The meta-layer · the steward

The AI Lifecycle Harness

Everything else on this site is the output — a QX-250 digital thread carried from a customer RFP to a flight-verified design. The AI Lifecycle Harness is the engine: the application that reads the RFP, frames the work as an agentic Work-Breakdown Structure, orchestrates the Siemens Xcelerator tools across the whole lifecycle, and measures itself as it goes. This weekend it framed and drove the build — with a human still prompting each step. It is built to steward that loop going forward.

Meta-layer · in progress RFP → flight-verified Agentic WBS · tool orchestration

The loop it stewards

From a customer RFP to a flying design

The QX-250 program did not start with a drone — it started with a customer need, written as a request for proposal modeled on real U.S. Air Force solicitations. Everything downstream is an answer to it. The harness's job is to carry that need, unbroken, all the way to a verified aircraft:

01RFP

The customer need — a USAF-style RFP + 41-page system spec.

02Requirements

Decomposed into 51 trace-linked requirements.

03Analyze

Reliability + 6-DOF simulation, up front — the design authority.

04Design

Functions, logical, electrical, mechanical, compute, software.

05Deliver

Program, schedule, EBOM / MBOM, quality.

06Verify

51 / 51 requirements trace-linked to results — PASS.

07Fly

Re-flown at the as-built mass — it flies with margin.

◆ stewarded end-to-end by the harness

How it knows what to build

The agentic Work-Breakdown Structure

A harness can only steward what it can represent. The RFP is decomposed into a structured program of work — an agentic WBS — in which deliverables must meet criteria that satisfy accomplishments that deliver to milestones. That structure is what turns "build a drone" into a list of concrete, checkable units of work an agent can execute and a human can govern — the same Program-Planning / IPP&E backbone the managed program already uses, pointed at the agent's own work.

Deliverable

A concrete artifact — a requirement set, a schematic, an assembled model, a verification result.

Criteria

Machine-checkable conditions the deliverable must meet — the line between "asserted" and "proven".

Accomplishment → Milestone

Deliverables roll up into accomplishments, which deliver to program milestones and the gates a human approves.

This weekend — the honest baseline

The human directed; the AI operated every tool

Here is the distinction that matters. Every human touch this weekend was direction, not operation: no human ever clicked a button, dragged a node, or typed a value in NX, Capital, Teamcenter, Simcenter Amesim or MADe. The AI operated every tool itself — by API, MCP bridge and browser automation. The Time-to-Solution Dashboard counts 26 human touches (22 prompts, 2 approvals), and every one was a human saying what to do next — never "here, let me do that part."

So the autonomy that matters is already here. Hands-on-tool execution across the whole lifecycle was 100% agentzero human tool actions. What is not yet autonomous is the direction: the agent still needed a human to sequence the work 22 times. Closing that gap — driving the direction from the WBS instead of a prompt — is the one thing the harness is built to do.
The number to drive down. Touches-per-deliverable — today about 2 prompts per deliverable. The target is a human who approves at the gates while the harness drives the deliverables from the WBS. That is the difference between an agent you prompt and an agent that stewards.

What has to become true

Its two instruments

The harness is only as good as the tools it can drive and the honesty of its own measurement. Two views on this site are its instruments:

The thesis. A digital thread proves the output can be carried unbroken from RFP to flight. The AI Lifecycle Harness is the bet that the carrying itself can be stewarded by an agent — measured, governed and driven from a structured program — until "a complete design, verified in simulation, in a day" is the normal case, not a weekend feat.