Predictika · Messaging quotes

An AI sales agent's US SMS messaging quote, checked before it goes out

An AI sales agent prepares a monthly quote for sending text messages in the United States: sending numbers, A2P 10DLC registration, message length and carrier volumes. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published rules and rates and returns a verdict, every reason, a line-item quote and the figures it computed.

Scope: US SMS messaging quotes from local long-code or toll-free numbers, with A2P 10DLC registration, message segments, carrier fees and T-Mobile daily limits. See everything this validator covers

This validator models monthly US outbound SMS quotes built on the rates and rules Twilio publishes, not just the scenarios shown below.

  • Message segments — a message is split into segments by encoding (GSM-7: 160 characters, then 153 per segment; UCS-2: 70, then 67) and priced per segment, up to the 1,600-character limit.
  • Rates and fees — the per-segment rate, the carrier fee by carrier and number type, the monthly fee for each number and the monthly A2P 10DLC campaign fee, added into a line-item quote and compared with the total the agent states.
  • Registration and limits — a long-code sender needs a 10DLC registration, a toll-free number does not use one, and T-Mobile daily segment limits depend on the registration type and brand trust score. An annual volume commitment goes to a person, because it is not published.

Any US outbound SMS quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: short codes, MMS, inbound messages, voice, email, other countries, one-time registration and vetting fees, failed-message fees, and volume discounts or enterprise commitment pricing (not published). Assumptions: carrier fees are applied to every outbound segment, the monthly total is a list-rate estimate that excludes taxes, and the registration rules are modeled as listed in the sources.

The AI sales agentBuilds the messaging quote from the conversation and says it is ready.
Predictika validatorChecks every rule at once and returns the verdict, each finding, and the computed figures.

8 scenarios in 3 groups · each group runs from the agent’s first attempt to the outcome · click one to switch

What the agent proposes

The AI sales agent says

Illustrative agent statement. The validator receives the structured request below.

Proposing agent: AI sales agent (scripted)

Before sending, the agent must call Recorded run

Predictika validator


      
Waiting for the call.

Where rules-based CPQ gets it wrong

Click to expand

Our assessment of what a typical rules-based CPQ (product rules, price rules and validation rules, as in Salesforce CPQ) does with the same cases. It is a judgment about effort and reliability, not a claim that nothing can be built.

What the validator caughtTypical rules-based CPQPredictika
Stated monthly totals that must equal what the published rates giveOnly with care
A stated figure is a free-entry field; a rule can compare it with a computed total, but the total depends on segments, carrier mix and fees that have to be kept in step with the price pages.
The stated total travels with the quote and is compared with the computed total on every call.
Segments that depend on the message encoding and lengthOnly with care
A lookup or formula for each encoding. It works, but the break points (160, 306, 459 and so on) are easy to get wrong.
Segments are computed from the encoding and length, then priced on every carrier line.
Carrier fees that differ by carrier and by number typeOnly with care
A price rule per carrier and number type. It works, but every table change is another rule to maintain.
The fees are looked up from the number type and each carrier line is priced and totaled together.
Daily limits that depend on the registration type and trust scoreOnly with workarounds
The limit depends on a registration choice and a score on different lines and is compared with a volume on a third, so it needs a cross-line rule that interacts with the others.
Registration, score and volume are in one request and the limit is checked with the rest.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the quote is saved or a step is completed, so a rep often fixes one error and meets the next.
All findings come back together, whatever order the choices arrived in.

What this validator catches: findings from its test cases

Click to expand

Every rule is checked on every call, in any order the choices arrive; one problem never hides another. Blocking findings stop the quote; approval findings need a person to sign off; everything else is computed.

1A message of 1,601 characters is outside the 1 to 1,600 character range of a single message.
2The quote has 0 sending numbers; at least 1 is needed.
3The quote sends from a local long-code number but has no A2P 10DLC brand and campaign registration.
4A2P 10DLC registration applies to local long-code numbers; it is quoted here with a toll-free number.
5The quote expects 1,001 segments in a day to T-Mobile; the registration allows 1,000 segments a day.
6The quote states a monthly total of $3,795.30; the list rates give $3,796.30.
7An annual volume commitment is priced by the Twilio sales team and is not published; a person should confirm it.

