The Screenshot Boundary Is The Instrument And The Patience Budget Must Come From Outside The Model
Summary
The tabletop programme for testing pages with synthetic readers, and the three methodological corrections that decide whether it measures anything. Two agents: one renders the site and takes screenshots (an existing browser-automation service — a caller, not a build), one acts as a persona that receives pixels and nothing else and answers with spatial clicks. The screenshot boundary is the instrument, not a limitation: a persona that can read the source understands the page better than any human could. The page under test must be a fixed artefact authored before the run — a page generated during the run measures the model agreeing with itself — and the patience budget must be set exogenously, because patience generated by the same model that generates the confusion will always cohere with it. The honest limit: synthetic readers find defects and cannot report preferences, so they clear the levels and humans judge the variants. And the brief raises, for the third time, the rule against simulating named individuals — proposing the narrow, testable exception: an archetype composed from several people that none of them would recognise.
Key concepts
- The screenshot boundary — pixels and nothing else — no text, no structure, no purpose, and clicks named spatially rather than semantically
- The fixed-artefact requirement — a hand-written mockup satisfies it completely, which is what makes testing before building available
- The exogenous patience budget — screens, minutes and clicks fixed before the run — abandonment becomes a measured event rather than a narrative
- Portrait versus archetype — if the person it came from, or a colleague of theirs, would recognise them in it, it is a portrait
Key ideas
- Synthetic readers find defects, not preferences — a page that does not answer its own question, a term used before definition, a dead end.
- The comprehension question is fixed wording every time: what would you do now, and what did that page tell you.
- A simulated acceptance must never be confusable with a real one — and export is exactly the moment a marker is lost.
- The part-two service is one question away from the banned tool: comprehension and confusion yes, what would this person approve, never.
- The runs worth publishing most are the abandoned ones, because those are the ones that changed the design.
On this site
Became document 08 of the Map Your Case pack — the synthetic-reader programme — with the two simulation rules carried verbatim into the pack's principles.