DOCUdavit AI Calling Project - Enterprise Options & Strategy

Prepared for Stephen Leibtag, DOCUdavit | By Ben Block, Pixel Block Studio | February 2026

📋The Big Picture
🎯The Strategy
Platform ARetell AI
🛡️Platform BBland AI
🔧Platform CCustom Build
⚖️Side-by-Side
📜The Rules
🎯Coverage Plan
📅Timeline
🛡️Risks
🚫Also Evaluated
🚀Next Steps

What Changed

When we first scoped this project, we were planning for one doctor's retirement - about 1,200 patients to notify. That's still the pilot. But Stephen, you told us something that changes the entire picture:

This isn't a one-off project. DOCUdavit has hundreds of thousands of patients to reach over time.
This is a core, ongoing business operation - not a single campaign. Each retiring doctor brings 500-2,000 patients. The system needs to handle growing volume as DOCUdavit signs more doctors.

The exact volume per month depends on how quickly DOCUdavit onboards retiring doctors. We've built this analysis around several scenarios so we can plan for the right scale.

The CPSO Pipeline

Here's the business reality that drives the volume:

1
The College of Physicians (CPSO) has ~108,000 physician records in Ontario alone.
2
About 60,000 of those are general practitioners. They're the ones with patient lists.
3
Filter by graduation year and you can identify which doctors are approaching retirement age - or have already retired.
4
Each retiring doctor = 500 to 2,000 patients who need to be notified that their records are stored with DOCUdavit.
5
Multiple script variations are needed. A patient whose doctor just retired last month gets a different message than a patient whose doctor retired 5 years ago and the records have been sitting in storage.
Volume Scenarios:
ScenarioDoctors/YearPatients/YearAvg Calls/Month
Steady Growth10-2010,000-40,000~1,000-3,500
Moderate Scale30-5030,000-100,000~2,500-8,500
Full Pipeline50-100+50,000-200,000+~4,000-17,000+

The calls don't all have to go out in one month - campaigns can be spread across the year as doctors are signed. The pilot will reveal the actual pace.

Why this matters for platform choice: If campaigns are bursty (a few big pushes per year), pay-as-you-go platforms like Retell win - no wasted subscription fees in quiet months. If volume becomes consistently high (thousands of calls every week), enterprise subscriptions or a custom build may save money long-term. We don't need to decide now - the pilot tells us.

Our Approach: Pilot First, Then Scale

We're not guessing at volume. Here's the smart path:

1
Pilot with 1,200 patients - prove the concept works. Test voice quality, delivery rates, callback rates, voicemail detection, and compliance. Low cost, low risk.
2
Evaluate the results - with real data in hand, get enterprise quotes from the top platforms. Make an informed decision about the long-term platform.
3
Scale on the right platform - whether that's Retell AI Enterprise, Bland AI Enterprise, or a custom Twilio build depends on the pilot data, the quotes we get, and your budget.

The Voicemail Message

Important discovery: The voicemail message CANNOT include the patient's name, mention their medical records specifically, or reference any health information. Ontario privacy rules (CPSO guidelines) say you can't leave personal health information on voicemail because you can't verify who's listening. Maybe the patient's spouse picks up. Maybe a roommate.

The message must be generic:

"Hello, this is Sandra calling from DOCUdavit Medical Records on behalf of Dr. Smith's office. We have an important message for you. Please call us back at 416-781-9083. Thank you."

Key insight that simplifies everything: Because the voicemail has to be generic anyway (privacy rules), we only need about 10-20 unique audio files per campaign - one per retired doctor. Not one per patient. This makes the system dramatically simpler and cheaper to operate at scale.
Confirmed: DOCUdavit acts as custodian of medical records on behalf of the doctor and has the doctor's explicit permission to contact their patients. This means solicitation concerns do not apply - these are authorized custodian notifications, not unsolicited calls.
One rule still applies: The message should NOT mention fees, pricing, or services. Keeping the call purely informational ("your doctor retired, your records are here, call us") is the safest approach and avoids any grey area around telemarketing classification. Fines for telemarketing violations: up to $15,000 per call.

The Three-Phase Strategy

We don't pick the final platform on day one. We earn the right to make that decision by running a real campaign first.

Phase 1: PILOT

1,200 patients on Retell AI pay-as-you-go | ~$180 in calling costs | 1-2 weeks to launch

Goal: Prove the concept works before committing to a long-term platform.

  • Test AI voice quality with Sandra's cloned voice on real calls
  • Measure delivery rate: what percentage of patients actually hear the message?
  • Measure callback rate: how many patients call back after getting the voicemail?
  • Test voicemail detection accuracy: does the system correctly identify voicemail vs. live answer?
  • Test different calling times: morning vs. afternoon vs. evening
  • Verify Canadian number delivery with Bell, Rogers, Telus
  • Identify any compliance issues before scaling
Why Retell AI for the pilot: Pay-as-you-go pricing ($0.10/min) means no subscription commitment. If it doesn't work, we've spent ~$180 on calls + Ben's setup time. Low risk, fast to launch.

Phase 2: EVALUATE

Get enterprise quotes with real pilot data in hand | 1-2 weeks

Goal: With actual pilot results, negotiate enterprise pricing and verify compliance claims.

  • Take the pilot data (delivery rates, call durations, callback rates) to Retell AI and Bland AI
  • Get real enterprise quotes from both platforms based on projected volume
  • Verify Bland AI's PHIPA compliance claim - ask for documentation, certification, or legal opinion
  • Determine: does DOCUdavit need live AI conversations, or is voicemail-only sufficient at scale?
  • Compare total cost of ownership across all three options
Why this matters: Enterprise pricing is always negotiable. A vendor who sees real campaign data and a committed customer will offer better rates than a cold inquiry. The pilot gives us leverage.