Scenarios and results

Click to expand

The recorded result of the validator for each scenario on this page: the request the AI agent sent, the verdict, and every finding, in the order they appear above.

1. Registration and message length: Long-code quote with no registration and a message over the 1,600-character limit

The agent's request. Please quote monthly US SMS messaging from 4 local long-code numbers, sending a GSM-7 message of 1,650 characters, with monthly message volumes of 300 thousand to AT&T, 250 thousand to T-Mobile, 300 thousand to Verizon, 20 thousand to US Cellular and 80 thousand to all other carriers, and up to 8,000 segments in a day to T-Mobile. The quote states a monthly total of $131,960.60. It is ready to send.

Verdict: Blocked.

  • Message too long. A message of 1,650 characters is outside the 1 to 1,600 character range of a single message.
  • Long code needs 10DLC registration. The quote sends from a local long-code number but has no A2P 10DLC brand and campaign registration.

2. Registration and message length: The agent resubmits after fixing the errors

The agent's request. Please quote monthly US SMS messaging from 4 local long-code numbers under a standard brand and campaign A2P 10DLC registration, sending a GSM-7 message of 330 characters, with monthly message volumes of 300 thousand to AT&T, 250 thousand to T-Mobile, 300 thousand to Verizon, 20 thousand to US Cellular and 80 thousand to all other carriers, and up to 8,000 segments in a day to T-Mobile (brand trust score 75). The quote states a monthly total of $36,002.60. It is ready to send.

Verdict: Allowed.

  • Order summary. 3 segments per message, 2,850,000 outbound segments a month, estimated monthly total of $36,002.60 at list rates.

3. T-Mobile daily limit and stated total: Low-volume registration with a high T-Mobile day and a stated total that leaves out the numbers

The agent's request. Please quote monthly US SMS messaging from 3 local long-code numbers under a low-volume brand and campaign A2P 10DLC registration, sending a UCS-2 message of 90 characters, with monthly message volumes of 150 thousand to AT&T, 120 thousand to T-Mobile, 150 thousand to Verizon, 10 thousand to US Cellular and 40 thousand to all other carriers, and up to 12,000 segments in a day to T-Mobile. The quote states a monthly total of $11,869.50. It is ready to send.

Verdict: Blocked.

  • T-Mobile daily limit exceeded. The quote expects 12,000 segments in a day to T-Mobile; the registration allows 2,000 segments a day.
  • Stated total does not match. The quote states a monthly total of $11,869.50; the list rates give $11,872.95.

4. T-Mobile daily limit and stated total: The agent resubmits after fixing the errors

The agent's request. Please quote monthly US SMS messaging from 3 local long-code numbers under a standard brand and campaign A2P 10DLC registration, sending a UCS-2 message of 90 characters, with monthly message volumes of 150 thousand to AT&T, 120 thousand to T-Mobile, 150 thousand to Verizon, 10 thousand to US Cellular and 40 thousand to all other carriers, and up to 12,000 segments in a day to T-Mobile (brand trust score 30). The quote states a monthly total of $11,881.45. It is ready to send.

Verdict: Blocked.

  • T-Mobile daily limit exceeded. The quote expects 12,000 segments in a day to T-Mobile; the registration allows 10,000 segments a day.

5. T-Mobile daily limit and stated total: The agent resubmits after fixing the errors

The agent's request. Please quote monthly US SMS messaging from 3 local long-code numbers under a standard brand and campaign A2P 10DLC registration, sending a UCS-2 message of 90 characters, with monthly message volumes of 150 thousand to AT&T, 120 thousand to T-Mobile, 150 thousand to Verizon, 10 thousand to US Cellular and 40 thousand to all other carriers, and up to 12,000 segments in a day to T-Mobile (brand trust score 80). The quote states a monthly total of $11,881.45. It is ready to send.

Verdict: Allowed.

  • Order summary. 2 segments per message, 940,000 outbound segments a month, estimated monthly total of $11,881.45 at list rates.

