LensReading which lens this session carries.
Engineering/Developer Experience

Sub-function

Developer Experience

Owns developer request work end to end inside Engineering. Runs 3 lines across 16 stations, drains the repeatable share into the AI-OPS tower, and holds 2 human gates.

orchestrator Developer Experience Orchestratorhuman owner Director, Developer Platform routes into ai-ops

Estate rating

A

78 / 100

autonomy 85%cap 90%

Environment provisioning and toolchain setup are fully self-service and touchless. Only platform roadmap choices need a human.

Agents

8

Lines

3

Units / wk

13,955

Timetable vs actual

14.9h → 15.7h

Cost / unit

$13

was $36

Run-rate saving

$16.7M

annualized at this volume

The 8 agents running this sub-function

Grouped by what they are for, not by where they sit. The agent org is process-shaped.

OrchestratorOwns the queue and arbitrates between desks.

Developer Experience Orchestrator

Owns the developer experience lane end to end. Sequences the other agents, holds the timetable, and decides what surfaces to a human.

ObserveA3152 / 24h91%7% ovr$7.27/task

ceiling A4 · escalates to Escalates to Director, Developer Platform when the unit falls outside the decision envelope or confidence drops below the floor.

AI GBSRuns the shared transaction spine.

Build Time Agent

Runs the repeatable portion of developer experience inside the shared transaction spine at spine cost and spine controls.

AI GBSA41,860 / 24h93%7% ovr$0.55/task

ceiling A4 · escalates to Escalates to Director, Developer Platform when the unit falls outside the decision envelope or confidence drops below the floor.

Onboarding Automation Agent

Runs the repeatable portion of developer experience inside the shared transaction spine at spine cost and spine controls.

AI GBSA43,866 / 24h91%4% ovr$0.54/task

ceiling A4 · escalates to Escalates to Director, Developer Platform when the unit falls outside the decision envelope or confidence drops below the floor.

TaskExecutes stations on a line.

Environment Provisioning Agent

Executes the developer experience step it owns, posts its evidence, and hands the unit to the next stage.

WorkflowA4332 / 24h93%4% ovr$0.35/task

ceiling A4 · escalates to Escalates to Director, Developer Platform when the unit falls outside the decision envelope or confidence drops below the floor.

Tooling Support Agent

Executes the developer experience step it owns, posts its evidence, and hands the unit to the next stage.

WorkflowA42,263 / 24h90%7% ovr$0.44/task

ceiling A4 · escalates to Escalates to Director, Developer Platform when the unit falls outside the decision envelope or confidence drops below the floor.

ObserveWatches signals and watches the agents.

Friction Sensing Agent

Watches developer experience continuously. Detects drift, quantifies it, and routes what matters without waiting for a reporting cycle.

ObserveA467 / 24h96%13% ovr$8.82/task

ceiling A4 · escalates to Escalates to Director, Developer Platform when the unit falls outside the decision envelope or confidence drops below the floor.

StrategyForms and defends a position.

Platform Roadmap Agent

Authors positions on developer experience. Frames the question, models the options, and writes a recommendation a human can ratify or reject.

StrategyA217 / 24h96%9% ovr$5.24/task

ceiling A4 · escalates to Escalates when two options sit inside the confidence band and the evidence cannot separate them.

ChallengerPaid to disagree before a human has to.

Developer Experience Challenger Agent

Adversarial reviewer for developer experience. Argues the opposite case on every position and flags where the evidence does not carry the claim.

StrategyA2179 / 24h89%14% ovr$9.11/task

ceiling A4 · 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.

Control Coverage85
Evidence Quality88
Override Discipline83
Data Integrity75
Recovery Readiness69
Cost Transparency78
Judgment Readiness61

People

What the humans stopped doing, and what they do now.

headcount on this work62.930.0 FTE

Redeployed into cross-function process redesign.

inference cost per unit$3.05

Lines running in this sub-function

Each line is a workflow. Click a line to walk it station by station.

13 clear3 evidenced2 held
EN9AEnvironment RequestTransactional · 5 stations

Request

1 live

Validate

1 live

Provision

1 live

Verify

2 live

Notify

2 live

EN9BFriction RemediationTransactional · 6 stations

Sense signal

1 live

Diagnose

1 live

Draft fix

1 live

Owner accept

3 q

Ship

23 q

Measure

4 live

EN9CDeveloper OnboardingTransactional · 5 stations

Trigger

1 live

Provision toolchain

1 live

Assign path

2 live

Verify readiness

26 q

Manager confirm

2 q

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.

EN9-POS-100

Developer Experience Operating Position

Rejectedv3

Is the current cost per developer request defensible against external comparators once inference spend is counted in full?

Hold the ceiling at A4 for developer experience. Environment provisioning and toolchain setup are fully self-service and touchless. Only platform roadmap choices need a human. Raise it only after two consecutive quarters where the override rate stays under five percent and every override has a written cause.

confidence

76%

The challenge — Developer Experience Challenger Agent

Developer Experience 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 6 percent for two consecutive months
  • ·Cost per developer request 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 $15k are sampled, not fully measured
Alternative consideredCostRiskVerdict
Hold the current position$671k run rateKnown and priced. Cedes ground if comparators move faster.live
Raise the ceiling one level now$1474k to build controlsOverride rate is 11 percent; raising the ceiling before that settles imports the error into production.rejected on evidence
Move the exception tail to the spine$232k transitionLoses local context. Rework risk on the cases that are hardest to recover.under review
authored by Platform Roadmap Agentratifier Director, Developer Platform3 stated assumptions

Policy register

The rules the agents above are bound by. Version, owner, approver, and the agents each rule constrains.

RefRuleScopeOwner agentApproved byVersionStatus
EN9-POL-200

Developer Experience Decision Envelope

Agents in this lane may act without a human when the developer request 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 4 agents · Global · EU

envelopeDeveloper Experience OrchestratorDirector, Developer Platformv4.3under review
EN9-POL-201

Developer Experience 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 4 agents · LATAM · US

evidenceDeveloper Experience OrchestratorDirector, Developer Platformv4.1Active
EN9-POL-202

Developer Experience 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, Developer Platform owns the response clock.

binds 4 agents · APAC

escalationDeveloper Experience OrchestratorDirector, Developer Platformv3.3under review