Phase 3: SCALE

Choose the long-term platform and build for volume | 2-4 weeks

Goal: Commit to the right platform and operationalize it for DOCUdavit's ongoing business.

The final choice depends on what we learn in Phases 1 and 2:

  • Retell AI Enterprise - if their Canadian compliance story improves and pricing is competitive
  • Bland AI Enterprise - if their PHIPA claim checks out and they can match on pricing
  • Custom Twilio Build - if volume is high enough that the $6,000-8,000/month savings over platforms justifies the upfront build cost and ongoing maintenance

The Coverage Cascade (Still Applies at Scale)

No single method reaches every patient. At any volume, the cascade strategy applies:

1
AI Phone Calls - primary method. Reaches 70-85% of patients.
2
Ringless Voicemail Drop - backup for screeners who ignore unknown numbers. Catches another 10-15%.
3
Canada Post Mailing - fallback for disconnected numbers and patients without voicemail. DOCUdavit already does this.
4
SMS Text (optional) - last resort for cell phones that never answered. Pennies per text.
The cascade becomes more valuable as volume grows. If AI calls reach 80% of patients, that's 20% who still need follow-up. Automating each tier of the cascade saves enormous manual effort compared to DOCUdavit's current process.

Platform A: Retell AI Recommended for Pilot

What is it? Retell AI is an all-in-one AI calling platform. It handles making calls, detecting voicemail vs. live answer, playing messages, having AI conversations, cloning voices, and tracking results - all from one dashboard.

How It Works

1
Create a Retell AI account for DOCUdavit. Buy a Canadian phone number ($5/month). Complete business verification so calls aren't flagged as spam.
2
Sandra clones her voice in the platform. She records a few minutes of speech. Retell creates an AI version. Voice cloning is built into the platform - no third-party service needed.
3
Ben writes the scripts and configures the AI agent. "When you reach voicemail, say this. When a human answers, say this instead." Sets calling hours, retry logic, and compliance rules.
4
Upload the patient spreadsheet. CSV with phone numbers and which doctor each patient belonged to. Click "Send." The system calls everyone automatically.
5
Monitor results on the built-in dashboard. See in real time: who got the voicemail, who picked up, who didn't answer, who needs a retry.

What Happens When Someone Picks Up?

This is where Retell shines. If a patient answers, the AI can have a basic conversation:

Pilot Budget (1,200 Calls)

ItemCostNotes
Ben's setup & configuration$900 - $1,35012-18 hours @ $75/hr
Voice cloning consent docsIncluded aboveWritten licence for Sandra
Retell AI calls (1,200 x 1.5 min avg)~$180$0.07/min base + $0.03/min Canada telephony
Canadian phone number$5/monthCancel anytime
Total for pilot campaign$1,085 - $1,535 + HST

Scaled Budget Scenarios

Monthly VolumePay-As-You-GoEnterprise Rate (est.)Notes
5,000 calls~$750N/A (stay on PAYG)A few doctors/month
10,000 calls~$1,500~$1,200Enterprise may make sense here
50,000 calls~$7,500~$6,000Enterprise commitment likely required
100,000 calls~$15,000~$12,000Negotiated rates, $3K/mo minimum

Note: Real all-in cost with premium voice/LLM options can range from $0.13-$0.31/min, not the advertised $0.07. Enterprise estimates assume negotiated rates. Actual volume depends on how many doctors DOCUdavit signs per year.

Scale Considerations

Pay-as-you-go vs. enterprise: Retell's PAYG model is ideal when volume is unpredictable or campaign-based. Enterprise commitments (~$3,000/month minimum) only make sense at consistent high volume. The pilot will reveal DOCUdavit's actual usage pattern before any commitment is needed.
Infrastructure reliability: As a dedicated AI calling platform, Retell handles scaling, uptime, and support automatically. No maintenance burden on DOCUdavit - if call volume spikes during a busy month, Retell handles the infrastructure scaling.
Pricing predictability: Enterprise rates are negotiable but require real usage data. The pilot gives DOCUdavit negotiating power - a platform that sees committed volume and usage patterns will offer better rates than a cold inquiry.

Pros and Cons

Pay-as-you-go = perfect for pilot (no commitment)

Handles BOTH voicemail AND live AI conversations

Built-in dashboard - Stephen's team can run campaigns independently

HIPAA/BAA included on Enterprise tier (no extra charge)

Voice cloning built into the platform

Automatic voicemail detection

Canadian phone numbers available directly

Works with all phones - cell, landline, VoIP

Concurrency: 20 concurrent on pay-as-you-go, unlimited on Enterprise

Canadian compliance: working towards PHIPA best practices but NOT fully certified yet

Canadian telephony surcharge ($0.03/min) is 2x the US rate - adds up at scale

System prompts over 3,500 tokens incur additional surcharges

AI live conversations can occasionally sound unnatural - needs testing

Required: Voice Likeness Licence
Before any voice cloning can begin, Sandra (or whichever employee is chosen) must sign a Voice and Likeness Licence. This covers: what the voice will be used for, how long the licence lasts, what happens if she leaves, and her right to revoke consent. A cloned voice is classified as biometric personal information under Canadian privacy law (PIPEDA). No licence = no voice cloning. Ben provides the template.

Platform B: Bland AI New Addition

What is it? Bland AI is a self-hosted, end-to-end AI calling platform. Unlike Retell (which connects multiple third-party APIs behind the scenes), Bland runs their own voice AI, their own telephony, and their own infrastructure. No third-party API hops means your data stays within their system - a significant advantage for healthcare privacy.

The headline: Bland AI is the only platform that explicitly claims PHIPA compliance - Ontario's healthcare privacy law. That's a big deal for DOCUdavit.

