LensReading which lens this session carries.

Function cockpit

Engineering

Agents build, test and document. Engineers own architecture and release.

Autonomy0% / 80%

Phase: Phase 3 — Functional orchestration

Run the intent-to-release graph as a governed system: decomposition, code generation, testing, documentation, vulnerability detection and deployment preparation are agent work; product intent, architecture and production release remain human.

Trust score

0

Touchless

0%

Human review

0%

Override rate

0%

Capacity released

25-40% engineering capacity in selected software-factory settings (case-specific)

Accountable human

Chief Technology Officer

CoS agent: Engineering Chief of Staff

Watch one unit run any procedure on the happy viable agentified path

Process simulation

Run any Engineering procedure on the happy viable agentified path

Pick a procedure and press run.

The written procedures

Procedures you can run

33

Stations across them

176

every one of them a step in some run

Decision points

37

stations that stop for a named person

Stop for nobody

2

31 of the 33 still have a person on them

Units a week

116,848

the recorded volume across all of them

33 procedures. Pick one and it runs.
now running
EN2ADesign DecisionArchitecture & Design · Judgment · 5 a week
speed
worked clock
00:00
allowance clock
00:00
stations cleared
0/7
the happy path, worked time0 min of 7.3 days
the same run against its allowance0 min of 13.3 days
Human
decides · 1
Agent
does the work · 6
GBS
shared spine · 0
run log

Nothing has happened yet.

where the worked time goes7.3 days a unit
Person25 hrs · 14%Agent6.3 days · 86%1 crossing between lanes
what makes this path viable
  • The lanes are the recorded lanes. 1 of the 7 stations stop for a person and every one of them still does on this run.
  • Every one of the 1 decision is still taken by the person who holds it. The happy path is that each one is released first time, not that it is skipped.
  • The owning team is held to a 70% autonomy ceiling and this run sits at 86% unattended, inside it.
  • 1 system is attributed across the stations, and 0 of them are connected. Nothing in this run has been watched executing against a real system of record.
what would have to change

One decision, held by Chief Architect.

stays with a person
  • 07 Review board ratify — The last decision on the line. Something on every procedure ends with a person, so this one is never offered.
what this run is, and what it is not

This is a run, not a forecast.

Happy means nothing goes wrong: no station raises an exception, no gate sends the unit back, no rework loop fires and nothing sits in a queue between stations.

The second clock is the allowance.

A decision may be handed to the agent lane only if two things hold …

The run reads the station rows only.

What this run does not model: arrival patterns, contention between procedures for the same person, shift patterns, weekends, learning curves, and the cost of anything.