Capsa Coding
Capsa Charge Capture · the product that's live today

Coding built on your data — proven against your claims.

Capsa encodes your guidelines, reads the signed note, and recommends every CPT/HCPCS code the chart supports with a plain-English reason — verifying each quote is verbatim in the chart before a coder sees it, then scoring itself against what your coders actually billed. 93–96% accuracy.

93–96% accuracy vs. what coders billed 100% of codes cited to the chart
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
precision 96.9%recall 95.5% +1 missed charge recovered
Why it matters

Both ways coding goes wrong are expensive.

After a provider signs a note, a coder reads it and bills every service performed. Billable work is easy to miss, inconsistent between coders, and hard to audit after the fact.

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.

TakeawayBoth failure modes are expensive — and context is everything.
How it works

You don't buy AI prompts — you get the pipeline.

Capsa turns your own material into a living coding system: your guidelines, cohorts, coding patterns, and paid claims drive a loop 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 predictions to what your coders actually billed — scope-aware precision and recall.

3

Adjust

Refine rules from real disagreements, applied as traceable, versioned diffs.

4

Monitor

Track accuracy continuously over time as documentation and payers change.

TakeawayA living system you control — not a static product you install once.
Inside a single visit

Read the note. Prove the code. Measure against what was billed.

01

Ingest

The signed note comes in from the EHR; augmenters fill known gaps like structured vaccine records.

02

Triage

A fast model decides which coding categories even apply, so effort goes only where it's needed.

03

Analyze

Each category runs an explicit, human-readable rule set and proposes codes with a plain-English reason.

04

Cite-check

Every quote is verified verbatim in the chart. Unsupported recommendations are dropped before a coder sees them.

05

Validate

Predictions are scored against what the coder actually billed — scope-aware precision and recall.

A guided tour

Real screens from the product.

Screenshots are from the live application. Patient identifiers and clinical text are scrubbed; codes, rules, versions, and metrics are real.

capsa · visit traceability (the money-shot)
Visit traceability: AI-recommended vs coder-billed codes with match pills and the why-the-AI-recommended-these-codes evidence cards
Visit traceability. AI-recommended vs. coder-billed codes with match pills, and a card for every recommendation showing the rule and the verbatim chart text behind it.
capsa · overview
Improvement-cycle dashboard with a five-stage flow and per-stage KPIs
Overview. The build-validate-adjust-monitor cycle with per-stage KPIs.
capsa · guideline detail
Guideline detail: rules, codes and modifiers, evidence patterns, examples, source materials, and version history
Guideline detail. Rules, codes, evidence patterns, worked examples, and full version history — all in one place.
capsa · validation
Validation dashboard with two-axis scorecard, overall metrics, and per-CPT, per-template and per-rule breakdowns
Validation. Scope-aware precision, recall and F1 with per-CPT, per-template, and per-rule breakdowns.
capsa · iterate
Iterate two-way worklist with run-vs-baseline KPI deltas and a per-visit AI-vs-billed grid
Iterate. A two-way worklist — where AI and the coder agree, where AI over-fired, and where the coder caught something AI missed.
capsa · coder review
Coder review ticket: a clarifying question, an answer form, and a metadata sidebar
Clinician-governed loop. CDI nurses answer clarifying questions and approve rule updates — no engineering required.
Proof, measured

Measured on cases your team already coded.

Precision = of the codes Capsa recommends, the share coders agree with. Recall = of the in-scope codes coders billed, the share Capsa caught.

93–96% accuracy across our two measured categories

Vaccines and health screening are measured and proven against what your coders actually billed; five more categories are built on the same framework, measurement in progress.

Coding categoryPrecisionRecallNote
Vaccines96.9%95.5%Recall SLA (≥95%) met; precision at target.
Health screening · A93.7%95.7%Recall SLA met.
Health screening · B93.9%93.4%Both metrics near target.
Portability proof: the health-screening category went from a 54% / 35% cold start to roughly 94% / 94% using the exact same framework that matured vaccines. New categories inherit the machinery instead of starting over.

“If your human coders can code it, the AI can too.”

Internal, validated results across two live coding skills, measured on cases your team already coded. Not an external certification.

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. Unsupported quotes are dropped before a coder ever sees them. Answer “why this code?” in one click.

Versioned and auditable

Rules, codes, evidence, and worked examples are versioned together with full history and side-by-side diffs. When a payer rule shifts, the change is on the record.

Scope-aware measurement

Precision and recall are measured against the codes each skill actually owns — so the numbers mean what they say instead of being diluted by out-of-scope codes.

Clinician-governed loop

CDI nurses — not engineers — answer clarifying questions and approve rule updates through a guided workflow, with a complete audit trail.

Built on your data

Your guidelines, cohorts, coding patterns, and paid claims drive the system — so it fits your hospital instead of a stranger's static prompt set.

No model lock-in

One engine runs every category, wired to no single EMR or guideline source. All logic lives in explicit rule sets — not weights baked into a model.

In two minutes

See the whole loop, end to end.

A two-minute walkthrough of build → validate → adjust → monitor on real screens. Prefer a live look on your own data? Book a pilot.

FAQ

Questions coders, CDI, and compliance ask.

Is this just generic AI prompts?+
No. Capsa is built on your data. Your guidelines, patient cohorts, coding patterns, and paid claims become the system, so it adapts to your providers' documentation and your payers' rules — instead of using one static prompt set written for everybody.
How is this different from a black-box coding model?+
All clinical logic lives in explicit, human-readable rule sets. Every recommended code links to the rule that produced it and the verbatim chart text that triggered it — at the exact rule version that ran. There's no fine-tuning and nothing hidden inside a model nobody can inspect.
Will Capsa replace our coders?+
No. Capsa is decision support. Coders review AI-recommended codes with the supporting chart evidence attached, and CDI nurses own the rules. Capsa partners with coders; it doesn't replace them.
How do you measure accuracy?+
Predicted codes are compared against what the coder actually billed, on a scope-aware basis that measures only the codes a given skill is responsible for. We report precision and recall with per-CPT, per-template, and per-rule breakdowns.
Is it audit-defensible?+
Yes. Every code links to its rule and the verbatim chart text, at the exact version that ran. Rules, codes, and examples are versioned together with full history and side-by-side diffs.
What does a pilot involve?+
We build a guideline from your rules, run it against a sample of visits your team already coded, and report scope-aware precision and recall against what was billed — no EMR rip-and-replace.
How do you handle PHI and data security?+
Pilots run under appropriate data agreements on limited or de-identified data. We do not train models on your data; all logic is in inspectable rule sets.
Book a pilot on your data

See Capsa on cases your team already coded.

We'll build a guideline from your rules, run it against your cohorts and paid claims, and show you scope-aware precision and recall on visits you've already billed. No rip-and-replace.

  • Built on a sample of your own visits
  • Accuracy measured vs. what your coders billed
  • Every recommendation cited to the chart
  • No EMR or vendor lock-in
[email protected] · capsacoding.com

Request a demo / pilot

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

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