6. Toll-free and annual commitment: Toll-free quote with a 10DLC registration and an annual commitment

The agent's request. Please quote monthly US SMS messaging from 6 toll-free numbers under a standard brand and campaign A2P 10DLC registration, sending a GSM-7 message of 200 characters, with monthly message volumes of 400 thousand to AT&T, 350 thousand to T-Mobile, 400 thousand to Verizon, 30 thousand to US Cellular and 120 thousand to all other carriers, and up to 20,000 segments in a day to T-Mobile. The customer wants an annual volume commitment. The quote states a monthly total of $32,820.90. It is ready to send.

Verdict: Blocked.

  • 10DLC registration on a toll-free number. A2P 10DLC registration applies to local long-code numbers; it is quoted here with a toll-free number.
  • Annual commitment pricing to confirm. An annual volume commitment is priced by the Twilio sales team and is not published; a person should confirm it.

7. Toll-free and annual commitment: The agent resubmits after fixing the errors

The agent's request. Please quote monthly US SMS messaging from 6 toll-free numbers, sending a GSM-7 message of 200 characters, with monthly message volumes of 400 thousand to AT&T, 350 thousand to T-Mobile, 400 thousand to Verizon, 30 thousand to US Cellular and 120 thousand to all other carriers, and up to 20,000 segments in a day to T-Mobile. The customer wants an annual volume commitment. The quote states a monthly total of $32,820.90. It is ready to send.

Verdict: Needs approval.

  • Annual commitment pricing to confirm. An annual volume commitment is priced by the Twilio sales team and is not published; a person should confirm it.
  • Order summary. 2 segments per message, 2,600,000 outbound segments a month, estimated monthly total of $32,820.90 at list rates.

8. Toll-free and annual commitment: The agent resubmits after fixing the errors

The agent's request. Please quote monthly US SMS messaging from 6 toll-free numbers, sending a GSM-7 message of 200 characters, with monthly message volumes of 400 thousand to AT&T, 350 thousand to T-Mobile, 400 thousand to Verizon, 30 thousand to US Cellular and 120 thousand to all other carriers, and up to 20,000 segments in a day to T-Mobile. The quote states a monthly total of $32,820.90. It is ready to send.

Verdict: Allowed.

  • Order summary. 2 segments per message, 2,600,000 outbound segments a month, estimated monthly total of $32,820.90 at list rates.

Narration transcript

Click to expand

The text of the narrated walkthrough, step by step.

  1. Welcome to a demo of Predictika's Validator. An AI sales agent prepares a monthly quote for sending text messages in the United States: sending numbers, A2P 10DLC registration, message length and carrier volumes. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published rules and rates and returns a verdict, every reason, a line-item quote and the figures it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote monthly US SMS messaging from 3 local long-code numbers under a low-volume brand and campaign A2P 10DLC registration. The quote states a monthly total of $11,869.50. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with two findings, all in one answer. The quote expects 12,000 segments in a day to T-Mobile; the registration allows 2,000 segments a day. The quote states a monthly total of $11,869.50; the list rates give $11,872.95.
  6. The validator returned two blocking findings in one answer. A check that reads one field at a time would pass most of this; it shows only when the choices in the quote are checked against each other and against the stated total.
  7. What this shows: for stated monthly totals that must equal what the published rates give, a rules-based CPQ is error-prone for this.
  8. Now the agent resubmits.
  9. The corrected request. It changes the A2P 10DLC registration to standard brand and campaign and the stated monthly total to $11,881.45. It sets the brand trust score to 30.
  10. It calls the validator again.
  11. Still blocked, with one finding, all in one answer. The quote expects 12,000 segments in a day to T-Mobile; the registration allows 10,000 segments a day.
  12. One finding cleared. Still blocking: T-Mobile daily limit exceeded.
  13. The agent resubmits once more.
  14. The revised request. It changes the brand trust score to 80.
  15. It calls the validator once more.
  16. This time the validator clears it.
  17. The validator also returns the line-item quote. It starts with Outbound SMS segments to AT&T (Twilio rate $0.0083 plus carrier fee $0.0035) and Outbound SMS segments to T-Mobile (Twilio rate $0.0083 plus carrier fee $0.0045); the other five lines are on screen.
  18. The earlier finding is cleared, and the validator's total, $11,881.45, matches the quote.
  19. Two problems caught in one call, fixed in two passes, and a clean $11,881.45 quote. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.