LensReading which lens this session carries.
Research & Development/Discovery Research

Sub-function

Discovery Research

Owns research thread work end to end inside Research & Development. Runs 3 lines across 17 stations, drains the repeatable share into no shared tower, and holds 2 human gates.

orchestrator Discovery Orchestratorhuman owner Director, Discovery Researchno shared tower — judgment density too high

Estate rating

BB

67 / 100

autonomy 71%cap 78%

Literature synthesis and hypothesis generation are exactly where agents outperform — they read everything. A scientist validates before anything becomes a program.

Agents

7

Lines

3

Units / wk

2,471

Timetable vs actual

22.6h → 25.3h

Cost / unit

$17

was $50

Run-rate saving

$4.2M

annualized at this volume

The 7 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.

Discovery Orchestrator

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

ObserveA329 / 24h96%14% ovr$11/task

ceiling A3 · escalates to Escalates to Director, Discovery Research when the unit falls outside the decision envelope or confidence drops below the floor.

TaskExecutes stations on a line.

Literature Synthesis Agent

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

WorkflowA3771 / 24h99%7% ovr$0.47/task

ceiling A3 · escalates to Escalates to Director, Discovery Research when the unit falls outside the decision envelope or confidence drops below the floor.

Prior Work Agent

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

WorkflowA33,067 / 24h90%8% ovr$0.31/task

ceiling A3 · escalates to Escalates to Director, Discovery Research when the unit falls outside the decision envelope or confidence drops below the floor.

Feasibility Screening Agent

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

WorkflowA31,625 / 24h89%8% ovr$0.41/task

ceiling A3 · escalates to Escalates to Director, Discovery Research when the unit falls outside the decision envelope or confidence drops below the floor.

StrategyForms and defends a position.

Hypothesis Generation Agent

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

StrategyA212 / 24h89%16% ovr$12/task

ceiling A3 · escalates to Escalates when two options sit inside the confidence band and the evidence cannot separate them.

Research Direction Agent

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

StrategyA286 / 24h93%6% ovr$13/task

ceiling A3 · 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.

Discovery Research Challenger Agent

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

StrategyA2140 / 24h97%4% ovr$11/task

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.

Control Coverage66
Evidence Quality66
Override Discipline79
Data Integrity67
Recovery Readiness71
Cost Transparency70
Judgment Readiness54

People

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

headcount on this work23.315.0 FTE

Redeployed into exception judgment and supplier relationship work.

inference cost per unit$3.14

Lines running in this sub-function

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

9 clear3 evidenced2 held
RD1ADiscovery SprintAnalytical · 7 stations

Frame question

1 live

Synthesize literature

34 q

Generate hypotheses

34 q

Screen feasibility

27 q

Draft findings

1 live

Scientist review

3 q

Log

1 live

RD1BResearch Direction PositionJudgment · 6 stations

Frame

4 q

Map field

41 q

Model options

1 live

Draft position

1 live

Challenge

45 q

Chief Scientist ratify

0 q

RD1CPrior Work SweepTransactional · 4 stations

Scan publications

2 live

Match to program

2 live

Alert team

1 live

File

4 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.

RD1-POS-100

Research Direction Position

Supersededv2

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

Hold the ceiling at A3 for discovery research. Literature synthesis and hypothesis generation are exactly where agents outperform — they read everything. A scientist validates before anything becomes a program. Raise it only after two consecutive quarters where the override rate stays under five percent and every override has a written cause.

confidence

79%

The challenge — Discovery Research Challenger Agent

Discovery Research 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 6 percent for two consecutive months
  • ·Cost per research thread 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 $46k are sampled, not fully measured
Alternative consideredCostRiskVerdict
Hold the current position$231k run rateKnown and priced. Cedes ground if comparators move faster.live
Raise the ceiling one level now$1435k to build controlsOverride rate is 8 percent; raising the ceiling before that settles imports the error into production.rejected on evidence
Move the exception tail to the spine$885k transitionLoses local context. Rework risk on the cases that are hardest to recover.under review
authored by Hypothesis Generation Agentratifier Director, Discovery Research3 stated assumptions
RD1-POS-101

Discovery Research Operating Position

Rejectedv1

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

Keep the repeatable research thread 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

66%

The challenge — Discovery Research Challenger Agent

Discovery Research 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 research thread 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 $50k are sampled, not fully measured
Alternative consideredCostRiskVerdict
Hold the current position$640k run rateKnown and priced. Cedes ground if comparators move faster.live
Raise the ceiling one level now$357k to build controlsOverride rate is 13 percent; raising the ceiling before that settles imports the error into production.rejected on evidence
Move the exception tail to the spine$684k transitionLoses local context. Rework risk on the cases that are hardest to recover.under review
authored by Research Direction Agentratifier Director, Discovery Research3 stated assumptions

Policy register

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

RefRuleScopeOwner agentApproved byVersionStatus
RD1-POL-200

Discovery Research Decision Envelope

Agents in this lane may act without a human when the research thread 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 3 agents · Global · EU

envelopeDiscovery OrchestratorDirector, Discovery Researchv2.7under review
RD1-POL-201

Discovery Research 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 3 agents · LATAM · US

evidenceDiscovery OrchestratorDirector, Discovery Researchv2.3Active
RD1-POL-202

Discovery Research 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, Discovery Research owns the response clock.

binds 3 agents · US · Canada

escalationDiscovery OrchestratorDirector, Discovery Researchv1.4Active