Sub-function
Technical Debt
Owns debt item work end to end inside Engineering. Runs 3 lines across 16 stations, drains the repeatable share into no shared tower, and holds 3 human gates.
Estate rating
A
77 / 100
Detection, migration and deprecation are mechanical and agentic. Accepting the remediation into a team backlog is an owner decision.
Agents
8
Lines
3
Units / wk
12,503
Timetable vs actual
13.4h → 15.8h
Cost / unit
$17
was $43
Run-rate saving
$16.8M
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.
Technical Debt Orchestrator
Owns the technical debt 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, Engineering Effectiveness when the unit falls outside the decision envelope or confidence drops below the floor.
Debt Detection Agent
Watches technical debt continuously. Detects drift, quantifies it, and routes what matters without waiting for a reporting cycle.
ceiling A3 · escalates to Escalates to Director, Engineering Effectiveness when the unit falls outside the decision envelope or confidence drops below the floor.
Risk Scoring Agent
Executes the technical debt step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Engineering Effectiveness when the unit falls outside the decision envelope or confidence drops below the floor.
Remediation Planning Agent
Executes the technical debt step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Engineering Effectiveness when the unit falls outside the decision envelope or confidence drops below the floor.
Migration Agent
Executes the technical debt step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Engineering Effectiveness when the unit falls outside the decision envelope or confidence drops below the floor.
Deprecation Agent
Executes the technical debt step it owns, posts its evidence, and hands the unit to the next stage.
ceiling A3 · escalates to Escalates to Director, Engineering Effectiveness when the unit falls outside the decision envelope or confidence drops below the floor.
Debt Doctrine Agent
Authors positions on technical debt. Frames the question, models the options, and writes a recommendation a human can ratify or reject.
ceiling A3 · escalates to Escalates when two options sit inside the confidence band and the evidence cannot separate them.
Technical Debt Challenger Agent
Adversarial reviewer for technical debt. 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.
Roles held flat; released hours absorbed volume growth rather than headcount reduction.
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.
Debt Doctrine Position
Ratifiedv1Which parts of technical debt should deliberately stay human, and how do we defend that against a cost argument?
Hold the ceiling at A3 for technical debt. Detection, migration and deprecation are mechanical and agentic. Accepting the remediation into a team backlog is an owner decision. Raise it only after two consecutive quarters where the override rate stays under five percent and every override has a written cause.
confidence
72%
The challenge — Technical Debt Challenger Agent
Technical Debt Challenger Agent argues the recommendation leans on 2 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 debt item 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 $23k are sampled, not fully measured
| Alternative considered | Cost | Risk | Verdict |
|---|---|---|---|
| Hold the current position | $199k run rate | Known and priced. Cedes ground if comparators move faster. | not selected |
| Raise the ceiling one level now | $1123k to build controls | Override rate is 6 percent; raising the ceiling before that settles imports the error into production. | rejected on evidence |
| Move the exception tail to the spine | $487k transition | Loses local context. Rework risk on the cases that are hardest to recover. | selected |
Ratified 5 months ago. Measured since: cost per debt item fell 27 percent against a forecast of 22 percent.
Technical Debt Operating Position
In challengev1Where should the autonomy ceiling for technical debt sit over the next four quarters, and what evidence would justify moving it?
Keep the repeatable debt item volume in the spine and pull the exception tail back into the function. The spine is cheaper per unit; the tail is where the context that prevents rework actually sits.
confidence
68%
The challenge — Technical Debt Challenger Agent
Technical Debt Challenger Agent argues the recommendation leans on 3 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 11 percent for two consecutive months
- ·Cost per debt item stops falling while volume keeps rising
- ·A comparator publishes a materially lower unit cost on a like-for-like basis
Evidence gaps
- ·No external comparator on a like-for-like unit definition
- ·Exception cases under $48k are sampled, not fully measured
| Alternative considered | Cost | Risk | Verdict |
|---|---|---|---|
| Hold the current position | $872k run rate | Known and priced. Cedes ground if comparators move faster. | live |
| Raise the ceiling one level now | $1617k to build controls | Override rate is 4 percent; raising the ceiling before that settles imports the error into production. | rejected on evidence |
| Move the exception tail to the spine | $1041k 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 |
|---|---|---|---|---|---|---|
| EN8-POL-200 | Technical Debt Decision Envelope Agents in this lane may act without a human when the debt item 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 · EU · UK | envelope | Technical Debt Orchestrator | Director, Engineering Effectiveness | v4.7 | Active |
| EN8-POL-201 | Technical Debt 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 | evidence | Technical Debt Orchestrator | Director, Engineering Effectiveness | v5.7 | Active |