iBridge DigitaliBridge Digital
← back

How it works

From your first callwith us to your firstcolleague inproduction.

A Smarna colleague onboards the way a new staff member would: assigned to a workflow, given a phone number, paired with a training authority, and taught by voice. The difference is she begins work on day one and keeps learning every day after.

Safety commitment

30-day
shadow.

Every deployment · non-negotiable

Every agent we ship runs in shadow mode for 30 days before it makes an autonomous decision. Your team reviews every call, approves every field, catches every edge case. Then autonomous mode turns on — not before.

You approve every call·Zero autonomous action·Full audit chain visible

The arc of an engagement

Five phases.
Discovery free. Build fixed. Shadow before autonomous.

W1

Free · 30 min

Discovery

We map your operation, call volume, payer mix, EHR stack, workflows that hurt. You leave with a one-page scope.

You: 30 minutes on the phone

W2 – W4

Included in build

Design

Autonomy policy design. Integration mapping. Scope and refusal rules. Training authority chart signed by your team.

You: 2-3 review sessions

W4 – W10

Fixed price · commit

Build

Agent configured against your specific workflows. Integration built. Weekly demos with your training authority. Audit chain live from day one.

You: weekly demo review

W10 – W14

30-day supervised

Shadow

Agent runs alongside your team. Every call reviewed by a human before it changes state. No autonomous action. You approve every field and decision the agent makes.

You: reviewing every call

W14+

Per call · published rates

Autonomous

Agent takes calls independently. Your training authority actively teaching new workflows. Escalation queue for anything the agent refuses.

You: teaching + oversight

The shadow phase is the architectural signature. Most vendors optimize for time-to-autonomous. We optimize for time-to-trust — and trust is earned by 30 days of your team reviewing every call the agent takes.

Engagement

Six to eight weeks from first call
to a colleague in production.

01 / Discovery

Week 1

We map your operational layer.

30-minute call. We map your call volume, payer mix, EHR or RCM stack, the workflows that hurt most, and what good looks like. You leave with a one-pager: which agents we'd deploy, in what order, with what integration depth.

02 / Benchmark

Week 2

We run your real calls through our agents.

You send 100 representative calls (or call recordings, or job samples). We process them through Smarna in a sandbox tenant. You get back: cost per call, accuracy by field, average handle time, and a confidence-scored breakdown of where the agents win and where they hand off.

03 / Pilot

Weeks 3 to 6

One agent. One workflow. One clinic location.

We deploy a single agent against a bounded scope: e.g., outbound prior auth status calls for one specialty at one location. Authority chart set. Knowledge sources connected. Voice training begins on day one with your training authority and one or two peers.

04 / Production

Week 7+

Scope expands as the colleague proves herself.

In-scope teachings ship continuously. Out-of-scope changes flow through the architect for approval. Audit log is queryable from day one. We add agents and locations as your team is comfortable. No big-bang cutovers.

What makes a colleague different from a bot

Four design principles.
All four show up in every agent we ship.

Voice training, not config UIs

A peer dials her number and teaches her by voice. She listens, reasons, asks a clarifier if needed, pushes back politely on contradictions, reflects back, and announces routing transparently. No prompt-editing dashboards for clinics.

Authority and scope, by tier

Owners, training authorities, peers, architects. In-scope changes apply. Out-of-scope changes create an escalation flag with the full reasoning chain. The colleague refuses what her clinic hasn't authorized.

Knowledge in layers

Foundation knowledge from the LLM. Authoritative APIs (CMS, AAPC, payer policy) consulted live. Clinic-specific semantic memory from voice teaching. Risk discipline scaffolded into every decision.

PHI never reaches the core

PHI lives in process memory for the duration of one call, then is destroyed with a hashed proof. The colleague's reasoning, persisted memory, audit log, and customer-facing surfaces never see PHI by architectural enforcement.

Integration

We meet you
where your data lives.

EHR, PM, RCM, telephony, payer APIs. We integrate at the level appropriate to the engagement — from API-first deep integrations to portal-orchestration to flat-file batch.

EHR / PM

  • Epic
  • athenahealth
  • eClinicalWorks
  • NextGen
  • Greenway
  • DrChrono

RCM platforms

  • Waystar
  • Availity
  • Change / Optum
  • AdvancedMD
  • Kareo

Telephony

  • Twilio
  • RingCentral
  • 8x8
  • Five9 (SIP)

Knowledge

  • CMS NCD/LCD
  • AAPC
  • Payer policy APIs
  • FDA NDC

What you see

Four customer-facing surfaces.
All of them read-mostly.

Smarna doesn't hide behind dashboards full of knobs. Your team reads what the colleague is doing, what she's learning, what's waiting on review, and what's been flagged. Approval is the only write action.

Call Reader

Every call the colleague makes or takes, turn-by-turn, with detected issues highlighted and structured outputs attached.

Training Inbox

Pending peer teachings awaiting verification by the training authority. One-click verify, correct, or reject. Or review by voice.

Architect Inbox

Out-of-scope escalations with the full reasoning chain. Each flag shows what change, why out-of-scope, what knowledge was consulted, recommended routing.

Risk Register

Open risks the colleague has identified, with severity, likelihood, recurrence count, status, and recommended response.

Next step

Six to eight weeks. One agent.
Bring us the workflow that hurts most.

Book a 30-min callRead the security posture

Common questions about iBridge engagements

For teams evaluating vendors

How long is a typical iBridge deployment?

8 to 14 weeks from first call to autonomous production. Broken down: Week 1 discovery (free), Weeks 2-4 design and autonomy policy, Weeks 4-10 build and integration, Weeks 10-14 mandatory 30-day shadow period with every call reviewed by the customer’s team, Week 14+ autonomous operation with ongoing training authority oversight.

What is the 30-day shadow period?

A mandatory safety phase where the voice colleague runs alongside your existing team. Every call is reviewed by your training authority before the colleague makes any autonomous decision. Zero autonomous action during shadow. Full audit chain visible. Autonomous mode activates only after the shadow period completes successfully. This is non-negotiable across all iBridge deployments.

Who from the customer side needs to be involved?

A training authority: typically an operations lead or RCM director who owns the workflow. During discovery (Week 1), 30 minutes of their time. During design (Weeks 2-4), 2-3 review sessions. During build (Weeks 4-10), weekly demo review. During shadow (Weeks 10-14), review of every call the colleague takes. Post-autonomous, 2-4 hours per week of oversight and teaching.

How is the voice colleague taught?

Not through prompt editors, rule forms, or admin panels. The colleague is taught by voice — a training authority dials the colleague’s phone number and teaches in conversation. The colleague asks clarifiers when uncertain, refuses what she has not been taught, and every teaching moment is audit-logged with the human who taught it.

What if we need to change something after the colleague is live?

Voice teaching remains active post-deployment. Your training authority can teach new workflows, correct edge cases, or update policies by calling the colleague and holding a training conversation. Changes propagate after verification. Every change is audit-logged. No prompt editing, no configuration UI, no engineering escalation for operational changes.