LensReading which lens this session carries.

Standard operating procedure · CS8B · Customer Service

Detractor Closed Loop

Transactional procedure owned by Voice of Customer in Customer Service. 6 numbered steps, 0 of them a person deciding and 6 of them agent work …

Procedure code

CS8B

Transactional

Rule versions in force

v1.8 · v4.5 · v2.6

3 governing rules stacked over it

In force since

2024-10-07

Earliest effective date across those rules

Last reviewed

2026-08-08

Latest review date across those rules

Rules approved by

1

Head of Customer Experience

Rule health

1/3

1 under review · 1 superseded

There is no document register behind this header. The version, the dates and the approver names are read off the governing rules this procedure runs inside, which is the closest thing the estate holds to a document control record. Nobody wrote these procedures. There is no document library behind this page and no Word file anywhere in the estate. Every procedure below is generated from rows this platform already holds: the line and its ordered stations, the owning team and the person accountable for it, the policy items bound to that team, and the governance gates seeded against the function. The steps, the owners, the gates, the approvers, the dwell times and the volumes are read straight off those rows. The sentences that join them together are generated. Read a procedure as the estate describing itself, not as a document somebody signed.

Purpose and scope

What this procedure is for and where it stops

To run detractor closed loop to one repeatable standard inside Voice of Customer, part of Customer Service.

Entry condition

Runs transactional. Starts when a request lands in the queue.

Exit condition

The unit clears close.

In scope

  • Every unit of detractor closed loop raised inside Voice of Customer, from the trigger below through to the final step.
  • 6 of the 6 steps, which run without a person present.
  • No decision on this line stops for a person; it runs end to end without one.

Out of scope

  • Anything outside the envelope set by the owning team. With no gate on this line, an out-of-envelope unit is refused rather than held.
  • Work that belongs to another function. This line records no handoff, so nothing leaves it mid-flow.
  • The 1 step carried on the shared AI GBS spine. They are done for this line but not by this function.

Who owns it

Runs the line

Voice of Customer Orchestrator

Accountable person

Head of Customer Experience

The end of the escalation path. Above them sits Customer Service Chief of Staff for the function.

That team’s remit

Owns feedback theme work end to end inside Customer Service.

That remit describes the whole team, not this one procedure, so its counts are larger than the ones on this page.

Autonomy

78% now · ceiling 78%

Ingestion and theme extraction are agentic at full volume.

The procedure, step by step

6 numbered steps · 0 of them stop for a person

A step is one station on the line.

No.StepWho does itWhat happensSystem of recordTime on the stepIn flight
01

Detect detractor

Agentworkflow

Feedback Ingestion Agent

Feedback Ingestion Agent performs this step unattended at the workflow layer, inside the envelope its owning team has set, and writes an evidence record naming the actor, the authority it acted under and the digests of what it read and wrote.Customer Relationship Management1.5 hrsstandard 3.5 hrs33
02

Assign owner

Agentworkflow

Theme Extraction Agent

Theme Extraction Agent performs this step unattended at the workflow layer, inside the envelope its owning team has set, and writes an evidence record naming the actor, the authority it acted under and the digests of what it read and wrote.Contact Center Platform2.1 hrsstandard 2.8 hrs19
03

Contact

Agentworkflow

Driver Analysis Agent

Driver Analysis Agent performs this step unattended at the workflow layer, inside the envelope its owning team has set, and writes an evidence record naming the actor, the authority it acted under and the digests of what it read and wrote.IT Service Management33 minstandard 48 min6
04

Resolve

Agentworkflow

Churn Signal Agent

Churn Signal Agent performs this step unattended at the workflow layer, inside the envelope its owning team has set, and writes an evidence record naming the actor, the authority it acted under and the digests of what it read and wrote.Workforce Management1.2 hrsstandard 2.0 hrs8
05

Verify

Agentworkflow

Closed-loop Follow-up Agent

Closed-loop Follow-up Agent performs this step unattended at the workflow layer, inside the envelope its owning team has set, and writes an evidence record naming the actor, the authority it acted under and the digests of what it read and wrote.Customer Relationship Management1.4 hrsstandard 2.1 hrs20
06

Close

GBSgbs

Closed-loop Follow-up Agent

Closed-loop Follow-up Agent performs this step unattended on the shared AI GBS transaction spine, outside the function, inside the envelope its owning team has set, and writes an evidence record naming the actor, the authority it acted under and the digests of what it read and wrote.Customer Relationship Management3.0 hrsstandard 4.2 hrs16

The swimlane

The same steps, laid out by who is holding the work

Three lanes: a person deciding, an agent working, and the shared services spine.