How It Works

The workflow is similar to Retell AI - create an account, clone a voice, write scripts, upload patient lists, and launch campaigns. Bland has a visual "pathway builder" for designing call flows. The key difference is what happens under the hood: all processing stays within Bland's infrastructure.

Current Pricing (Restructured December 2025)

Heads up: Bland AI recently restructured their pricing. The old $0.09/min rate that shows up on older review sites is gone. Here's what's current as of February 2026:
TierMonthly FeePer MinuteDaily Call LimitConcurrent Calls
Start (Free)$0$0.14/min10010
Build$299$0.12/min2,00050
Scale$499$0.11/min5,000100
EnterpriseCustom~$0.08-0.09 (est.)CustomCustom

Hidden Costs to Know About

💰
Failed call fee: Bland charges $0.015 per call attempt regardless of whether the call connects. If 40% of calls fail (busy, no answer, disconnected), that adds up. Example: 10,000 calls with 40% fail rate = ~$60 in failed-call fees. Scales proportionally with volume.
💰
Transfer time double-billing: If a call gets transferred (e.g., to a human agent at DOCUdavit), Bland bills both the AI rate AND the transfer rate for the transfer duration. This matters if live conversations include transfers.

Pilot Budget (1,200 Calls)

ItemCostNotes
Ben's setup & configuration$900 - $1,35012-18 hours @ $75/hr
Monthly subscription (Build tier)$299 - $499Minimum to get reasonable call limits
Call costs (1,200 x 1.5 min avg)~$198 - $216$0.11-0.12/min depending on tier
Failed call fees (est. 30% fail rate)~$5$0.015 x ~360 failed attempts
Total for pilot campaign$1,300 - $1,850 + HST

Scaled Budget Scenarios

Monthly VolumeEst. Monthly CostNotes
5,000 calls~$1,100 - $1,400Build/Scale tier + per-min + failed call fees
10,000 calls~$2,150 - $2,500Scale tier likely needed
50,000 calls~$6,500 - $8,000Enterprise tier required (5K/day limit on Scale)
100,000 calls~$12,000 - $14,000Enterprise negotiated rates - needs real quote

Scale Considerations

PHIPA compliance advantage: As volume grows, Bland AI's explicit PHIPA compliance claim becomes increasingly valuable. Processing healthcare data through a compliant platform reduces DOCUdavit's regulatory risk significantly.
Failed call fee impact: Bland's $0.015 per attempt (regardless of success) adds up. At 10,000 calls with 40% failure rate, that's $60/month in failed attempts. At higher volumes it scales proportionally. This fee structure favors high-quality contact lists.
Platform maturity risk: Bland AI is newer than Retell, which means both opportunity (better pricing, more responsive to enterprise needs) and risk (less battle-tested at massive scale). The pilot will reveal their actual reliability under DOCUdavit's use case.

Pros and Cons

Only platform explicitly claiming PHIPA compliance (Ontario healthcare law)

Self-hosted architecture - no third-party API hops = strongest data privacy story

Sub-400ms response latency (fast, natural conversations)

Visual pathway builder for designing call flows

Voice cloning: 5-15 clones depending on tier

Handles both voicemail and live conversations

Monthly subscription required even during slow months ($299-499 minimum)

Failed call fees add up with volume ($0.015/attempt regardless of success)

Pricing was restructured recently - current rates are higher than older reviews suggest

Scale tier maxes at 5,000 calls/day - Enterprise needed for higher volumes

Enterprise pricing requires negotiation - no public rates

PHIPA compliance claim needs verification (ask for documentation)

Required: Voice Likeness Licence
Same as Platform A - Sandra must sign a Voice and Likeness Licence before any voice cloning begins. No licence = no voice cloning. Ben provides the template.
Key question we need answered: Bland AI claims PHIPA compliance, but we haven't seen the certification or documentation. Before committing to this platform at scale, we need to verify this claim. During Phase 2, Ben will request their compliance documentation and, if necessary, have Stephen's legal team review it.

Platform C: Custom Twilio + ElevenLabs Build Most Complex

What is it? Build a custom phone system from scratch using Twilio (phone infrastructure) and ElevenLabs (AI voice). Ben writes all the code: call logic, voicemail detection, campaign management, dashboard, retry logic, audit logging - everything.

Why is it still on the table? One reason: cost at volume. A custom build is significantly cheaper per call than the platform options. The savings grow with volume - at sustained high usage, the upfront build cost pays for itself quickly.

The maintenance reality: While custom builds are cheaper at scale, they require ongoing maintenance and support that platform providers handle automatically. Retell AI and Bland AI guarantee system uptime, handle infrastructure scaling, and provide support teams. With a custom build, Ben becomes your infrastructure team - which means additional labor costs and dependency on a single developer. This is manageable but needs to be factored into the total cost of ownership.

How It Works

1
Set up Twilio - buy a Canadian phone number ($1.15/month), configure the account, complete business verification for high-volume calling.
2
Clone Sandra's voice in ElevenLabs - generate all audio files (one per doctor) and store them. Cancel ElevenLabs subscription after generating audio if ongoing cloning isn't needed.
3
Ben builds the call engine - a custom application that reads the patient CSV, calls each number via Twilio, uses Answering Machine Detection to route correctly, plays the right audio file, logs everything.
4
Ben builds a campaign dashboard - so Stephen's team can upload patient lists, launch campaigns, and monitor results without calling Ben.
5
Ben builds audit logging, multi-script support, retry logic, compliance features - everything that comes "out of the box" with a platform needs to be custom-built here.

