Main site

Telecom AI agent · Plan recommendation

Plan-Recommendation AI Agent

Check the consent basis, compare published rate plans, upgrades and add-ons, surface the broadband label alongside the offer, and hold the recommendation for the named adviser, who decides whether anything changes.

Typical delivery
4–6 weeks
Deployment
Your stack
Adviser approval
Consent-checked
After launch
Agent Care

What this agent does

Builds the comparison, not the authorisation

In

  1. 01

    Account, tariff and usage records arrive from the billing, CRM and product-catalogue systems in scope.

  2. 02

    The consent basis on the account is read first, and no comparison is built where the basis is missing.

Reason

  1. 03

    Published plan terms, the price card and the broadband label are normalised into one comparable shape.

  2. 04

    Eligibility rules configured for the market decide which plans may appear in the comparison at all.

  3. 05

    Each figure shown is bound to the published term it came from, and anything the terms leave open is marked.

Decide

  1. 06

    Material restrictions — throttling thresholds, add-a-line and trade-in conditions — travel with the headline.

  2. 07

    Location and roaming signals stay out unless express prior authorisation is recorded for that customer.

Out

  1. 08

    The comparison, the consent basis and the adviser's decision are kept, so a later complaint is answered from it.

  2. 09

    Write actions run only inside the boundaries agreed at implementation; changing a plan is not one of them.

Product statement

The agent proposes a comparison; the named adviser decides whether it is shown, and the carrier stays the seller of record.

Example workflow

One recommendation, record to release

  1. 1Account record receivedBilling account, product catalogue, price card and published label
  2. 2Consent basis checkedThe approval tier recorded for this customer, and what it permits the comparison to use
  3. 3Comparison builtPlan options, restrictions and confidence
  4. 4Controls appliedPublished-term checks, restriction checks, market eligibility rules and confidence threshold

No human action required

Stages 1 to 4 run unaided, and no plan moves at any of them — the agent is comparing, and the adviser's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold
High confidence

Goes to the named adviser to release.

Low confidence

Adds a compliance read first.

Adviser approval

The comparison is held with its published sources, its restrictions and the confidence.

Approve · Amend · Send to compliance review

Approved — released to the adviser

  1. 6Sales systems updatedOnly where write access and approval policy allow it
  2. 7Outcome evaluatedAmendment rate, restriction-disclosure outcomes, label surfacing and post-sale complaints

Amendments

Every adviser amendment is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Changing a rate plan, or adding a billable add-on.
    • Verifying the customer's authorisation for that change.
    • Using usage data where the consent basis is missing.
    • Quoting a term that is not on the published price card.

  • Automation boundary

    Agent acts unaided

    • ✓Compare published plans inside the category the account already holds.
    • ✓Surface the broadband label next to the plan it belongs to.
    • ✓Check the consent basis on file before a comparison is built.
    • ✓Carry each restriction with its headline, and hold for the adviser.

    Any write stays inside the boundaries agreed at implementation, and never moves the plan itself.

    • Offering a product outside the customer's own category.
    • Using location or roaming signals to shape an offer.
    • Calling a device lease a purchase, or a phone free.
  • Changes to eligibility, consent or approval rules.

Example output

One comparison, annotated

Everything the agent shows is attached to the published term it was taken from.

Recommendation output · single account

Illustrative example
Account
Mobile · two lines
Line shown
Unlimited data, with the speed threshold shown beside it
Quoted from
Published price card
Consent basis
Total-service, on file
Confidence
88%
Disclosure shown
Broadband label link

As received

Taken from the published price card and the label on file — nothing on this side is written by the agent.

Published terms used

  • Price-card entry
  • Broadband label
  • Consent record

Why this comparison

It compares inside the category the account already holds — the adviser's call.

What the score decides

Below the configured threshold the comparison takes a compliance read before.

Action

ApproveAmendSend to compliance review

Value

Where AI adds value

The same four claims, placed at the point in the workflow where each one applies.

Where the value lands

Value 01 – 04

Every comparison

From the published terms

03Comparison

Compare from the price card

Draw on the published plan terms, the label on file and the consent basis recorded for that customer.

01Approved path

Compare, and show the label

Routine plan comparisons arrive already built, with their restrictions attached.

02Human review

Send review to the risky offers

Flagged restrictions and low-confidence comparisons are marked, so the adviser's read starts where the risk sits.

04

Build an evidence trail

The comparison, the consent it relied on and the adviser who released it stay together.

