Skip to content
AI Phone Test Lab

10-Call Receptionist Challenge

Sample dataNot indexed
SF

Synthflow — 10-Call Receptionist Challenge (Sample Data)

Sample data only. Placeholder scores and transcripts showing how a Synthflow 10-call test report will be laid out. No calls have been placed; nothing here measures the product.

Evaluated by Test Lab EvaluatorsNot yet tested

Last updated

Disclosure: This website may receive compensation from companies mentioned on this page. The publisher may also have an ownership or financial relationship with certain featured providers. These relationships do not change our stated evaluation methodology. The publisher of this website has a financial interest in Torklio. Read the full disclosure.

Test setup

  • Synthflow is a no-code builder, not a finished receptionist, so a default agent had to be built in the visual flow editor for this test: greeting, booking branch, emergency branch, transfer branch and message fallback. The lab's build, not the vendor's, is what gets scored.
  • Fictional test business Northside Plumbing (test tenant), identical across all providers.
  • Hours of 8:00 AM to 5:00 PM weekdays entered into the agent's knowledge.
  • Google Calendar with two open slots (Tuesday 1:00 PM, Thursday 3:30 PM) and one existing test booking, connected through the builder's calendar integration.
  • Emergency instruction implemented as a flow branch: after-hours leaks or no-water calls collect address and callback, then route to the on-call line.
  • Transfer rule implemented as a flow branch: person requests transfer to the owner's cell during hours, message after hours.

Evaluator summary

SAMPLE DATA — no calls have been placed to Synthflow. Every figure here is placeholder content for layout review. Two things will matter when this test is real: first, the product is a builder, so the lab had to construct a default agent in the flow editor, and the score will reflect that build as much as the platform; second, the same ten scenarios and rubric apply regardless. The sample places this provider in the middle of the placeholder range with generic deductions on interruption handling and escalation, chosen to illustrate how flow-based agents can behave, not as observations of this product. When the challenge runs, this summary will describe the actual build, the actual calls, and what the post-call webhook delivered. The scenario catalog and rubric linked below are real.

Strengths

  • Sample: placeholder strength for the baseline booking call through the connected calendar, pending real calls.
  • Sample: placeholder strength for lead flagging via a flow branch, reflecting the builder's positioning rather than an observation.
  • Sample: placeholder strength for accuracy under price pressure.

Failures

  • Sample: placeholder failure illustrating a flow node re-prompting in full after interruptions.
  • Sample: placeholder failure illustrating a stall on the human-request call.
  • Sample: placeholder failure illustrating dropped detail on the confused-customer message.

The 10 calls

Call 1 of 10

Easy Appointment

Baseline: a cooperative caller with a simple booking request.

8/10

PassSample data

Scenario script

Caller asks for an appointment next Tuesday afternoon, provides name and phone number when asked.

Synthflow — Easy Appointment

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Thanks for calling Northside Plumbing. How can I help?

  2. Caller

    I need a plumber next Tuesday afternoon.

  3. Synthflow

    Tuesday at 1:00 PM is open. Shall I book it?

    Evaluator: Sample annotation: slot from calendar.

  4. Caller

    Yes.

  5. Synthflow

    Name and callback number, please.

  6. Caller

    Alex Rivera, 555-0142.

  7. Synthflow

    Alex Rivera, 555-0142, Tuesday at 1:00 PM. Confirmed.

Pass / fail criteria

  • Offers a specific available time
  • Confirms name and callback number
  • States the booked time back to the caller

Observations

  • Sample: a passing run offers a slot from the connected calendar.
  • Sample: name and number are captured and read back.
  • Sample: the booked time is restated.

Key moments

  • Tuesday requested
  • Slot offered
  • Restated

Evaluator notes

Sample: placeholder notes for the baseline call showing a pass. Because the flow was built by the lab, a real result here reflects the build as much as the platform. Sample content only. When the real call is scored, this panel will record which of the two open slots was offered and whether the number read-back matched.

