note coming back.

Insurance Checker

eligibility and network verification agent

Replaces

Manual eligibility calls to payer portals before scheduling

Trigger

A new inbound referral arrives and is routed to the intake queue.

Actions

Runs eligibility check against the patient's payer in real time
Confirms in-network status for the referred service and specialty
Identifies coverage gaps, authorization requirements, or benefit limits
Logs the result to the referral record with a timestamp

Capacity Matcher

appointment slot matching and scheduling queue agent

Replaces

Back-and-forth phone tag to find an open appointment slot

Trigger

An inbound referral clears eligibility and completeness checks and is ready to schedule.

Actions

Queries available appointment slots matched to the referred procedure and specialty
Proposes scheduling options and queues the task for the appropriate team
Notifies the referral coordinator that scheduling is ready to confirm
Logs slot availability and proposed options to the referral record

Referral Closer

prior auth and consult note loop-closing agent

Replaces

Staff chasing prior auth decisions and consult notes by fax

Trigger

An inbound referral has been scheduled and requires prior auth, or an appointment has passed without consult notes returned.

Actions

Initiates prior authorization if required and tracks the decision
Follows up with the specialist for consult notes after the appointment date
Notifies the referring provider when the referral loop is closed
Logs all communications and decisions in the referral timeline

Outbound Referral Automation

Refer Out Without Losing the Thread

Agents that find the right specialist, clear prior auth, and chase records back — so outbound referrals don't disappear into a black hole.

Specialist Finder

in-network specialist matching and selection agent

Replaces

Manual provider directory searches and referral coordinator calls

Trigger

An outbound referral order is created and a specialist has not yet been identified.

Actions

Searches the network directory for in-network specialists matched to the procedure and patient location
Filters by specialty, availability, and network status
Presents ranked options to the care team with relevant details
Logs the final selection to the referral record

Prior Auth Prepper

outbound prior authorization submission and tracking agent

Replaces

Manually building auth packets and submitting to payer portals

Trigger

An outbound referral requires prior authorization from the patient's payer before records are sent.

Actions

Verifies PA requirements for the procedure and payer combination
Collects required clinical documentation from the EHR
Builds and submits the authorization packet to the payer
Tracks the decision and alerts the team when authorization is received

Consult Note Chaser

outbound records delivery and consult note retrieval agent

Replaces

Repeated follow-up faxes and calls to get consult notes back

Trigger

An outbound referral appointment has passed and consult notes have not been returned within the configured window.

Actions

Sends the patient records to the specialist via fax or secure message
Initiates follow-up outreach at configured intervals until notes are received
Logs all delivery confirmations and follow-up attempts
Marks the referral complete when consult notes are returned

Medical Records & Release of Information Automation

Request In, Records Out

Agents that parse release requests, compile chart packets, and dispatch records — with a traceable handoff history at every step.

Request Reader

inbound records release request parsing and routing agent

Replaces

Staff manually reading and sorting faxed release requests

Trigger

An inbound records release request arrives via fax, portal, or secure message.

Actions

Parses the request to identify the requesting party, patient, date range, and record types needed
Validates that required authorization is present and sufficient
Routes the validated request to the appropriate records workflow
Logs the request details and routing decision for audit purposes

Record Compiler

chart packet assembly and completeness verification agent

Replaces

Manually pulling and assembling chart sections for each release

Trigger

A validated release request has been processed and the chart packet needs to be assembled.

Actions

Pulls relevant records from the EHR based on the request scope and date range
Compiles the packet and checks it for completeness against the request
Flags any gaps between what was requested and what is available
Queues the compiled packet for release review

Fax Dispatcher

records delivery and traceable handoff confirmation agent

Replaces

Manual fax sends with no delivery confirmation or audit trail

Trigger

A compiled chart packet has passed review and is ready to be delivered to the requesting party.

Actions

Routes the packet to the requesting party via fax or secure message
Confirms delivery and logs the confirmation against the release record
Generates a traceable handoff receipt for compliance documentation
Updates the release record with delivery status and timestamp

Revenue Cycle Automation

Denials and Coding, Tightened Up

Agents that draft denial responses, flag coding discrepancies, and route rework — catching revenue leakage before it compounds.