Twilio Pricing Details

Twilio's Canada outbound rate: $0.014/min (pay-as-you-go)
Volume discounts are surprisingly shallow:
  • First 100K minutes: $0.014/min
  • Next 900K minutes: $0.0138/min (only 1.43% savings!)
  • You'd need 10M+ minutes to see meaningful discounts
Watch out for SIP Trunking "savings": Twilio SIP Trunking advertises $0.0095/min - looks cheaper. But "Canada - High Cost" rural routes cost $0.1485/min! If DOCUdavit's patient lists include rural Ontario, northern communities, or independent carriers, some calls could cost 10x the expected rate. Standard pay-as-you-go ($0.014/min flat) is safer.

Pilot Budget (1,200 Calls)

ItemCostNotes
Ben's build (full custom system)$3,000 - $5,00040-67 hours @ $75/hr. Higher than original estimate due to enterprise features needed: multi-script, campaign management, dashboard, audit logging.
Voice cloning consent docsIncluded above
Twilio calls (1,200 x 1.5 min avg)~$25$0.014/min
ElevenLabs + LLM + hosting~$50For pilot scale
Phone number$1.15/month
Total for pilot campaign$3,075 - $5,075 + HST

Scaled Budget Scenarios

Monthly VolumeEst. Monthly CostNotes
5,000 calls~$900 - $1,500Twilio + ElevenLabs + hosting + maintenance
10,000 calls~$1,200 - $2,000Twilio scales linearly, maintenance stays flat
50,000 calls~$2,500 - $4,000Significant savings over platforms at this level
100,000 calls~$4,000 - $6,0002-3x cheaper than platforms

Custom build costs include Ben's ongoing maintenance (~$750-$1,500/month). The per-call cost is lowest of all options, but the upfront build ($3,000-$5,000) and ongoing maintenance dependency must be factored in.

Scale Considerations

Perfect for campaign-based usage: Unlike platform subscriptions with monthly minimums, Twilio is pure pay-per-use. If DOCUdavit runs campaigns as doctors are signed rather than on a fixed schedule, the custom build only costs calling fees when actually making calls. No wasted subscription fees in quiet months.
Single point of failure: Ben becomes the infrastructure team. As volume grows, system reliability becomes more critical. If the custom system goes down during a campaign, there's no vendor support team to call - it's Ben's problem to fix. This operational risk needs to be weighed against the cost savings.
Maintenance cost reality: The ~$750-$1,500/month maintenance estimate assumes steady-state operation. Major feature requests, compliance updates, or scaling issues could require significantly more developer time. Factor in additional budget for unexpected maintenance spikes.

Pros and Cons

Cheapest ongoing cost per call - savings grow with volume

Maximum control over every detail of the system

Twilio is rock-solid, industry-standard Canadian telephony

Twilio AMD (Answering Machine Detection) is mature and accurate

HIPAA-eligible (Twilio has HIPAA-eligible products)

Unlimited concurrency after business verification

No platform lock-in - DOCUdavit owns the code

Highest upfront cost ($3,000-5,000 to build)

Ben builds and maintains everything - Stephen can't self-serve without the custom dashboard

Ongoing maintenance costs (Ben's time for bug fixes, updates, new features)

If Ben is unavailable, the system doesn't get updated

Takes weeks to build vs. days to configure a platform

Compliance is your responsibility - Twilio provides the pipes, you handle the rest

When this becomes the right choice: If DOCUdavit reaches sustained high volume (thousands of calls per week, consistently), the savings over a platform option justify the upfront build and ongoing maintenance. The pilot and early campaigns will reveal whether volume reaches that threshold. Until then, platforms are lower-risk.

Side-by-Side Comparison

Cost Comparison

Scenario ⭐ Retell AI 🛡️ Bland AI 🔧 Custom Twilio
First campaign (1,200 calls) $1,085 - $1,535 $1,300 - $1,850 $3,075 - $5,075
Monthly at 10K calls ~$1,500 ~$2,150 - $2,500 ~$700 - $1,200
Monthly at 50K calls ~$6,000 ~$6,500 - $8,000 ~$2,500 - $4,000
Monthly at 100K calls ~$12,000 ~$12,000 - $14,000 ~$4,000 - $6,000

All prices CAD + HST where applicable. Enterprise rates are estimates - actual quotes may vary.

Feature Comparison

Feature ⭐ Retell AI 🛡️ Bland AI 🔧 Custom Twilio
Canadian compliance (PHIPA) Working towards it, not certified Claims PHIPA compliance Your responsibility
HIPAA/BAA Included on Enterprise Available on Enterprise Twilio offers HIPAA-eligible
Live AI conversations Yes - built in Yes - built in Possible but complex to build
Voicemail detection Automatic Automatic Twilio AMD (mature, accurate)
Voice cloning Built into platform 5-15 clones per tier Via ElevenLabs (separate)
Dashboard for Stephen's team Built in Built in Ben builds it (custom)
Stephen can run it independently Yes, after training Yes, after training With custom dashboard, yes
Works on all phones Cell, landline, VoIP Cell, landline, VoIP Cell, landline, VoIP
Concurrency 20 (free) / unlimited (enterprise) 10-100 by tier / custom (enterprise) Unlimited after verification
Audit trail Full call logs + transcripts Full call logs Whatever Ben builds
Setup time 1-2 weeks 1-2 weeks 4-6 weeks
Ongoing maintenance None (platform managed) None (platform managed) Ben maintains it
Platform lock-in risk Medium (data portable) Medium (data portable) None (DOCUdavit owns code)

When Would You Pick Each Platform?