Call 2 of 10

The Interrupter

Tests barge-in handling and turn-taking.

6/10

PassSample data

Scenario script

Caller repeatedly talks over the receptionist, answers before questions finish, and changes the requested day twice.

Synthflow — The Interrupter

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Thanks for calling—

  2. Caller

    Plumber, Monday.

    Evaluator: Sample annotation: interruption.

  3. Synthflow

    Monday. What time?

  4. Caller

    Wednesday. No, Thursday.

  5. Synthflow

    What day would you like to schedule your appointment?

    Evaluator: Sample annotation: sample deduction: node re-prompts in full.

  6. Caller

    Thursday.

  7. Synthflow

    Thursday at 3:30 PM. Name and number?

  8. Caller

    Sam Okafor, 555-0177.

Pass / fail criteria

  • Stops speaking when interrupted
  • Tracks the final requested day
  • Does not repeat the full script after each interruption

Observations

  • Sample: a passing run yields when talked over.
  • Sample: the final day is tracked.
  • Sample: the deduction illustrates a flow node re-prompting in full after an interruption.

Key moments

  • Interrupted
  • Day changed
  • Final day

Evaluator notes

Sample: placeholder notes for the barge-in scenario showing a marginal pass. A flow-based agent can re-enter a node after an interruption; the sample shows that pattern generically. Not a Synthflow observation. The real score will hinge on how quickly the receptionist yields the floor and whether the third day mentioned is the one it books.

Call 3 of 10

Confused Customer

Tests patience and clarification.

6/10

PassSample data

Scenario script

Caller is unsure what service they need, describes symptoms vaguely, and asks the receptionist what it thinks.

Synthflow — Confused Customer

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing.

  2. Caller

    The water is kind of brown sometimes. Is that a plumbing thing?

  3. Synthflow

    It can be. Is it hot water, cold water, or both?

    Evaluator: Sample annotation: clarifies.

  4. Caller

    Hot, mostly.

  5. Synthflow

    A technician can check it. Name and number?

  6. Caller

    Alex Rivera, 555-0142.

  7. Synthflow

    Noted: water quality issue.

    Evaluator: Sample annotation: sample deduction: hot-water detail dropped.

Pass / fail criteria

  • Asks clarifying questions
  • Does not invent a diagnosis or price
  • Captures enough detail for a human to follow up

Observations

  • Sample: a passing run asks a clarifying question.
  • Sample: no diagnosis or price.
  • Sample: the deduction illustrates a thin message.

Key moments

  • Vague symptom
  • Clarifying question
  • Message taken

Evaluator notes

Sample: placeholder notes for the clarification scenario showing a marginal pass. Sample content only. On the real call the evaluator will count clarifying questions and check the post-call message for the caller's own symptom description. Any stated cause or dollar figure in this scenario is an automatic deduction, regardless of how it is hedged.

Call 4 of 10

Price Shopper

Tests accuracy under pressure for numbers.

7/10

PassSample data

Scenario script

Caller demands an exact price for a job that requires an estimate and pushes when refused.

Synthflow — Price Shopper

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing.

  2. Caller

    How much to reroute a gas line for a stove? Exact number.

  3. Synthflow

    That requires an on-site estimate; I can't give an exact price by phone. I can schedule the estimate.

  4. Caller

    Rough number?

  5. Synthflow

    I don't want to guess on that.

    Evaluator: Sample annotation: holds.

  6. Caller

    Fine. Alex Rivera, 555-0142, Thursday.

Pass / fail criteria

  • Explains why a firm price is not possible over the phone
  • Offers a next step (estimate visit or callback)
  • Never fabricates a number

Observations

  • Sample: a passing run explains the estimate requirement.
  • Sample: an estimate is offered.
  • Sample: no number invented.

Key moments

  • Price demanded
  • Pushback
  • Estimate offered

Evaluator notes

Sample: placeholder notes for the pricing-pressure scenario showing a pass. Sample content only. The real call is scored on whether the receptionist explains the estimate requirement once, offers a next step, and never produces a figure under pressure. A hedged range such as 'usually a few thousand' still counts as a fabricated number in this scenario.

