Capsa Coding
Capsa Coding · one engine, from visit to claim

AI medical coding,
built on your data.

Capsa reads the note the way your best coder would and finds every billable charge the documentation supports — each one defensible, cited to the exact words in the chart. Then it does it on every visit, at once — the read no coding team could staff, at a fraction of the coder hours. Built on your data, measured against what your coders actually billed.

“If your coders can code it, Capsa can too — on every visit.” Every code cited to verbatim chart text
Visit · well-child, 4 mo acct 5000004
Capsa recommends · evidence attached
90460
VAC-ADM-001
“…admin with counseling by physician; first component…”
billed
90686
VAC-PROD-014
“…Influenza, quadrivalent, 0.5 mL IM administered today…”
billed
96110
HS-DEV-001
“…ASQ-3 developmental screen completed, score recorded…”
caught
every code cited to the chart +1 charge the claim missed
93–96%
Coding accuracy vs. what your coders billed
100%
Codes cited to verbatim chart text
35% → 94%
New skill: cold-start to matured
7
Coding categories on one framework
The problem

Published coding guidelines are only half the job.

After a provider signs a note, every service performed has to be billed — the vaccines and screenings, the labs and procedures, the medications, and the visit level itself. Easy to miss, inconsistent between coders, hard to audit later.

Missed codes

Lost, fully compliant revenue — gone for good

Billable work the coder didn't capture is money you earned and won't see. At scale, a few missed codes per visit is a seven-figure annual leak.

Over-coded claims

Audit risk and clawback exposure

Codes billed without support in the chart invite denials and recoupment. The goal isn't “more billing” — it's the right amount, provably.

TakeawayUndercoding loses revenue; overcoding invites audits. Getting it right depends on how your hospital actually codes.
The trap to avoid

A stranger's AI prompts can't code for your hospital.

Most “AI coding” is a fixed set of prompts written by an engineer somewhere else and dropped into your hospital — never adapted to it. Capsa is the opposite: it's built on your data.

Generic, off-the-shelf AI

A static prompt set, identical for every customer — blind to everything that makes coding work at your site:

  • Your providers' documentation phrasing
  • Your payers' contract and visit rules
  • Your team's established coding patterns
  • Your own paid-claims history

Capsa, built on your data

Your own data becomes the system — so it learns exactly the context a stranger's prompts can't see:

  • Your providers' documentation phrasing
  • Your payers' contract and visit rules
  • Your team's established coding patterns
  • Your own paid-claims history
TakeawayStatic prompts can't capture local nuance — so they miss it, every visit.
The realization

Good coders quietly tune their work to each hospital.

Hand the same signed note to coders at two different hospitals and you can get two different — equally correct — claims. What changes is local: the wording providers use, the payers, and how the team has always coded it.

One encounter

Same note.
Same services performed.

Coded differently depending on where it happened — because three things change per site.

Documentation habits

Which phrases this site's providers actually use to record the work.

Local payer rules

Contract and visit conditions specific to this hospital's payers.

Coding patterns

How this team has historically coded similar encounters.

TakeawayThe rulebook is only half the story. How your hospital actually codes is the other half.
Our approach

You don't buy off-the-shelf AI — you get coding built on your data.

Capsa turns your own material into a coding system that fits your hospital — your guidelines, a sample of your past visits, how your team codes, and what payers actually paid drive a cycle you control.

Built on your data Your guidelines Your patient cohorts Your coding patterns Your paid claims
1

Build

Encode your rules, codes, and worked examples into an explicit, human-readable guideline.

2

Validate

Compare Capsa's codes to what your coders actually billed — precision and recall on the codes that matter.

3

Adjust

Fix the rules from real disagreements — every change tracked and versioned.

4

Monitor

Keep watching accuracy over time as documentation and payers change.

TakeawayA system you control and keep improving — not a fixed product you install once.
The headline result
93–96%

coding accuracy, measured against what your coders actually billed.

“If your coders can code it, Capsa can too — on every visit.”

Why that's the ceiling At this accuracy, the remaining differences are usually source-data problems or human coding mistakes — not AI errors.

Internal, validated results across two live coding skills (vaccines and health screening), measured on cases your team already coded. Not an external certification.

Where revenue leaks

See where charges slip away.

Every charge passes through several hands: the doctor writes the note, a coder turns it into a claim, the payer decides what to pay. Money can fall out at each step. Capsa checks the whole path and shows you exactly where — and how much you could recover.

capsa · note to code set
The leakage chain: physician to coder to Capsa, showing the charges each step caught that the one before it missed

See the full breakdown

See it in the product

Transparently benchmarked against your coders.

During validation, Capsa’s codes sit next to what your coders billed — every code carried by the exact line of the note that supports it — so you can see, down to the visit and the code, that it codes as well as or better than your team. In production Capsa just codes; the benchmark is how you earn that confidence first.

capsa pipeline · the defensible code set
Capsa's code set next to the coder's claim: codes they agreed on, codes Capsa added that the claim missed, and codes to review
The defensible code set. Capsa’s codes and how they differ from the coder’s — agreed, captured, and worth a look. The differences are the value, not a grade.
capsa studio · scorecard
Scorecard: scope-aware precision, recall and F1 measured against what coders billed, with per-CPT and per-rule breakdowns
Measured against your coders. Scope-aware precision & recall with per-CPT and per-rule breakdowns — proof, on cases your team already coded.
capsa studio · guidelines
Guidelines registry: every coding guideline with its rules, codes, modifiers and worked examples, versioned
Every rule, visible and yours. Codes and rules are editable and versioned — never hidden inside a model.

See how Capsa codes

No black box

Transparent by design — and yours to govern.

Every code traces to the chart

Code → rule → the verbatim chart text that triggered it, at the exact version that ran. Every quote is checked word-for-word against the chart; if the words aren’t there, the code never makes it into the set.

Versioned and auditable

Rules, codes, and examples are versioned together with full history and side-by-side diffs. When a payer rule shifts, the change — and every code made under it — is on the record.

Your coding logic isn’t in a black box

Every rule and guideline is written in plain language your team can open, read, and change — the logic is right there to inspect, not hidden where you can’t see it. The same explicit guidelines run across every category.

What we cover

Flexibility to grow with you.

Start with one area of coding and grow from there — from a single category to preparing the whole bill, across new care settings as we expand. Live today across pediatric primary care:

Available now Vaccines Health screening Preventive visits Labs Medications In-office procedures E&M & modifiers
Coming next Emergency department Imaging Inpatient

However you buy it — to find missed revenue (Charge Capture) or to catch denials before they happen (Claim Validation) — it's the same coding underneath. See everything we cover →

Find out more

Curious what Capsa would find in your charts?

Tell us a bit about your team and we'll show you what Capsa finds across your visits — on the categories you care about, measured against what your coders already billed, including the charges going uncoded today.

  • Every visit coded — at a fraction of the coder hours
  • Accuracy measured vs. what your coders billed
  • Every recommendation cited to the chart
  • No EMR or vendor lock-in
[email protected] · capsacoding.com

Get in touch

We'll get back to you within one business day.

No spam, ever. Your details are used only to contact you about Capsa.