LensReading which lens this session carries.
The catalogueResearch & DevelopmentData Science & ModelingTransactional

Service RD5B

Drift Response

Runs transactional. Starts when a request lands in the queue. It runs 7,707 times a week across 6 stations. One of those stations stops for a person and 5 are done by an agent, 4 of them on the shared spine.

Runs a week

7,707

90 in flight right now.

Stations

6

1 person · 1 agent · 4 spine

Agent share of steps

83%

Autonomy on this service is set at 75% against a ceiling of 83%.

Decisions a person makes

1

Held by Director, Data Science.

Touchless

82%

Share of runs that complete without anybody opening them.

Timetable against actual

17.4h

Actual 14.6h, 2.8h under the timetable.

Operations

The lane diagram

Read it left to right.

Person1 station and 31% of the dwellAgent1 station and 22% of the dwellShared spine4 stations and 47% of the dwell4 crossings between lanes
Human
decides
Agent
does the work
GBS
shared spine
System
attributed by rule
Product Lifecycle Management
Product Lifecycle Management
Product Lifecycle Management
Product Lifecycle Management
Product Lifecycle Management
Product Lifecycle Management
Click any station to see who does it, what it costs in time, the rule that gates it and the system attributed to it.

Operations

Every station in order

The same stations as a list, with the dwell the estate records against each one and the system a station of that shape would touch.

#StationLaneWhoLayerDwellTargetIn flightSystem
1

Detect drift

GBSFeature Engineering Agentgbs2h 34m5h 23m30Product Lifecycle Management
2

Diagnose

AgentModel Training Agentworkflow2h 52m6h 28m7Product Lifecycle Management
3

Retrain

GBSFeature Engineering Agentgbs37m1h 20m19Product Lifecycle Management
4

Validate

GBSFeature Engineering Agentgbs1h 19m2h 37m23Product Lifecycle Management
5

Approve promotion

Held for a named human when the unit exceeds the model decision envelope, when confidence falls below the floor, or when a policy clause is engaged.

HumanDirector, Data Sciencepolicy4h4h 55m3Product Lifecycle Management
6

Deploy

GBSFeature Engineering Agentgbs1h 32m3h 33m8Product Lifecycle Management

Operations

Run it

Change the volume, move the autonomy line, release a gate, and watch what happens to the hours in each lane and to the time it takes one run to get through.

Move something
Demand100%
7,707 a week is what the estate records.
Decisions handed to agents0 of 0
This service has at most one gate, so there is nothing to hand over without removing the last human decision.
People on the gates881 people
Each one is assumed to have 2,100 productive minutes a week, which is 35 hours.
Agent speed100%
100% is the dwell the estate records today.
Person time a week
30,828h
7,707 items at 240 minutes of decision each.
Agent time a week
68,592.3h
534 minutes an item, which does not compete for a person.
Gate load
100%
Inside capacity, with 7h of headroom.
Stations without a person
83%
1 gate left on 6 stations.
Where an item spends its time
31% waiting on a person
69% in the agent lane
An item now takes 774 minutes of worked time end to end against 774 in the recorded estate, a change of +0%. This is worked time, not calendar time: nothing here models a queue or a weekend.
What this model is, on Drift Response

The simulation is arithmetic on the estate, not a queueing model.

How it runs

Run it again, going wrong

The same unit and the same stations, broken the way the estate already records breaking.

6 stations, walked twice

Once clean, once with the categories the estate counts

This is the same unit on the same stations, breaking.

No break below was chosen.

One play head, two tracks, the same scale. The clean run stops when it runs out of stations; the other one keeps going.

As written

6 stations, nothing waiting, nothing sent back

0 min of 13 hrs

now Detect drift · Feature Engineering Agent · 2.6 hrs

As the ledger has it

the same stations, plus 4 categories the estate already counts

0 min of 31 hrs

now Detect drift · Feature Engineering Agent · 2.6 hrs

personagentshared spinework the break addsnobody working it

What breaks, and where it is counted

No break below was chosen.

What the two runs say together

4 counted categories land on this procedure.

What this run cannot claim

These breaks are shown together on one unit so the shape of a bad day fits on one screen.

The separation register records a duty conflict against a sub-function and a named post, not against one procedure.

Two clocks run. Worked time is the sum of the time the work is actually being done …

Live observability

Systems this service would touch

Attributed by rule from the function's system list.

1 systems attributed

0 of 1 returning records

Product Lifecycle Management

Siemens Teamcenter · engineering · inbound · high

modeled

6 of 6 stations attributed here · read only

System attribution is a rule, not a reading.

Who runs it

Orchestration and accountability

Orchestrated by
Modeling Orchestrator
That orchestrator’s remit
Owns model work end to end inside Research & Development. Runs 3 lines across 19 stations, drains the repeatable share into the DATA-ANALYTICS tower, and holds 4 human gates.
Accountable person
Director, Data Science
Sub-function
Data Science & Modeling
Shared spine tower
data-analytics
Hand-over points
None — this service stays inside its function

Other services in this sub-function

2 alongside this one

What this page is and is not

This is a catalogue of the modeled estate.