Bland AI (If Compliance is King)

  • Strongest Canadian compliance story (PHIPA claim)
  • Self-hosted architecture = best for data privacy
  • Worth getting an enterprise quote during Phase 2
  • Must verify PHIPA claim before committing

Custom Twilio (If Volume Justifies It)

  • Cheapest per-call cost - savings grow with volume
  • Maximum control and no lock-in
  • Only makes sense at sustained high volume (thousands of calls/week consistently)
  • Highest upfront cost and requires ongoing maintenance

The Hybrid Path (Our Recommendation)

  • Pilot on Retell AI (pay-as-you-go)
  • Get enterprise quotes from Retell + Bland with pilot data
  • Verify Bland's PHIPA claim
  • Choose the scale platform based on real data and real quotes
  • Consider custom Twilio only if sustained volume justifies the build cost

The Rules (Plain English)

Several Canadian laws and guidelines control what DOCUdavit can and can't do with automated calls. Here's what each one means in practice:

🏛️ CRTC (Canada's Phone Regulator)

✅ Custodian Authorization Confirmed: DOCUdavit has confirmed that, as custodian of the medical records on behalf of the doctor, they have the doctor's explicit permission to contact patients. Solicitation concerns do not apply - these are authorized custodian notifications about medical record access.

What it says: You CAN make automated informational calls. Automated sales calls require prior consent from each person.

What it means for us: With custodian authorization in place, our calls are clearly informational and authorized. That said, best practice is to keep the message purely informational - "Your doctor retired, your records are here, call us." Avoiding any mention of fees or services keeps us well clear of any telemarketing classification.

  • Calling hours: weekdays 9am - 9:30pm, weekends 10am - 6pm (patient's local time)
  • Must identify DOCUdavit and the purpose immediately
  • If the message is over 60 seconds, repeat the identification at the end
  • Penalties: up to $15,000 per call for violations

📵 Do Not Call List (DNCL)

Good news: The DNCL does NOT apply to DOCUdavit. DNCL only applies to telemarketing calls. DOCUdavit's calls are authorized custodian notifications - informational, not sales. No need to check the list. This saves significant complexity and cost.

🏥 CPSO (Ontario Medical Privacy Guidelines)

The big one for voicemails: You CANNOT leave personal health information on a voicemail. Why? You can't verify who's listening. Maybe the patient's spouse picks up. Maybe a roommate.

What it means: The voicemail must be GENERIC. No patient name. No "your medical records." Just: "Important message regarding Dr. Smith's practice. Please call us." The details only come when the patient calls back and DOCUdavit verifies it's actually them.

🔒 PHIPA (Ontario Health Privacy Law)

What it says: Patient data (names, phone numbers linked to a doctor) must be encrypted, access-controlled, and logged. DOCUdavit is an "agent of the custodian" (the retired doctor) and must protect this data at every step.

What it means for platform choice: Whatever platform we use needs encrypted data handling, audit logs, and the ability to delete data after campaigns. DOCUdavit's ISO 27001 certification helps a lot here - it demonstrates existing security practices.

As volume grows, this matters even more: Processing thousands of patient phone numbers through a third-party platform is a significant data flow. The platform's compliance posture becomes a critical decision factor.

🗣️ Voice Cloning (No Specific Law Yet, But...)

Canada has no voice cloning law yet. But we still need:

  • Written consent from the employee whose voice is cloned (a "Voice and Likeness Licence")
  • Clear terms about what happens if the employee leaves the company
  • The employee creates the voice clone in THEIR OWN account and shares it (platform requirement)
  • AI disclosure recommended (not legally required yet): "This is an automated message using a digital version of Sandra's voice"

Voice cloning becomes even more practical with volume. The same 10-20 audio files per doctor get reused across all calls for that doctor. The clone is generated once and used indefinitely (within the licence terms).

📞 Ringless Voicemail (Special Case)

Ringless voicemail is the least regulated option. CRTC Decision 2004-65 approved it. It's not classified as an ADAD (automated dialing device). The phone never rings, so most "nuisance call" rules don't apply. Still need to identify DOCUdavit in the message and follow CPSO voicemail privacy rules.

Ringless VM remains valuable as Round 2 of the cascade at any volume - catching patients who screen unknown callers.

The Problem: No Single Method Reaches Everyone

Whether it's 1,200 patients or 50,000 patients, the reality is the same: some have cell phones, some have old landlines, some never answer unknown numbers, some have disconnected numbers. No single calling method will reach 100% of them.

The solution is a cascade - try the best method first, then work down the list for anyone who wasn't reached.

The Coverage Cascade

1
Round 1: AI Phone Calls
Call all patients. The system automatically detects voicemail vs. human, leaves the right message, and logs the result. Retries patients who don't answer (up to 3 attempts at different times of day).

Expected reach: 70-85% of patients either get a voicemail or pick up the phone.
Cost at pilot: ~$180 for 1,200 calls
Cost scales linearly: ~$0.07-$0.15/min depending on platform and volume tier
2
Round 2: Ringless Voicemail Drop
For patients who never answered after 3 call attempts - drop a voicemail directly into their inbox without ringing the phone. Catches the "screeners" who ignore unknown callers but do check their voicemail.

Expected additional reach: 40-60% of the remaining patients.
Cost: ~$0.06-0.10 per drop (only for the unreached group)
3
Round 3: Canada Post Mailing
For anyone who couldn't be reached by phone at all - disconnected numbers, no voicemail, never responded. Send them a physical letter. DOCUdavit already does this today, so this isn't new work - it's just a smaller, targeted mailing instead of blasting the entire list.

Expected additional reach: 80-90% of remaining patients (some addresses may be outdated too).
Cost: DOCUdavit's existing mailing process. Much cheaper when it's 200 letters instead of 1,200.
4
Round 4 (Optional): SMS Text Message
For cell phone numbers that never answered calls or checked voicemail - a simple text: "Important notice from DOCUdavit Medical Records regarding Dr. Smith's practice. Please call 416-781-9083."