Denial Drafter

claim denial response drafting and documentation agent

Replaces

Starting denial response letters from scratch with no docs attached

Trigger

A claim denial is received from a payer and logged in the workflow.

Actions

Identifies the denial reason code and the documentation required for appeal
Drafts the denial response letter with the appropriate clinical language
Attaches supporting documentation pulled from the EHR
Queues the draft for staff review and signature before submission

Coding Reviewer

procedure code discrepancy detection and routing agent

Replaces

Manual claim audits and coding spot checks done after the fact

Trigger

A claim or document is submitted and a discrepancy between procedure codes and clinical documentation is detected.

Actions

Compares procedure codes against the clinical documentation in the record
Flags specific discrepancies with the supporting evidence identified
Routes the flagged item to the appropriate coder with context attached
Logs the discrepancy for trend analysis and audit purposes

Rework Router

denial and correction task assignment and escalation agent

Replaces

Shared email queues and verbal task handoffs with no tracking

Trigger

A denial, coding flag, or rework item is identified and needs to be assigned for resolution.

Actions

Determines the appropriate team member or queue based on task type and priority
Assigns the task with full context and relevant documentation attached
Tracks completion status and sends reminders for tasks approaching their deadline
Escalates stalled items when they exceed the configured SLA threshold

Operational Visibility Automation

One View Across Every Workflow

Agents that surface performance data, SLA risk, and capacity signals — so leadership sees what's happening before staff have to report it.

Performance Analyst

workflow volume and turnaround reporting agent

Replaces

Manually pulling reports from multiple systems into a spreadsheet

Trigger

A configured reporting interval is reached (daily, weekly) or an on-demand report is requested.

Actions

Aggregates workflow volume and completion data across all active queues
Calculates turnaround times and completion rates by workflow type
Generates a summary report with trends and period-over-period comparison
Delivers the report to configured recipients via email or dashboard

SLA Sentinel

queue SLA risk detection and bottleneck surfacing agent

Replaces

End-of-day queue reviews that surface problems too late to fix

Trigger

A queue item approaches its SLA threshold or a volume spike is detected that puts throughput at risk.

Actions

Monitors SLA status across all active queues in real time
Identifies items at risk of missing their turnaround-time targets
Surfaces at-risk cases to the appropriate team lead with time remaining
Logs each alert for pattern analysis

Capacity Forecaster

staffing impact and capacity modeling agent

Replaces

Gut-feel staffing decisions made reactively after backlogs form

Trigger

A configured reporting interval is reached or a significant volume deviation from baseline is detected.

Actions

Analyzes workflow volume trends across queues and workflow types
Models staffing impact against current queue capacity and throughput rates
Identifies the highest-leverage opportunities for staffing or process adjustment
Generates a capacity report with specific recommendations

Coverage

Agents embedded across
every workflow

Calvient's agents aren't a bolt-on add-on. They're part of each use case workflow — sitting inside the operational layer your team already uses.

Intake & Triage

Intake Concierge · Insurance Checker · Request Reader

See workflow →

Referral Management

Insurance Checker · Capacity Matcher · Referral Closer · Specialist Finder · Consult Note Chaser

See workflow →

Prior Auth & Payer Ops

Prior Auth Prepper · Referral Closer · Denial Drafter · Coding Reviewer

See workflow →

Scheduling & Patient Readiness

Reminder Agent · Intake Concierge · Capacity Matcher

See workflow →

Patient Outreach & Follow-Up

Follow-Up Sentinel · Reminder Agent · Rework Router

See workflow →

Medical Records & Release of Information

Request Reader · Record Compiler · Fax Dispatcher

See workflow →

Frequently Asked Questions

What is agentic AI in healthcare? +

Agentic AI in healthcare refers to AI systems that autonomously execute multi-step administrative workflows in response to defined triggers — without requiring step-by-step human instruction for each action. Unlike chatbots that answer questions, agentic AI agents take action: verifying documents, sending follow-ups, routing tasks, checking eligibility, submitting prior authorizations. They handle the repetitive operational middle of healthcare workflows and hand off to staff only when the situation requires clinical judgment or exception handling.

