/ case studies / patient access Work with us

Case Study · AI Enablement · Healthcare Patient Access

The 15-minute referral.

A healthcare patient-access company whose platform turns physician referrals into confirmed appointments — except every referral first had to be manually transcribed between systems: a measured ~15 minutes of read, interpret, verify, and re-key across four screens. The fix wasn’t OCR. It was structure, verification, and an audit trail — built under the governance healthcare actually demands. The system we designed is being built by their own team, to expectations we set together: person-to-person calling down ~97%, and daily call capacity up from 400 human-dialed calls to 5,000 AI-automated interactions.

Sector: Healthcare — patient access Focus: Referral intake → end-to-end workflow Engagement: 2026 Expected impact: −97% person-to-person calls · 400 → 5,000 calls/day
~15 min
Per referral, measured on the floor ourselves — the baseline everything gets judged against
400 → 5,000
Calls per day — expected capacity as AI automation takes the routine outreach
−97%
Expected drop in person-to-person calling — humans reserved for conversations that need one
0 PHI
In any non-compliant AI surface — protected data moves only through covered, auditable channels

The company

A real platform with a manual front door.

Built by operators, serving major health systems, with a genuine platform behind it — this is not a laggard. But the front door of the whole operation was human: referrals arrive from hospital EHRs, and an operator reads each one, interprets it, verifies it across systems, and re-keys it into the platform. We didn’t take anyone’s word for the pain — we got operator access and walked a live referral ourselves: ~15 minutes. And the time isn’t typing. It’s reading, interpreting, and verifying across four different systems.

Multiply that by every referral, every clinic, every day — while half the industry’s specialty referrals never get scheduled at all — and the front door is the business case.

The reframe

Structure, not OCR.

The obvious pitch was “point AI vision at the documents.” We killed that framing early. The leverage isn’t reading pixels — it’s the mapping layer: one canonical field schema every referral lands in, no matter how it arrives. So intake became a ladder:

TIER 1
Direct integration — referrals ingested straight from modern EHR APIs. The majority path, and the best one: no interpretation, no re-keying.
TIER 2
Structured intake portal — a self-service form for clinics without API access. Adoption-led: it only wins if it’s faster than the fax machine it replaces.
TIER 3
AI-assisted extraction — the fallback for everything else, with a human reviewing every exception. AI proposes; people approve; nothing auto-commits.

Under all three tiers, the same pipeline — exception-based by design:

Referral arrives
Extract & map to one canonical schema
Deterministic patient match
Human reviews exceptions only
Write to platform
Audit trail + learning loop

The engagement so far

Measured, mapped, governed, taught.

1

Measured the floor ourselves

Hands-on operator access, a live referral walked end to end, a stopwatch on every step. Baseline before AI touches anything — when the numbers land, nobody has to take them on faith.

✓ ~15 min/referral, measured
2

Mapped the whole factory

Intake → authorization → scheduling → confirmation, as one interactive systems map with live queue depths per station. Two competing internal process maps — operations’ and product’s — reconciled into a single canonical view of how work actually moves.

3

Shipped a working proof, not a deck

A live extraction service against a public federal provider registry — real lookups, mapped into the canonical schema, zero protected data — handed to their engineering team as running code plus an engineering-handoff page: field maps, pipeline, open questions, guardrails.

✓ Live · handed to engineering
4

Installed the governance the domain demands

Protected data moves only through covered, compliant endpoints — never consumer AI tools. No auto-commit: humans approve before anything writes. Full audit trail: source, confidence, reviewer, final record. We advise; the client owns deployment and compliance sign-off.

5

Taught leaders first, then the floor

A live build demo for the executive team, then an open AI education forum for everyone. Education-first is the strategy: the tools change monthly; a team that understands the principles doesn’t.

6

Grew a champion — the real deliverable

Months in, their own senior engineer presented AI dev practices to the whole team — plan-first-then-code, grounding agents in the repo, forcing verification — our guidance, contextualized to their systems, in his voice. Adoption that doesn’t depend on us being in the room.

✓ Champion teaching, unprompted

The results

What we set in motion.

The structural work was delivered and handed over: the baseline measured, the architecture agreed, a working proof placed in their engineers’ hands, the governance installed, and their own champion teaching the practices onward. The capacity numbers below are the expectations we set with the client — and the measured 15-minute baseline is what they’ll be judged against.

~15 min
The number to beat. Measured by us, on the floor, before anything changed. The whole engagement will be judged against it — publicly, on this page.
400 → 5,000
Calls per day, expected. AI automation takes the routine outreach and confirmations; person-to-person calling drops ~97%, reserved for the conversations that actually need a human.
Handed over
Architecture agreed, working proof shipped to their engineers, champion teaching — built by their team, with our oversight.
Governed
Protected data through covered endpoints only, humans approving writes, a full audit trail — installed, not promised.

Why it’s built this way

Healthcare doesn’t need faster guesses. It needs structure, verification, and an audit trail.

Measure it yourself

We don’t baseline from interviews. Operator access, a live walkthrough, a stopwatch — then the improvement claim can survive an audit.

Schema is the product

The canonical field mapping outlives any OCR model, any vendor, any tier. Structure first; extraction is a detail.

Humans on exceptions

Automation earns trust by handling the routine and escalating the ambiguous. Nothing writes without a person or a proof.

Champions over consultants

The engagement succeeds when their people teach it without us. That’s the deliverable the invoice never quite captures.

Regulated industry, manual front door?

Healthcare, finance, anywhere the data is protected and the stakes are real — we build AI systems with the governance your auditors expect and the baselines your board can trust.

Start a conversation → More case studies