Note: SMS may fall under Canada's Anti-Spam Law (CASL) and could require different compliance. Needs further research before implementing.
Cost: ~$0.01-0.03 per text

Coverage Estimate at Pilot Scale (1,200 Patients)

RoundMethodPatients ReachedRunning TotalCost
1AI Phone Calls~840-1,02070-85%~$180
2Ringless Voicemail~70-215 more85-95%~$15-25
3Canada Post~50-150 more95-99%Existing process
4SMS (optional)Varies~99%+~$5
Total digital cost (Rounds 1-2)~$195-205

Coverage Estimate at Scale (Example: 10,000 Patients/Month)

RoundMethodPatients ReachedUnreachedMonthly Cost
1AI Phone Calls~7,000-8,5001,500-3,000$700-1,200
2Ringless Voicemail~600-1,800 more500-1,500~$90-180
3Canada Post~400-1,350 more50-250Existing process (much smaller)
Total digital cost (Rounds 1-2)$800-1,400/month

Costs scale linearly. At 50,000 patients/month: multiply by ~5. At 100,000: multiply by ~10. Actual volume depends on how many doctors DOCUdavit signs - see volume scenarios above.

Why this matters legally: Under Ontario's PHIPA (Section 42), DOCUdavit needs to prove they made "reasonable efforts" to notify each patient. A documented cascade - phone call, then voicemail drop, then physical letter - with logs at every step is an airtight defense.

How Tracking Works

After Round 1, every patient ends up in one of these categories:

StatusWhat HappenedNext Action
Voicemail DeliveredAI left a message on their voicemailWait for callback. Done.
Live ConversationPatient answered, AI delivered the messageDone.
Called BackPatient called the number backStaff handled it. Done.
No Answer (retrying)Rang but nobody picked upSystem retries automatically.
No Answer (max retries)Tried 3 times, never reachedMove to Round 2 (Ringless VM)
DisconnectedNumber is no longer in serviceMove to Round 3 (Canada Post)
Fax / InvalidHit a fax machine or invalid numberMove to Round 3 (Canada Post)

After each round, export the "unreached" list and feed it into the next method. As volume grows, this handoff can be automated so the cascade runs itself.

Project Timeline - Phased Approach

This timeline reflects the three-phase strategy: pilot first, evaluate, then scale.

Weeks 1-2: Pilot Setup & Test

Platform: Retell AI (pay-as-you-go)

WhenTaskWho
Week 1, Day 1-2Create Retell AI account, buy Canadian number, complete KYC business verificationBen
Week 1, Day 2-3Sandra records voice samples, clones voice in the platformSandra + Ben (guiding)
Week 1, Day 3-4Write voicemail and live-answer scripts, send to Stephen for approvalBen writes, Stephen approves
Week 1, Day 4-5Configure AI agent: call flow, scripts, calling hours, retry logicBen
Week 1, Day 5Prepare and sign Voice and Likeness LicenceBen provides, Sandra signs
Week 2, Day 1-2Test calls to our own phones - check voice quality, voicemail detection, script deliveryBen + Stephen
Week 2, Day 2-3Small pilot: call 10-20 real patients as a test batch. Monitor results.Ben runs, Stephen monitors

Weeks 2-3: Run Pilot Campaign

1,200 patients - the real test

WhenTaskWho
Week 2, Day 4Upload full patient list (1,200 numbers). Launch campaign.Ben (first time), Stephen watches
Week 2-3Monitor results. System auto-retries failed calls. Handle any issues.Ben monitors, Stephen's team handles callbacks
Week 3Round 1 complete. Run Round 2 (Ringless VM) and Round 3 (Canada Post) for unreached patients.Ben + Stephen decides

Weeks 3-4: Analyze Results & Get Enterprise Quotes

Turn pilot data into leverage

WhenTaskWho
Week 3Compile pilot results: delivery rate, callback rate, average call duration, voicemail detection accuracyBen
Week 3-4Contact Retell AI for enterprise pricing (with pilot data as leverage)Ben
Week 3-4Contact Bland AI for enterprise pricing + request PHIPA compliance documentationBen
Week 4Present enterprise options to Stephen with real data and real quotesBen + Stephen

Weeks 4-6: Decision on Scale Platform

Choose the long-term solution

WhenTaskWho
Week 4-5Stephen decides on scale platform based on quotes, compliance, and budgetStephen (Ben advises)
Week 5-6Sign enterprise agreement with chosen platform (or begin custom Twilio build)Stephen + Ben

Weeks 6-8: Enterprise Setup & First Scaled Campaign

Go big

WhenTaskWho
Week 6-7Configure enterprise account, set up multi-campaign workflows, create script templates for different scenariosBen
Week 7Train Stephen's team on running campaigns at scale (upload, launch, monitor, export)Ben trains, Stephen's team learns
Week 7-8Launch first scaled campaignStephen's team (Ben supports)
Week 8Deliver all documentation: compliance checklist, script templates, voice consent template, operations guideBen
Total timeline: ~8 weeks from kickoff to enterprise-scale operations. The pilot campaign is running by Week 2. Enterprise decision is made by Week 5. Stephen's team is operating independently by Week 8.
Dependencies (things that could slow us down):
  • Sandra's availability for the voice recording session
  • Stephen's turnaround time on script approval
  • Platform KYC verification (usually 1-2 business days)
  • Patient data - we need the CSV from the mailing house before we can test or launch
  • Enterprise quote turnaround from Retell AI and Bland AI (1-2 weeks typical)
  • If Custom Twilio is chosen, add 3-4 weeks for the build

What Could Go Wrong (And What We Do About It)

Every project has risks. As volume grows, some risks become more significant. Here's what we've identified and our plan for each.

