Anatomy of a Run
One question, followed through the instrument. The result appears first; the machinery is offered second. Every stage below corresponds to a real execution state the system reports, and every visual change on the plate is driven by that state, not by decoration.
This walkthrough is a prototype demonstration. Every run identifier, scene reference, coordinate, date and metric shown is a synthetic placeholder — the sequence is driven by the mock event stream, not a live backend. The footer repeats this in full.
What changed here?
The question
Everything downstream is a consequence of this string. It arrives with a scene reference — which plate, which epoch pair, which ground sampling distance — and nothing else.
Query processor
The question is parsed into a task and a set of slots. This is disambiguation, not reasoning: the output is a label the controller can act on, and it is shown to you verbatim.
Policy controller
A deterministic rule table selects the analysis path. There is no learned router and no hidden preference — the rules that fired are listed, and the ones that did not are listed too.
Specialist analysis
The temporal pair is co-registered first — a residual above tolerance invalidates any pixel comparison, so it is measured before anything is detected. Then the selected specialists run, and only those.
Grounding
Change proposals are resolved to located regions. A proposal without a location is not evidence; it is a guess with a coordinate missing.
Evidence
Each region is measured in metres, scored, and tied to the component that produced it. Evidence is what the answer is allowed to refer to.
Confidence
Reported confidence is temperature-scaled and checked against observed accuracy on a held-out calibration split. When calibration fails, the system is expected to abstain rather than sound certain.
Answer
The answer is assembled last, from evidence that already exists. It is bounded by what the imagery can support at this ground sampling distance — and the bound is stated, not hidden.
What is deliberately not shown
Never exposed
- Chain-of-thought or internal reasoning traces
- Intermediate prompts, unless the user asked for them
- Uncalibrated scores presented as confidence
- Evidence regions without a source component
Always exposed
- Current stage and active specialist
- Component and model identity, plus execution timing
- Registration residual before any change claim
- Region areas, scores, provenance and run identifiers