Integrations

Typical integrations

Five system groups connect to the same agent. Which of them are in scope is decided in discovery.

  • Billing and charging

    • Amdocs
    • Netcracker
    • CSG
    • Optiva
    • Ericsson

  • Product catalogue

    • Published price card
    • Broadband consumer labels

  • CRM and care

    • Salesforce
    • Dynamics 365
    • Pega
    • ServiceNow

Agent

Plan recommendation

  • Reads the terms
  • Builds the comparison
  • Holds for approval

  • Order and sales

    • Order management
    • CPQ
    • Retail POS
    • self-service

  • Observability & evaluation

    • OpenTelemetry
    • Langfuse
    • Supported monitoring/evaluation sources

Integration availability depends on the client's existing systems and API access.

Agent controls

Six layers between the model and the offer

The layers nest. What each one misses is named in the map below.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modePull the agent back to the published price card when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, comparison-rule and market-configuration changes.Track
L4TraceabilityRecord the terms used, the consent basis, the restrictions shown and the release.Record
L3Adviser approvalHold comparisons for the named adviser; it governs release, not whether the comparison is right.Gate
L2Policy guardrailsTest comparisons against the published terms and the recorded consent tier; a failure returns them.Restrict
L1Confidence thresholdsRoute low-confidence comparisons to a compliance read before the adviser sees them.Require review
Model coreComparison built — plan options, restrictions, label link and confidence
L1 – L2
Test whether a comparison may stand
L3
Puts the release in an adviser's hands
L4 – L5
Show what the comparison was built from
L6
Reverts to the published price card when signals degrade

How Nestack evaluates it

Evaluate the recommendation workflow — not only the plan that was shown.

Coverage runs the whole depth of the workflow, and every layer is cut by slice.

Surface — the comparison the customer sees

  1. E1Final-output evaluationDid each figure shown match the published term behind it?
  2. E2Step-level evaluationDid the agent use the right consent basis, price card and market rules?
  3. E3Tool evaluationDid it read the correct account and the current price card?
  4. E4Confidence calibrationDo low-confidence comparisons actually attract more adviser amendments?
  5. E5Slice evaluationHow does performance change across specific plan families?
  6. E6Business outcomeHow many comparisons needed an amendment, or a correction after the sale?

Floor — the outcome the carrier answers for

Failure modes

Where each failure originates in the agent

Seven failure modes, placed at the stage each one starts.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • ZR-03

      Superseded price card read

      A term is quoted from a price card the carrier has since replaced.

    Stage gathers

    Account, price card, label and consent record

  2. 02 · Reasoning

    2 modes

    • ZR-04

      Consent tier assumed

      A global setting stands in for the approval recorded on the account.

    • ZR-06

      Restriction left off the claim

      An unlimited headline is compared without the threshold behind it.

    Stage proposes

    Plan options, restrictions and confidence

  3. 03 · Tool / write

    2 modes

    • ZR-02

      Cross-category offer built

      A comparison is assembled outside the category on the account.

    • ZR-05

      Location signal used

      Roaming data shapes an offer with no express authorisation on file.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • ZR-01

      Label not surfaced

      A broadband plan is shown without its consumer label beside it.

    Stage returns

    The comparison the adviser releases to a customer

  5. 05 · Change / Version

    1 mode

    • ZR-07

      Silent comparison regression

      A model or rule change widens what the comparison will assert.

    Stage tracks

    Model, prompt, comparison rules and market config

  • Sev-1 · a plan changed without authorisation
  • Sev-2 · a wrong term reaches the customer
  • Sev-3 · price card stale, offer routes to review
See the complete Telecom failure-mode catalogue

Affected slices

Overall accuracy can hide one plan family

Aggregate comparison accuracy can sit inside its band while bundled broadband and mobile carries most of the amendments. Nestack reports the amendment rate by slice, not only in total.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Bundled broadband and mobile5.3%3.3×Review
Promotional and trade-in offers3.8%2.4×Review
Legacy and withdrawn plans2.4%1.5×Watch
Single-line mobile renewals1.1%0.7×Normal

Bar: adviser-amendment-rate lift vs. single-line renewal baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

A cycle ends in a test, not a note

A cycle is done when the miss has become a test the next release has to survive. That suite is what the next comparison shown is measured against.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Adviser-amendment rate rises in a plan family.

  2. 02

    Diagnose

    Not the model first — the price card, the consent record and the rules are read until one cause holds.

  3. 03

    Improve

    Version-stamp the change and attach the comparisons that exposed it.