High Impact Risks

📞
Platform doesn't work well with Canadian carriers
What could happen: Poor call quality, numbers flagged as spam by Bell/Rogers/Telus, low connection rates.
How likely: Low-medium. Both Retell and Bland support Canadian numbers, but we need to test with real campaigns.
Backup plan: The pilot is designed to catch this. If Canadian carrier delivery is poor on one platform, we try the other. If both struggle, Custom Twilio uses Twilio's industry-standard Canadian carrier relationships.
⚖️
CRTC complaint or regulatory pushback
What could happen: A patient complains to the CRTC about receiving an automated call. CRTC investigates. Higher call volumes mean more exposure surface.
How likely: Very low - DOCUdavit has confirmed custodian authorization from the doctor to contact patients, our calls are informational (not telemarketing), and we follow all ADAD rules.
Backup plan: Immediately pause the campaign. Review the complaint. DOCUdavit's custodian authorization, compliance documentation, and ISO certifications provide strong legal standing. If needed, switch to Canada Post mailings for that batch.
🛡️
PHIPA compliance gap
What could happen: None of the platforms are fully PHIPA-certified (Bland claims it, but we haven't verified). Processing patient phone numbers through a non-compliant platform could be a regulatory issue as volume grows.
How likely: Medium. This is the biggest open question in the project.
Backup plan: Phase 2 specifically addresses this. We verify Bland AI's PHIPA claim and check Retell's progress. If neither passes, Custom Twilio with Canadian-hosted servers gives us full control over data handling. DOCUdavit's ISO 27001 certification provides additional coverage.
🔒
Platform lock-in
What could happen: After committing to a platform with a monthly minimum, DOCUdavit discovers they need to switch. Migration costs, re-configuration, and downtime.
How likely: Medium if enterprise contracts are signed. Typically 6-12 month commitments.
Backup plan: The phased approach mitigates this. We pilot before committing. Enterprise contracts should include exit clauses. Patient data (phone numbers, call logs) is always exportable. The scripts and voice clones can be recreated on another platform.

Medium Impact Risks

💰
Volume pricing uncertainty
What could happen: Enterprise quotes come in higher than our estimates in this document.
How likely: Medium. Enterprise pricing is always negotiable, but the numbers here are estimates until we get real quotes.
Backup plan: Get quotes from both platforms and play them against each other. If platform pricing is too high, Custom Twilio offers the cheapest per-call rate. Having three options gives us negotiating leverage.
🗣️
Voice clone sounds robotic or unnatural
What could happen: Sandra's cloned voice doesn't sound convincing. Patients hang up or feel uncomfortable.
How likely: Medium. Quality varies based on recording quality and the platform.
Backup plan: Sandra records the messages herself - real voice, not AI. We lose the "AI-generated at scale" angle but the messages still work. Pre-record 10-20 versions (one per doctor) and upload as audio files. This actually simplifies compliance (no voice cloning consent needed).
📱
Low delivery rate - many patients unreachable by phone
What could happen: Old phone numbers, disconnected lines, elderly patients. Only 50-60% reached in Round 1.
How likely: Medium-high. Some records may be years old. Older patient lists will have more disconnected numbers.
Backup plan: This is exactly why the cascade exists. The phone campaign doesn't need to reach everyone - it just needs to reduce the mailing list to a manageable size.
📊
Low callback rate
What could happen: Patients hear the voicemail but don't call back. Generic voicemails have lower engagement than personalized ones.
How likely: Medium.
Backup plan: Adjust the script for warmth/urgency. Try different calling times. Follow up with Round 2 (ringless VM) as a reminder. The goal isn't 100% callbacks - it's proving "reasonable efforts" to notify.

Lower Impact Risks

🔐
Data breach or privacy incident
What could happen: Patient phone numbers exposed, call logs leaked, unauthorized access.
How likely: Low. All platforms are SOC 2 certified with encryption.
Backup plan: DOCUdavit's ISO 27001 certification + platform security + our compliance setup minimize this risk. If it happens: follow PHIPA breach notification rules (notify the custodian physician, they notify patients + IPC).
👤
Sandra leaves DOCUdavit
What could happen: The voice clone is tied to Sandra's account. If she leaves, she can revoke access.
How likely: Low short-term, inevitable long-term.
Backup plan: The Voice Likeness Licence defines what happens at termination. For future campaigns, clone a different employee's voice. Or switch to a stock AI voice (less personal but no dependency).
🌐
French language requirement
What could happen: Stephen needs French voicemails sooner than expected.
How likely: Low - we'll confirm on the Zoom call.
Backup plan: All platforms support French. A bilingual employee records French samples. We create a second set of audio files. Adds a few hours of work but doesn't change the architecture.

Platforms & Approaches We Evaluated

Before landing on the three platforms presented, we researched and evaluated a wide range of options. Here's what we looked at and why each was set aside.

AI Calling Platforms

🚫
Synthflow AI - synthflow.ai
No-code drag-and-drop call builder with strong stated compliance (HIPAA, SOC 2, ISO 27001, BAA included).
Why not: Zero Canadian compliance evidence - no PHIPA or PIPEDA mentions anywhere. Zero pricing transparency beyond $375/month Pro plan. Cannot confirm Canadian phone number support. No way to estimate costs at volume without a sales call. Too many unknowns for a healthcare operation.
🚫
Vapi - vapi.ai
Developer-focused voice AI orchestration layer.
Why not: HIPAA compliance costs $1,000/month as a separate add-on. No Canadian-specific compliance (no PHIPA, no PIPEDA). API wrapper architecture means patient data passes through multiple third-party services (Vapi + your chosen LLM + your chosen TTS + Twilio) - a data privacy risk for healthcare. No dashboard for non-technical users. Total pilot cost: ~$1,360 for 1,200 calls.
🚫
Air AI - air.ai
AI calling platform designed primarily for sales conversations.
Why not: Opaque pricing (must talk to sales). Limited voice cloning options. Unverified healthcare compliance. Built for long sales calls, not short medical notifications. Poor architectural fit for DOCUdavit's use case.