Person0 stations and 0% of the dwellAgent5 stations and 70% of the dwellShared spine1 station and 30% of the dwell1 crossing between lanes
Human
decides
Agent
does the work
GBS
shared spine
System
attributed by rule
Customer Relationship Management
Contact Center Platform
IT Service Management
Workforce Management
Customer Relationship Management
Customer Relationship Management
Click any station to see who does it, what it costs in time, the rule that gates it and the system attributed to it.

Run the procedure

One unit walked along that swimlane on the happy viable agentified path

Press run and a single unit enters at station 01. Each station takes exactly the dwell this platform records for it and is held by whoever the estate says holds it.

speed
worked clock
00:00
allowance clock
00:00
stations cleared
0/6
the happy path, worked time0 min of 9.7 hrs
the same run against its allowance0 min of 16 hrs
Human
decides · 0
Agent
does the work · 5
GBS
shared spine · 1
run log

Nothing has happened yet.

where the worked time goes9.7 hrs a unit
Agent6.8 hrs · 70%Shared spine3.0 hrs · 30%1 crossing between lanes
what makes this path viable
  • The lanes are the recorded lanes. 0 of the 6 stations stop for a person and every one of them still does on this run.
  • There is no decision point on this procedure, so nothing was waived to make the run clean.
  • The owning team is held to a 78% autonomy ceiling and this run sits at 100% unattended, inside it.
  • 4 systems are attributed across the stations, and 0 of them are connected. Nothing in this run has been watched executing against a real system of record.
what would have to change

This procedure stops for nobody.

what this run is, and what it is not

This is a run, not a forecast.

Happy means nothing goes wrong: no station raises an exception, no gate sends the unit back, no rework loop fires and nothing sits in a queue between stations.

The second clock is the allowance.

A decision may be handed to the agent lane only if two things hold …

The run reads the station rows only.

What this run does not model: arrival patterns, contention between procedures for the same person, shift patterns, weekends, learning curves, and the cost of anything.

Run it again, going wrong

The same unit, the same stations, broken the way the estate already records breaking

This is the same unit on the same stations, breaking.

No break below was chosen.

One play head, two tracks, the same scale. The clean run stops when it runs out of stations; the other one keeps going.

As written

6 stations, nothing waiting, nothing sent back

0 min of 9.7 hrs

now Detect detractor · Feedback Ingestion Agent · 1.5 hrs

As the ledger has it

the same stations, plus 2 categories the estate already counts

0 min of 14 hrs

now Detect detractor · Feedback Ingestion Agent · 1.5 hrs

personagentshared spinework the break addsnobody working it

What breaks, and where it is counted

No break below was chosen.

What the two runs say together

2 counted categories land on this procedure.

What this run cannot claim

These breaks are shown together on one unit so the shape of a bad day fits on one screen.

Two clocks run. Worked time is the sum of the time the work is actually being done …

Roles and responsibilities

7 named parties

The responsibility grid is assigned by a rule, not lifted from a chart.

PartyRACIStepsDutyEscalates to

Voice of Customer Orchestrator

orchestrator

Runs the line0Sequences this line, holds its timetable and decides what has to surface to a person. Raises to Head of Customer Experience when a unit falls outside the envelope or confidence drops below the floor.

Feedback Ingestion Agent

agent

A3% autonomy · ceiling A3%

99% clean · 3% overridden

Responsible1Executes the voice of customer step it owns, posts its evidence, and hands the unit to the next stage.Escalates to Head of Customer Experience when the unit falls outside the decision envelope or confidence drops below the floor.

Theme Extraction Agent

agent

A3% autonomy · ceiling A3%

93% clean · 3% overridden

Responsible1Executes the voice of customer step it owns, posts its evidence, and hands the unit to the next stage.Escalates to Head of Customer Experience when the unit falls outside the decision envelope or confidence drops below the floor.

Driver Analysis Agent

agent

A3% autonomy · ceiling A3%

89% clean · 3% overridden

Responsible1Executes the voice of customer step it owns, posts its evidence, and hands the unit to the next stage.Escalates to Head of Customer Experience when the unit falls outside the decision envelope or confidence drops below the floor.

Churn Signal Agent

agent

A3% autonomy · ceiling A3%

94% clean · 15% overridden

Responsible1Watches voice of customer continuously. Escalates to Head of Customer Experience when the unit falls outside the decision envelope or confidence drops below the floor.

