Sub-function
Quality & Coaching
Owns quality review work end to end inside Customer Service. Runs 3 lines across 16 stations, drains the repeatable share into no shared tower, and holds 3 human gates.
Estate rating
BBB
71 / 100
Scoring at 100 percent coverage is a genuine agentic unlock. Coaching a named person on their performance is delivered by their manager, not a model.
Agents
10
Lines
3
Units / wk
14,523
Timetable vs actual
19.3h → 20.1h
Cost / unit
$8.65
was $22
Run-rate saving
$10.4M
annualized at this volume
The 10 agents running this sub-function
Grouped by what they are for, not by where they sit. The agent org is process-shaped.
Quality Orchestrator
Owns the quality & coaching lane end to end. Sequences the other agents, holds the timetable, and decides what surfaces to a human.
ceiling A3 · escalates to Escalates to Director, Service Quality when the unit falls outside the decision envelope or confidence drops below the floor.
Interaction Sampling Agent
Executes the quality & coaching step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Service Quality when the unit falls outside the decision envelope or confidence drops below the floor.
Calibration Agent
Executes the quality & coaching step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Service Quality when the unit falls outside the decision envelope or confidence drops below the floor.
Coaching Plan Agent
Executes the quality & coaching step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Service Quality when the unit falls outside the decision envelope or confidence drops below the floor.
Compliance Screening Agent
Executes the quality & coaching step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Service Quality when the unit falls outside the decision envelope or confidence drops below the floor.
Agent Performance Agent
Executes the quality & coaching step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Service Quality when the unit falls outside the decision envelope or confidence drops below the floor.
Quality Scoring Agent
Watches quality & coaching continuously. Detects drift, quantifies it, and routes what matters without waiting for a reporting cycle.
ceiling A3 · escalates to Escalates to Director, Service Quality when the unit falls outside the decision envelope or confidence drops below the floor.
Bias Monitor Agent
Holds the rules that bind every other agent in quality & coaching. Versions them, tests them against live decisions, and blocks work that breaches them.
ceiling A3 · escalates to Escalates on any decision that would breach a live policy version, with the clause cited.
Quality Policy Agent
Holds the rules that bind every other agent in quality & coaching. Versions them, tests them against live decisions, and blocks work that breaches them.
ceiling A3 · escalates to Escalates on any decision that would breach a live policy version, with the clause cited.
Quality & Coaching Challenger Agent
Adversarial reviewer for quality & coaching. Argues the opposite case on every position and flags where the evidence does not carry the claim.
ceiling A3 · escalates to Escalates when a ratified position is still running against a break condition it flagged.
Estate rating breakdown
Seven control dimensions. Judgment readiness runs against autonomy on purpose.
People
What the humans stopped doing, and what they do now.
Redeployed into agent supervision, calibration and coaching.
Lines running in this sub-function
Each line is a workflow. Click a line to walk it station by station.
Strategy positions this sub-function holds
An agent that only executes is a robot. These are the calls it made, the argument against each one, and what would prove it wrong.
Quality & Coaching Operating Position
Supersededv2Is the current cost per quality review defensible against external comparators once inference spend is counted in full?
Hold the ceiling at A3 for quality & coaching. Scoring at 100 percent coverage is a genuine agentic unlock. Coaching a named person on their performance is delivered by their manager, not a model. Raise it only after two consecutive quarters where the override rate stays under five percent and every override has a written cause.
confidence
83%
The challenge — Quality & Coaching Challenger Agent
Quality & Coaching Challenger Agent argues the recommendation leans on 4 quarters of data from a period with no volume shock. The confidence band overlaps the alternative, and the position does not say what it would take to be wrong. Recorded as a dissent, not a block.
Break conditions
- ·Override rate rises above 7 percent for two consecutive months
- ·Cost per quality review stops falling while volume keeps rising
- ·A control failure in this lane reaches a customer or a regulator
Evidence gaps
- ·No external comparator on a like-for-like unit definition
- ·Exception cases under $30k are sampled, not fully measured
| Alternative considered | Cost | Risk | Verdict |
|---|---|---|---|
| Hold the current position | $548k run rate | Known and priced. Cedes ground if comparators move faster. | live |
| Raise the ceiling one level now | $148k to build controls | Override rate is 10 percent; raising the ceiling before that settles imports the error into production. | rejected on evidence |
| Move the exception tail to the spine | $148k transition | Loses local context. Rework risk on the cases that are hardest to recover. | under review |
Policy register
The rules the agents above are bound by. Version, owner, approver, and the agents each rule constrains.
| Ref | Rule | Scope | Owner agent | Approved by | Version | Status |
|---|---|---|---|---|---|---|
| CS9-POL-200 | Quality & Coaching Decision Envelope Agents in this lane may act without a human when the quality review sits inside the stated value, risk and confidence envelope. Outside it, the unit holds at a gate with a named approver and a running clock. binds 5 agents · US · Canada | envelope | Bias Monitor Agent | Director, Service Quality | v4.8 | Superseded |
| CS9-POL-201 | Quality & Coaching Evidence Standard Every autonomous decision writes inputs, the rule version applied, the model and prompt version, the output and a reversal path. An action with no evidence record is treated as a control failure, not a fast decision. binds 5 agents · LATAM · US | evidence | Bias Monitor Agent | Director, Service Quality | v4.2 | Active |
| CS9-POL-202 | Quality & Coaching Escalation Rule 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. Director, Service Quality owns the response clock. binds 5 agents · Global | escalation | Bias Monitor Agent | Director, Service Quality | v1.3 | Active |
| CS9-POL-203 | Quality & Coaching Autonomy Ceiling The ceiling for this lane is 72 on the platform scale. Scoring at 100 percent coverage is a genuine agentic unlock. Coaching a named person on their performance is delivered by their manager, not a model. The ceiling is a governance decision, not a technical limit, and only Director, Service Quality can propose moving it. binds 5 agents · Global · EU | ceiling | Bias Monitor Agent | Director, Service Quality | v3.6 | Active |