Ringless Voicemail Providers

Research finding: We found zero reliable data on bulk ringless voicemail pricing or Canadian delivery rates from any provider. No provider publishes bulk rates or Canadian carrier delivery statistics. Ringless VM remains viable as a backup tier (Round 2 of the cascade) where we send drops to unreached patients - not as a primary channel.
🔍
Slybroadcast - slybroadcast.com
US-based ringless voicemail provider. Only provider with any published pricing: $0.06-0.10/drop for small volume packages.
Status: Viable for Round 2 of cascade. US data residency is a PIPEDA concern for bulk patient data. No Canadian-specific compliance. No bulk pricing disclosed. "Select landlines" only for Canadian support.
🔍
Drop Cowboy - dropcowboy.com
Ringless voicemail service with built-in "Mimic AI" voice cloning.
Status: Could not verify Canadian number support, compliance posture, or healthcare suitability. Needs direct vendor contact to evaluate.
🔍
Voicelogic / Stratics Networks (Canadian companies)
Canadian-based providers - data residency advantage.
Status: Promising due to Canadian base, but zero detailed product information available. Pricing, features, compliance certifications all unknown. Worth contacting if ringless VM becomes primary.

Technical Approaches

🚫
ElevenLabs Batch Calling API
ElevenLabs' native batch calling feature that auto-dials from a CSV.
Why not: Incompatible with their Zero Retention Mode, meaning patient data would be processed and potentially retained on their servers. For healthcare data under PHIPA, this is a compliance issue on standard plans. Enterprise tier (with BAA) has unknown and likely expensive pricing.
🚫
Twilio + ElevenLabs Real-Time Integration (WebSocket)
Route live call audio through ElevenLabs for real-time AI voice during calls.
Why not: Adds $0.07/min ConversationRelay fee on top of Twilio's calling costs. More expensive than Retell AI and requires significantly more development work. Overkill when pre-generated audio works fine.
🚫
Twilio Studio (Visual Call Builder)
Twilio's drag-and-drop visual call flow builder.
Why not as primary: Still requires significant configuration and some coding for batch outbound campaigns. No built-in voice cloning. More control than Retell but more work for similar results. Kept as backbone of Platform C (Custom Build).
Total platforms and approaches evaluated: 14+
We looked at every viable option before narrowing down. The research covered Canadian telecommunications law (CRTC), healthcare privacy regulations (PHIPA, PIPEDA), voice cloning legality, DNCL exemptions, platform pricing at various volume tiers, and detailed cost modeling for each approach.

Next Steps

Here's how this project moves forward. Each step builds on the previous one.

1
Stephen reviews this document
Read through all the tabs. Pay special attention to the Strategy tab (the three-phase approach), the Side-by-Side tab (cost comparisons at scale), and the Risks tab. Come to the Zoom call with questions and a preference.
2
Zoom call - February 26
We walk through this together and make key decisions:
  • Confirm the phased approach - pilot on Retell AI, then decide at scale?
  • Live conversations vs. voicemail-only? - Does the AI need to talk to patients who pick up, or just leave messages?
  • How many script variations? - Recent retirement vs. years-old files? Different messaging per scenario?
  • Who is the voice? - Sandra? Someone else? Bilingual?
  • Patient data format - What does the spreadsheet from the mailing house look like?
  • Volume projections - How many doctors per year is DOCUdavit signing now? How quickly is that growing?
  • Campaign pacing - Do campaigns go out as doctors are signed, or in batches (e.g., quarterly)?
  • Budget comfort - What's the monthly budget range Stephen is comfortable with for calling costs?
3
Stephen answers key questions
  • Live AI conversations needed, or voicemail-only at scale?
  • How many script variations for different scenarios?
  • Rough split: cell phones vs. landlines in patient lists?
  • French - now or later?
  • Who will run campaigns day-to-day on Stephen's team?
4
Start the pilot on Retell AI
Ben sets up the account, Sandra clones her voice, we write the scripts, configure the system, and test with a small batch. Timeline: 1-2 weeks from kickoff.
5
Run the 1,200-patient pilot campaign
Full campaign with real patients. Monitor delivery rates, callback rates, voice quality, voicemail detection accuracy. Run the full coverage cascade (AI calls, then ringless VM, then Canada Post for unreached patients).
6
Analyze results together
Ben compiles the pilot data and presents it: what worked, what didn't, what needs adjustment. This data becomes our leverage for enterprise pricing negotiations.
7
Get enterprise quotes from Retell AI + Bland AI
With real pilot data, approach both platforms for enterprise pricing. Request Bland AI's PHIPA compliance documentation. Compare total cost of ownership across all three options.
8
Choose the scale platform
Based on pilot data, enterprise quotes, compliance verification, and budget - commit to the long-term solution. Sign enterprise agreement or begin custom Twilio build.
9
Build for scale
Configure the enterprise platform (or build the custom system), set up multi-campaign workflows, create script templates, train Stephen's team, and launch the first scaled campaign.
End result: DOCUdavit has a scalable, compliant, repeatable system for notifying patients as new doctors are signed. The pilot proves the concept for ~$1,085-$1,535. The ongoing platform scales with DOCUdavit's growth - from a few thousand calls per month to tens of thousands and beyond. Stephen's team operates it independently after training.
All prices in this document are in CAD + HST where applicable. Enterprise pricing is estimated until real quotes are obtained in Phase 2. This document was prepared by Ben Block, Pixel Block Studio, for Stephen Leibtag, DOCUdavit, February 2026.
DOCUdavit AI Calling Project | Pixel Block Studio | February 2026
Based on deep research into CRTC, PIPEDA, PHIPA, platform capabilities, and enterprise pricing