Closed-loop Follow-up Agent

agent

A3% autonomy · ceiling A3%

90% clean · 8% overridden

Responsible2Executes the voice of customer step it owns, posts its evidence, and hands the unit to the next stage.Escalates to Head of Customer Experience when the unit falls outside the decision envelope or confidence drops below the floor.

Head of Customer Experience

person

Accountable0Accountable for this procedure and for the envelope the agents run inside. The end of the escalation path for this line.

Decision points and escalation

0 places this procedure stops

This procedure has no decision point.

Handoffs out of this procedure

Nothing leaves this procedure for another function. It completes inside Voice of Customer.

The rules this procedure runs inside

3 governing rules

Voice of Customer Decision Envelope

under review

CS8-POL-200 · envelope · vv1.8

Agents in this lane may act without a human when the feedback theme sits inside the stated value, risk and confidence envelope.

Approved by Head of Customer Experience · in force 2025-04-01 · reviewed 2026-07-29

Binds Feedback Ingestion Agent, Theme Extraction Agent, Driver Analysis Agent, Closed-loop Follow-up Agent, Journey Friction Agent

EU · UK · US

Voice of Customer Evidence Standard

active

CS8-POL-201 · evidence · vv4.5

Every autonomous decision writes inputs, the rule version applied, the model and prompt version, the output and a reversal path.

Approved by Head of Customer Experience · in force 2025-05-11 · reviewed 2026-08-08

Binds Feedback Ingestion Agent, Theme Extraction Agent, Driver Analysis Agent, Closed-loop Follow-up Agent, Journey Friction Agent

US · Canada

Voice of Customer Escalation Rule

superseded

CS8-POL-202 · escalation · vv2.6

Escalation is mandatory when confidence falls below the floor, when two options sit inside the confidence band, or when a break condition on a ratified position fires.

Approved by Head of Customer Experience · in force 2024-10-07 · reviewed 2026-07-19

Binds Feedback Ingestion Agent, Theme Extraction Agent, Driver Analysis Agent, Closed-loop Follow-up Agent, Journey Friction Agent

US · Canada

Systems this procedure touches

4 named · 0 connected

System attribution is a rule, not a reading.

SystemVendorDomainCriticalityStepsConnection
Customer Relationship ManagementSalesforce Sales Cloudcrmcritical3modeled
Contact Center PlatformGenesys Cloud CXservicehigh1modeled
IT Service ManagementServiceNow ITSMitsmhigh1modeled
Workforce ManagementNICE WFMservicemedium1modeled

0 of the 4 systems on this procedure is connected to the platform, and none of the twenty-six in the estate register is. 3 of them are marked as taking a write back, which is a property of the system, not a live path from here.

How it performs

End to end

9.7 hrs

Summed from the time each step sits, standard 15.5 hrs — running at 63% of the standard.

Touchless

82%

Agent share

100%

A week

3,980

In flight

102

Effort a week

0 human minutes · 583 agent minutes

Volume multiplied by the time on each step.

Assurance over this procedure

4 governance gates sit above it

The twenty-four controls and eighteen exception classes in this platform are held at estate level …

GateWhat trips itWho releases itClockWaivable

Refund or remedy above $500

approval

Any single remedy exceeding $500 in customer valueService manager4 business hoursNo

Vulnerability or hardship indicator

escalation

Any signal of hardship, bereavement, distress or safety riskTrained human specialistImmediateNo

Legal complaint or regulatory reference

escalation

Any legal threat, regulator mention or formal complaintLegal and service leadership2 hoursNo

Departure from published remedy

approval

Any resolution outside the published remedy catalogService manager1 business dayNo

What this document is and is not

These procedures describe the modeled estate.

Actions

What is waiting on a person

What one procedure document gives you, and what to check before you treat it as the standard.

Operations

What this desk is allowed to start

A surface that only reports is not operable.

Trigger and bound

A procedure document prints purpose, scope, entry and exit, the numbered steps with the actor on each, the roles and their RACI position, the swimlane, the decision points and escalation, the handoffs, the governing rules with version and approver, the systems by rule and the timings.

Live observability

What the record shows right now

The whole library, by lane, so a single document can be read against the estate it came from.

Current distribution

2,748 steps

Agent, inside the function1,38951%
Agent, on the shared spine85131%
Person deciding at a gate50818%

Is policy and strategy coming to fruition

Whether the written intent is holding here

Half. The document is complete and every actor on it is measured

Not holding on the record

A procedure here carries a version, an approver, an in-force date and a last-review date.