  4. 04

    Verify

    The affected cases run again, and a fail stops the release.

  5. 05

    Learn

    It becomes a standing test, and the comparison rules change with it.

  6. Learn → Detect

    The return edge. The next detection is measured against a suite one case longer.

Typical build scope

Twelve workstreams across six weeks

The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, comparison workflow, evaluation, integration, then production validation and handover.

Workstream

Week 1Week 2Week 3Week 4Week 5Week 6

  1. 01Recommendation workflow discovery and boundary definition.Week 1
  2. 02Billing and catalogue source assessment.Week 1, Week 2
  3. 03Consent-tier, eligibility and disclosure-rule mapping.Week 1, Week 2
  4. 04Account and price-card ingestion.Week 2
  5. 05Comparison logic and term binding.Week 2, Week 3
  6. 06Confidence scoring and flag routing.Week 3
  7. 07Adviser approval workflow.Week 3, Week 4
  8. 08Billing and sales-system integration.Week 5
  9. 09Consent and disclosure cases.Week 4, Week 5
  10. 10Guardrails and approval controls.Week 4
  11. 11Comparison-trail instrumentation.Week 5, Week 6
  12. 12Deployment, documentation and Agent Care handover.Week 6

12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallel

Final scope and sequence confirmed in discovery

Engagement tiers

What each tier includes

Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.

Capability✓ in scope · — not at this tierPilotOne market, one plan familyProductionProduction billing systemsAdvancedMultiple markets / brands
Introduced at Pilot
Comparison from published terms✓✓✓
Adviser approval✓✓✓
Comparison-accuracy baseline✓✓✓
Introduced at Production
Reporting by plan family—✓✓
Approval workflow in your systems—✓✓
Approved record write-back—✓✓
Billing-system integration—✓✓
Introduced at Advanced
Multi-market price and term rules——✓
Multi-stage sales approvals——✓
High comparison volume——✓
Multi-market plan controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build price
Confirmed after discovery based on integrations, workflow complexity, transaction volume, approval controls and deployment requirements.
Separate from build
Build pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.

What we need from you

What you bring, and what we build with it

Each input maps to a piece of build scope and a week in the delivery timeline.

  1. 01Your plan catalogue and published price card

    Price-card ingestion and published-term binding

    Week 1

  2. 02Representative recommendations already made

    Comparison baseline, term binding and restriction extraction

    Week 2

  3. 03Your consent tiers and disclosure rules

    Consent-tier, eligibility and disclosure-rule mapping

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    Billing and catalogue assessment, then integration setup

    Week 2

  5. 05Comparisons that should not have been shown

    Disclosure cases and the evaluation suite

    Week 4

  6. 06What must reach an adviser before a plan changes

    Confidence scoring, flag routing, guardrails and approval controls

    Week 3

  7. 07Named advisers to review comparisons

    Adviser approval workflow, then pilot and production validation

    Weeks 5–6

Nothing else is required

Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

Phases are drawn over the weeks they actually occupy, which is why week 5 doubles up rather than padding.

Phase

W1

W2

W3

W4

W5

W6

  1. DiscoveryW1
  2. BuildW2 – W3
  3. EvaluateW4 – W5
  4. Pilot & LaunchW5 – W6

Week focus

W1Recommendation workflow discovery, consent mapping and the boundary

W2Billing and catalogue integration, and the comparison baseline

W3Comparison workflow, confidence logic and approval controls

W4Evaluation suite, disclosure checks and failure-mode testing

W5Sales-system integration, pilot comparisons and targeted corrections

W6One sales cycle compared under the care team, then handover

Reading the band
Each bar spans only the weeks its work is named in. The fifth week genuinely carries two kinds of work.
At the end of W6
The last checks clear on live comparisons and monitoring moves to Agent Care.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Telecom AI agent

Build a plan-recommendation agent around your consent basis.

Bring us your price card, your consent tiers and your disclosure rules. A named adviser signs the comparison before a customer sees it, and the boundary is drawn around that signature.

Typical delivery
4–6 weeks
Deployment
Your billing and CRM
Adviser approval
Consent-checked
After launch
Agent Care available

Nestack Agents · Plan recommendation

AGT-TL-02 · Agent Care available after launch

Build a plan-recommendation agent

Four questions so the call starts from your actual setup — then pick a time that suits you.

About you
Your customers

No obligation. We’ll map the workflow, name the automation boundary and tell you if an agent is the wrong answer.