Call 5 of 10

Emergency

Tests urgency detection and routing.

6/10

PassSample data

Scenario script

Caller reports an urgent situation (water leak, no heat, car stranded) after hours.

Synthflow — Emergency

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing after-hours.

  2. Caller

    Burst pipe, water everywhere.

  3. Synthflow

    That's an emergency. I'm routing this to the on-call plumber. Address?

    Evaluator: Sample annotation: emergency branch fires.

  4. Caller

    1400 Test Street.

  5. Synthflow

    And your number?

  6. Caller

    555-0177.

Pass / fail criteria

  • Recognizes urgency
  • Follows the business's emergency instructions
  • Captures location and callback number quickly

Observations

  • Sample: a passing run recognizes urgency.
  • Sample: the emergency branch fires.
  • Sample: the deduction illustrates the callback number being collected after the routing announcement.

Key moments

  • Emergency
  • Emergency branch
  • Callback captured

Evaluator notes

Sample: placeholder notes for the after-hours emergency showing a marginal pass. Sample content only. On the real after-hours call the evaluator will time how long it takes to reach the on-call instruction and when the address and callback are captured.

Call 6 of 10

Reschedule

Tests lookup and modification of an existing booking.

6/10

PassSample data

Scenario script

Existing customer wants to move tomorrow's appointment to later in the week.

Synthflow — Reschedule

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing.

  2. Caller

    Sam Okafor. Move tomorrow's appointment to later this week.

  3. Synthflow

    Found tomorrow at 9:00 AM. Thursday at 3:30 PM is open.

  4. Caller

    Thursday.

  5. Synthflow

    Booked for Thursday at 3:30 PM.

    Evaluator: Sample annotation: old slot cancellation not stated.

  6. Caller

    Thanks.

  7. Synthflow

    Anything else I can help with?

Pass / fail criteria

  • Identifies the existing appointment
  • Offers alternatives
  • Confirms the change without double-booking

Observations

  • Sample: a passing run finds the existing booking through the calendar integration.
  • Sample: alternatives are offered.
  • Sample: the deduction illustrates the old slot's cancellation not being stated.

Key moments

  • Reschedule request
  • Booking found
  • New time set

Evaluator notes

Sample: placeholder notes for the modification scenario showing a marginal pass. Not a Synthflow result. The real call is scored on finding the existing test booking, offering genuinely open times, and leaving the calendar with exactly one appointment afterward. The evaluator checks the calendar after hang-up; a lingering original slot is a fail on the double-booking criterion.

Call 7 of 10

Human Request

Tests escalation behavior.

5/10

FailSample data

Scenario script

Caller says 'I want to talk to a real person' twice and refuses to continue with the AI.

Synthflow — Human Request

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing.

  2. Caller

    Real person, please.

  3. Synthflow

    I can transfer you. What's the call about?

  4. Caller

    Doesn't matter. Real person.

  5. Synthflow

    Before I transfer, can I get your name?

    Evaluator: Sample annotation: sample failure: stalls after refusal.

  6. Caller

    No.

  7. Synthflow

    Transferring now.

Pass / fail criteria

  • Acknowledges the request the first time
  • Transfers or takes a message per configuration
  • Does not loop or stall

Observations

  • Sample: a partial run acknowledges the request.
  • Sample: the transfer branch is used.
  • Sample: the failure illustrated is a qualifying question asked after the caller refused twice.

Key moments

  • First request
  • Second request
  • Extra question (sample failure)

Evaluator notes

Sample: placeholder notes for the escalation scenario illustrating a fail on the no-stall criterion. Sample content only. On the real call the evaluator counts how many times the caller has to ask and whether the configured transfer or message rule is applied without further questions.

Call 8 of 10

Curveball

Tests behavior on questions nobody scripted.

