LensReading which lens this session carries.
Legal/Litigation & Disputes

Sub-function

Litigation & Disputes

Owns matter work end to end inside Legal. Runs 3 lines across 20 stations, drains the repeatable share into no shared tower, and holds 6 human gates.

orchestrator Litigation Orchestratorhuman owner VP Litigationno shared tower — judgment density too high

Estate rating

BBB

69 / 100

autonomy 55%cap 58%

Deliberately the lowest ceiling in Legal. Agents review documents and build chronologies at scale, but privilege calls and settlement authority are personal to a qualified lawyer.

Agents

8

Lines

3

Units / wk

10,475

Timetable vs actual

8.2h → 7.7h

Cost / unit

$16

was $43

Run-rate saving

$14.5M

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.

Litigation Orchestrator

Owns the litigation & disputes lane end to end. Sequences the other agents, holds the timetable, and decides what surfaces to a human.

ObserveA263 / 24h91%6% ovr$11/task

ceiling A2 · escalates to Escalates to VP Litigation when the unit falls outside the decision envelope or confidence drops below the floor.

TaskExecutes stations on a line.

Matter Intake Agent

Executes the litigation & disputes step it owns, posts its evidence, and hands the unit to the next stage.

WorkflowA21,213 / 24h96%9% ovr$0.51/task

ceiling A2 · escalates to Escalates to VP Litigation when the unit falls outside the decision envelope or confidence drops below the floor.

Document Review Agent

Executes the litigation & disputes step it owns, posts its evidence, and hands the unit to the next stage.

WorkflowA22,512 / 24h88%1% ovr$0.31/task

ceiling A2 · escalates to Escalates to VP Litigation when the unit falls outside the decision envelope or confidence drops below the floor.

Chronology Builder Agent

Executes the litigation & disputes step it owns, posts its evidence, and hands the unit to the next stage.

WorkflowA22,875 / 24h90%2% ovr$0.30/task

ceiling A2 · escalates to Escalates to VP Litigation when the unit falls outside the decision envelope or confidence drops below the floor.

Exposure Modeling Agent

Executes the litigation & disputes step it owns, posts its evidence, and hands the unit to the next stage.

WorkflowA23,721 / 24h91%2% ovr$0.15/task

ceiling A2 · escalates to Escalates to VP Litigation when the unit falls outside the decision envelope or confidence drops below the floor.

PolicyAuthors and versions the binding rules.

Legal Hold Agent

Holds the rules that bind every other agent in litigation & disputes. Versions them, tests them against live decisions, and blocks work that breaches them.

PolicyA2209 / 24h86%7% ovr$13/task

ceiling A2 · escalates to Escalates on any decision that would breach a live policy version, with the clause cited.

StrategyForms and defends a position.

Settlement Doctrine Agent

Authors positions on litigation & disputes. Frames the question, models the options, and writes a recommendation a human can ratify or reject.

StrategyA270 / 24h95%16% ovr$2.54/task

ceiling A2 · 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.

Litigation & Disputes Challenger Agent

Adversarial reviewer for litigation & disputes. Argues the opposite case on every position and flags where the evidence does not carry the claim.

StrategyA2180 / 24h97%17% ovr$8.03/task

ceiling A2 · 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 Coverage50
Evidence Quality63
Override Discipline89
Data Integrity77
Recovery Readiness58
Cost Transparency81
Judgment Readiness75

People

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

headcount on this work49.334.4 FTE

Redeployed into exception judgment and supplier relationship work.

inference cost per unit$2.98

Lines running in this sub-function

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

7 clear3 evidenced3 held
LG7AMatter LifecycleTransactional · 8 stations

Intake

4 q

Issue legal hold

7 q

Assemble chronology

1 live

Model exposure

1 live

Strategy review

7 q

Counsel instruct

2 live

Track

1 live

Resolve

1 live

LG7BDiscovery ProductionTransactional · 6 stations

Scope

1 live

Collect

1 live

Review

1 live

Privilege check

1 live

Produce

1 live

Log

1 live

LG7CSettlement PositionJudgment · 6 stations

Frame

43 q

Model outcomes

42 q

Cost of continuing

6 q

Draft position

23 q

Challenge

26 q

GC ratify

1 live

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.

LG7-POS-100

Settlement Position

Ratifiedv1

What operating shape carries twice the current matter volume without adding headcount, and what breaks first if we are wrong?

Hold the ceiling at A2 for litigation & disputes. Deliberately the lowest ceiling in Legal. Agents review documents and build chronologies at scale, but privilege calls and settlement authority are personal to a qualified lawyer. Raise it only after two consecutive quarters where the override rate stays under five percent and every override has a written cause.

confidence

81%

The challenge — Litigation & Disputes Challenger Agent

Litigation & Disputes 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 9 percent for two consecutive months
  • ·Cost per matter 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 $24k are sampled, not fully measured
Alternative consideredCostRiskVerdict
Hold the current position$604k run rateKnown and priced. Cedes ground if comparators move faster.not selected
Raise the ceiling one level now$1279k to build controlsOverride rate is 14 percent; raising the ceiling before that settles imports the error into production.rejected on evidence
Move the exception tail to the spine$312k transitionLoses local context. Rework risk on the cases that are hardest to recover.selected
authored by Settlement Doctrine Agentratifier VP Litigation3 stated assumptions
outcome did not hold

Ratified 2 months ago. Measured since: cost per matter rose 6 percent against a forecast that it would fall 36 percent.

LG7-POS-101

Litigation & Disputes Operating Position

Ratifiedv3

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

Keep the repeatable matter 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

59%

The challenge — Litigation & Disputes Challenger Agent

Litigation & Disputes 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 15 percent for two consecutive months
  • ·Cost per matter 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 $10k are sampled, not fully measured
Alternative consideredCostRiskVerdict
Hold the current position$407k run rateKnown and priced. Cedes ground if comparators move faster.not selected
Raise the ceiling one level now$1051k 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$630k transitionLoses local context. Rework risk on the cases that are hardest to recover.selected
authored by Settlement Doctrine Agentratifier VP Litigation3 stated assumptions
outcome did not hold

Ratified 7 months ago. Measured since: cost per matter rose 7 percent against a forecast that it would fall 11 percent.

Policy register

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

RefRuleScopeOwner agentApproved byVersionStatus
LG7-POL-200

Litigation & Disputes Decision Envelope

Agents in this lane may act without a human when the matter 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 · US · Canada

envelopeLegal Hold AgentVP Litigationv2.0Active
LG7-POL-201

Litigation & Disputes 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 · EU · UK · US

evidenceLegal Hold AgentVP Litigationv5.2Active
LG7-POL-202

Litigation & Disputes 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. VP Litigation owns the response clock.

binds 4 agents · Global

escalationLegal Hold AgentVP Litigationv4.6Active