Recall list construction
Overdue annual visits, chronic care follow-ups, missed referrals and post-hospital follow-ups, pulled from your own data.
09 · Patient experience
AI Recall & Care Gap Agent
Every practice has a list of patients who should have come back and did not. The Care Gap Agent works that list every day and turns it into booked visits and closed quality measures.
Agent at a glance
- StatusIn development
- CategoryPatient experience
- Deployment2–4 weeks, shadow mode first
- Review modelHuman approval per action, configurable
- Headline metric15–30% Recall conversion
- EvidenceFull action log, exportable any time
3–8×
More recall outreach
Versus what a busy front desk can make time for.
15–30%
Recall conversion
Overdue patients who book after structured outreach.
100%
Gap closure documented
Every closed measure carries its supporting evidence.
What it does
Everything in this agent, in writing.
Quality gap identification
HEDIS, MIPS and payer-specific measures with the specific evidence needed to close each one.
Multi-channel outreach
Call, text, email and portal, sequenced by preference and response, with quiet hours respected.
Booking in the conversation
Outreach ends in a scheduled appointment, not a message asking the patient to call you.
Chronic care engagement
Between-visit check-ins for enrolled CCM and RPM patients, with clinical escalations routed to staff.
Closure reporting
Gap closure rates and the revenue and quality impact, reported monthly by measure and by provider.
Deployment
Live in weeks, not quarters.
01
Population analysis
We quantify the open care gaps and recall backlog and estimate the recoverable value.
02
Measure mapping
Your quality programme's measures mapped to the evidence that closes them.
03
Outreach pilot
One measure or one provider panel first, with conversion measured against a holdout group.
04
Scale to the panel
Roll out across measures and locations, with performance reported monthly.
Guardrails
What it will never do.
These limits hold regardless of configuration. They exist so that you can put an agent in front of patients without putting your licence next to it.
- Outreach is limited to non-clinical scheduling and screening reminders — no results by text or email
- Clinical questions from a patient always route to a human, immediately
- Contact frequency caps so no patient is hounded; preferences honoured and recorded
- Measures are never marked closed without the supporting evidence in the chart
- Clinical judgement about whether a screening is appropriate stays with the clinician
Human in the loop, by your choice
Every action can require approval before it commits. Start with all of care gap agent queued to your staff or to ours, watch the accuracy numbers, then widen autonomy workflow by workflow — or leave it queued forever. Both are supported.
Escalations land with certified people
Our review queue is staffed by the same certified coders, billers and credentialing specialists who run our managed services. Not a support desk, and not a chatbot watching a chatbot.
Full evidence trail
Input, decision, action, confidence, model version, reviewer and timestamp — retained and exportable as CSV or JSON, including after you leave us.
What we report against
Operational targets for this agent. They are internal commitments measured on your own data, reported monthly — including the misses.
15–30%
Recall conversion
3–8×
Outreach volume
100%
Evidence documented
< 1%
Complaint rate
Works with your systems
Your EMR, your numbers, your data.
- Athena
- eClinicalWorks
- NextGen
- Epic
- Tebra
- Payer quality portals
- Population health platforms
We integrate through FHIR and HL7 where the vendor supports it, and through secure automation or structured document intake where it does not. No API required, no vendor commission taken.
FAQ
Common questions.
How is this different from a text reminder?
A reminder tells the patient something. This finds the patients who need something, contacts them in the right channel at the right time, answers their questions and books the visit. Reminders are one step in a longer sequence.
Will it annoy our patients?
Frequency caps, channel preferences and quiet hours are enforced, and every opt-out is honoured permanently. We report complaint rates monthly — if a patient cohort is unresponsive, we stop contacting them.
Can it close HEDIS gaps?
It can identify the gaps, do the outreach, book the visit and assemble the documentation that supports closure. The clinical decision to perform a screening remains the clinician's.
Does it handle chronic care enrolments?
Yes — including CCM, RPM and PCM enrolment conversations, consent capture and the between-visit check-ins those programmes require.
Related agents
Usually deployed together.
10
In development
AI Prior Authorization Agent
Checks whether a service needs authorization, assembles the clinical packet, files it, and tracks every request to a decision — with the deadlines that matter.
- Requirement checked before the service is scheduled
- Clinical packet assembled from the chart automatically
- Every request tracked to a decision, with deadlines enforced
11
In development
AI Denials & Appeals Agent
Works deny-rail and clearinghouse rejections continuously: categorises each denial, drafts the appeal with clinical support attached, and escalates the patterns that keep recurring.
- Every denial categorised, owned and worked to resolution
- Appeals drafted with the clinical documentation attached
- Root-cause patterns fed back to coding and the front desk
12
In development
AI Payment Posting Agent
Reads ERAs and EOBs, matches payments to claims, posts insurance and patient amounts, verifies contractual adjustments, and reconciles every posting against the bank deposit.
- ERA and EOB posting with line-level matching
- Contractual adjustments verified, underpayments flagged
- Daily reconciliation to bank deposits with exceptions queued
See it run on your own workflow.
A 30-minute demo using your scenarios, your payer mix and your systems. We will show you the guardrails and the audit log, not just the happy path.
A 30-minute call with an operations lead. No obligation, no sales sequence, and we will say so if you do not need us.