How is agentic AI different from traditional healthcare automation? +

Traditional automation (RPA, rule-based bots) follows rigid scripts that break when data changes or edge cases appear. Agentic AI applies judgment within defined parameters — it can interpret unstructured documents, adapt to different payer requirements, and decide which action is appropriate based on context. The key difference is that agentic AI handles variability; traditional automation requires near-perfect data conditions to function reliably.

What healthcare workflows can Calvient AI agents automate? +

Calvient's agentic AI agents automate workflows across:

Document intake and triage — classifying, extracting, and routing faxes, forms, and messages
Referral management — validating completeness, tracking status, and notifying referring providers
Prior authorization — building and submitting auth packets, tracking decisions, chasing responses
Real-time eligibility verification — contacting patients with coverage mismatches before appointments
Patient appointment reminders — multi-channel outreach with risk-based escalation
Patient form completion follow-up — nudging unsigned digital intake paperwork
Queue management and SLA enforcement — auto-assigning work and escalating stalled items

How do Calvient AI agents know when to hand off to staff? +

Each agent has a defined handoff condition configured for its workflow. Handoffs are triggered when:

A case exceeds its SLA threshold despite agent outreach
An item contains ambiguous data below the agent's confidence threshold
A patient or provider has not responded after the maximum number of outreach attempts
The situation requires clinical judgment (e.g., a prior auth denial or clinical escalation)

When an agent hands off, it surfaces the item to the appropriate staff queue with the full task history, communications log, and extracted data attached — so staff can act immediately without reprocessing from scratch.

Do Calvient AI agents work with my existing EHR? +

Yes. Calvient's agents are designed to work alongside existing EHR platforms — including eClinicalWorks, athenahealth (athenaOne), NextGen Healthcare, ModMed, Veradigm (Allscripts), AdvancedMD, CureMD, and Greenway Health — without requiring a full system replacement. The agents read workflow state from the EHR, take actions within Calvient's operational layer, and write back to the EHR at defined handoff points.

What is "the repetitive middle" that Calvient agents handle? +

The "repetitive middle" refers to the operational work that happens between when a task is initiated and when it requires a qualified human decision.

For example: a referral arrives → a staff member manually checks whether it is complete → sends a fax to request missing documents → waits for a response → checks again → routes it to the scheduler. Every step in that loop except the final scheduling decision is the repetitive middle.

Calvient's agents handle those steps automatically, leaving staff to focus on the judgment-requiring endpoints — not the administrative connective tissue between them.

Ready to put agents to work?

See how Calvient's agentic AI agents reduce administrative burden, cut turnaround times, and give your staff their time back — inside the workflows they already use.

Book a Demo Explore the Platform

Agents Skilled inEvery Tedious Task

How every agent works

Trigger

Analyze

Act

Handoff

Meet the agents

Every Visit, Handled End to End

Reminder Agent

Intake Concierge

Follow-Up Sentinel

Intake to Consult, No Gaps

Insurance Checker

Capacity Matcher

Referral Closer

Refer Out Without Losing the Thread

Specialist Finder

Prior Auth Prepper

Consult Note Chaser

Request In, Records Out

Request Reader

Record Compiler

Fax Dispatcher

Denials and Coding, Tightened Up

Denial Drafter

Coding Reviewer

Rework Router

One View Across Every Workflow

Performance Analyst

SLA Sentinel

Capacity Forecaster

Agents embedded acrossevery workflow

Intake & Triage

Referral Management

Prior Auth & Payer Ops

Scheduling & Patient Readiness

Patient Outreach & Follow-Up

Medical Records & Release of Information

Frequently Asked Questions

Ready to put agents to work?

See Calvient Run Your Workflow Live

Agents Skilled in
Every Tedious Task

Agents embedded across
every workflow