ERA and EOB posting
835 files and scanned EOBs read and matched to claims at the line level, including multiple claims per payment.
12 · Revenue cycle
AI Payment Posting Agent
Posting is high-volume, low-judgement and unforgiving of error. The agent posts it, checks the contract rate, and balances to the bank every day — so your ledger is trustworthy and your A/R is real.
Agent at a glance
- StatusIn development
- CategoryRevenue cycle
- Deployment2–4 weeks, shadow mode first
- Review modelHuman approval per action, configurable
- Headline metric< 24 hrs Posting lag
- EvidenceFull action log, exportable any time
< 24 hrs
Payment to ledger
Same-day or next-day posting, no weekly catch-up.
99.5%+
Posting accuracy
Line-level matching with exceptions queued, not guessed.
100%
Daily reconciliation
Every posted batch balanced to the deposit, with variances explained.
What it does
Everything in this agent, in writing.
Patient responsibility posting
Deductible, co-insurance and copay amounts posted to the patient ledger and turned into a statement or a payment request.
Contractual adjustment verification
Allowed amounts checked against your fee schedule and contract; variances flagged rather than written off.
Underpayment recovery
Silent underpayments identified and routed to the Denials Agent for reprocessing or appeal.
Bank reconciliation
Deposits matched to posted batches daily, with unmatched items in a queue with an owner and an age.
Credit balance management
Overpayments identified and refunded or offset per your policy and state rules, with the trail retained.
Deployment
Live in weeks, not quarters.
01
Posting audit
We measure your current posting lag, error rate and reconciliation discipline against the numbers that matter.
02
Contract and fee schedule load
Payer-specific allowed amounts loaded for variance checking.
03
Parallel posting
The agent posts in parallel with your team until variance is under 0.5%.
04
Full posting and daily reconciliation
Straight-through posting with exceptions to staff.
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.
- Never adjusts a balance without a matching payer explanation on file
- Write-offs and refunds require human approval against your policy
- Every posting line traceable to its source ERA or EOB image
- Reconciliation variances reported daily, not discovered at month-end
- Segregation of duties: the agent posts, a human approves adjustments and refunds
Human in the loop, by your choice
Every action can require approval before it commits. Start with all of posting 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.
< 24 hrs
Posting lag
99.5%+
Accuracy
100%
Daily reconciliation
< 0.5%
Variance
Works with your systems
Your EMR, your numbers, your data.
- Any clearinghouse 835 feed
- Athena
- eClinicalWorks
- NextGen
- Tebra
- AdvancedMD
- Bank deposit feeds
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.
Can it read scanned EOBs?
Yes — paper and PDF EOBs are read with OCR and matched the same way as electronic remittances, with lower-confidence reads queued for a human.
How do you prevent double posting?
Every payment carries its payer trace number and is checked against posted history before it is applied. Duplicates are flagged, never silently applied.
Does it handle patient payments?
Yes — card, ACH and cash payments posted to the patient ledger, with deposits reconciled to the merchant processor's settlement report.
What about credit balances?
Identified and queued for refund or offset according to your policy and state escheat rules, with human approval before anything is issued.
Related agents
Usually deployed together.
13
In development
AI Credentialing Agent
Keeps every provider's credentials, CAQH profile, payer enrolment and expirables current — prefilling applications, chasing payers and escalating before anything lapses.
- Applications prefilled from a single source-of-truth profile
- Payer follow-up on a fixed cadence with escalation paths
- Expirables tracked with 120/90/60/30-day escalation
01
In development
AI Phone Agent
Answers every call on your existing number, day or night. Books and moves appointments in your EMR, captures refill requests, answers routine questions from your own practice information, and leaves staff a transcript plus a task.
- 24/7 answering on the number patients already call
- Books, reschedules and cancels directly in your EMR
- Transcript, intent and task attached to the patient record
02
In development
AI Web Chat Agent
Turns website visitors into booked appointments. Answers questions from your own practice information, checks provider availability, and hands the visitor a real appointment instead of a contact form.
- Books appointments from your website, 24/7
- Answers questions from your content, not the open web
- Escalates to staff with the full conversation attached
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.