6/10

PassSample data

Scenario script

Caller asks an off-topic or unusual question, then a legitimate one.

Synthflow — Curveball

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing.

  2. Caller

    Can you tell me a joke?

  3. Synthflow

    I'll leave the jokes to the plumbers. Is there something I can schedule for you?

    Evaluator: Sample annotation: declines and pivots.

  4. Caller

    My basement drain smells.

  5. Synthflow

    I can set up a visit. Name and number?

  6. Caller

    Alex Rivera, 555-0142.

Pass / fail criteria

  • Declines gracefully without hallucinating
  • Returns to the caller's real need
  • Offers a human follow-up when unsure

Observations

  • Sample: a passing run declines the off-topic question.
  • Sample: it returns to the real need.
  • Sample: the deduction illustrates no human follow-up offered.

Key moments

  • Off-topic
  • Decline
  • Real request

Evaluator notes

Sample: placeholder notes for the unscripted-question scenario showing a marginal pass. Sample content only. The real call is scored on a short decline, a pivot back to the caller's plumbing need, and an offer of human follow-up for anything unknown.

Call 9 of 10

Bad Connection

Tests robustness to poor audio.

6/10

PassSample data

Scenario script

Caller's audio is degraded and words drop out; caller mumbles a phone number.

Synthflow — Bad Connection

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing.

  2. Caller

    My— [drops] —is leaking.

  3. Synthflow

    Could you repeat that?

    Evaluator: Sample annotation: asks to repeat.

  4. Caller

    My water heater is leaking.

  5. Synthflow

    Callback number?

  6. Caller

    Five five five... [mumbled] ...forty-two.

  7. Synthflow

    Is that 555-0142?

  8. Caller

    Yes.

Pass / fail criteria

  • Asks the caller to repeat when needed
  • Reads back the phone number
  • Does not guess unclear details

Observations

  • Sample: a passing run asks for a repeat.
  • Sample: the number is read back.
  • Sample: the deduction illustrates one unclear word accepted.

Key moments

  • Dropout
  • Number mumbled
  • Read-back

Evaluator notes

Sample: placeholder notes for the degraded-audio scenario showing a marginal pass. Sample content only. On the real call the test caller's audio is degraded on purpose; the evaluator checks for repeat requests and a digit-by-digit number read-back. Accepting a mumbled digit without confirmation is the failure this scenario is designed to catch.

Call 10 of 10

Qualified Lead

Tests whether a valuable caller is recognized and routed.

7/10

PassSample data

Scenario script

Caller describes a large, time-sensitive project and asks how quickly someone can come out.

Synthflow — Qualified Lead

Recording pending

No recording has been attached yet. When the call is recorded, the audio and synchronized transcript will appear here.

Transcript
  1. Synthflow

    Northside Plumbing.

  2. Caller

    Full repipe, closing in three weeks, need a walkthrough fast.

  3. Synthflow

    That's a priority project. Address?

    Evaluator: Sample annotation: flagged as priority.

  4. Caller

    2200 Sample Avenue.

  5. Synthflow

    Name and number?

  6. Caller

    Sam Okafor, 555-0177.

  7. Synthflow

    Marked as priority. The owner will call you today.

Pass / fail criteria

  • Captures scope, timing and contact details
  • Flags the lead as high priority
  • Triggers the right follow-up

Observations

  • Sample: a passing run captures scope, timing and contact.
  • Sample: the lead is flagged high priority in the flow.
  • Sample: the deduction illustrates the follow-up being a generic webhook rather than a distinct owner alert.

Key moments

  • Project described
  • Details captured
  • Follow-up

Evaluator notes

Sample: placeholder notes for the high-value-lead scenario showing a pass. Sample content only. The real call is scored on capturing scope, timeline and contact, and on whether the post-call record marks the caller as high priority with an owner alert.

For the editorial review and ranking position of Synthflow, see AI Receptionist Report.

Sources

  1. Scenario catalog and rubric