Inferential discovery in generative workflows:
how abundance affects the designer’s relationship to work in progress.
The equation measures automation on a linear scale, providing a basis for discussing a spectrum from automation to agency.
Oᵢ is the assessed opportunity for inference in each of five aspects: subject, composition, form, appearance, and detail. Each is rated from 0 to 1, in provisional quarter steps. Higher opportunity places the operation farther left; lower opportunity places it farther right.
The sum ranges from 0 to 5. Multiplying by 3 maps it onto 0–15; subtracting from 15 preserves the map’s orientation. Each aspect contributes equally, with a maximum contribution of 3 coordinate units.
ComfyUI text-to-image example: a scoped assessment, not a rating of every ComfyUI operation.
| Subject | Composition | Form | Appearance | Detail |
|---|---|---|---|---|
| 0.75 | 1.00 | 0.75 | 0.50 | 1.00 |
∑Oᵢ = 4.00
X = 15 − (3 × 4.00) = 3.00
A change of 0.25 in one aspect changes X by 0.75. For example, lowering detail opportunity from 1.00 to 0.75 produces X = 3.75. This sensitivity calculation shows the consequence of a disputed rating; it does not change the plotted assessment.
Different profiles can have the same total. The five ratings and their rationales therefore remain available beside the coordinate.
The initial survey used shared axis descriptions and reference examples to guide coordinate judgments. A calculation for every original decimal coordinate has not been recovered. Those placements are part of the instrument’s history.
The archived Cell Math discussion contains successive proposals with different targets:
Xautomation = (10 / 8)(T + G + C + R)
Task delegation, generative resolution, decision closure, and run/continuation autonomy were each rated 0–2.
Xspecification = (10 / 8)(D + R + C + U)
A later proposal used direct input, representation, constraint control, and retention of user decisions, again rated 0–2. Both convert a maximum sum of 8 to a 0–10 scale. With integer component ratings, possible totals are separated by 1.25. These are historical proposals, not the equation used for the revised points.
Xspecification = ∑Sᵢ · Sᵢ ∈ {0, 1, 2, 3}
Subject, composition, form, appearance, and detail were scored by how they were supplied: unspecified, described in words, constrained by a guide or source, or explicitly constructed. Their sum gave a 0–15 specification score; the accompanying notes proposed 15 − X as opportunity for inference.
X = 15 − 3∑Oᵢ
The current worked examples assess what supplied inputs leave open for generative AI to resolve within a specific operation. They retain the five aspects while documenting the scenario, source evidence, rating rationale, and sensitivity. This is a change in assessment conventions, not merely a conversion of old scores. The earlier and revised points should not be read as measured changes in software.
The wine-rating analogy motivates a common descriptive reference: people can inspect a rating without sharing a preference. Here, the coordinate describes an operation’s production conditions; it is not a quality or taste score.
The arithmetic is repeatable once the five ratings are fixed. The research task is to make those ratings defensible: specify the operation and inputs, document evidence for each aspect, expose uncertainty, and compare independently assigned ratings. Independent agreement and calibration have not yet been established for this working rubric.
Equal weights and equally spaced quarter steps are provisional assumptions. They allow an explicit calculation, but do not establish that the aspects are equally consequential or that perceived differences are equally spaced. A decimal coordinate is not a percentage of AI contribution or a direct count of inferences.
This preview contains 387 operation records and 81 revised X examples. Earlier Y values are retained for comparison and have not been reassessed. Records without Y remain in the catalogue. Original source coordinates remain unchanged.
Search above to narrow results. Open a record to inspect its assessment.
The inquiry is located at the designer’s point of discovery.
This dissertation examines how the designer responds, and how an abundance of new information provided by generative workflows affects their relationship to work in progress.
A discovery can change how the designer understands the work and what its continuation might mean. Following these responses makes it possible to examine how that relationship develops, while further discovery remains possible.
The Inference Resolution Map describes production conditions that help situate these responses. It supports comparison across operations and provides context for studying the designer’s response and its significance for continuation.
How does a designer’s relationship to their visual work in progress shift when inferential discovery can recur across a generative workflow?
Dated proposal. The map and its placement criteria continue to develop.
Earlier work examined how different input modalities supply partial spatial information, how generative systems resolve that information, and how people interpret the resulting structures.
This provides context for the ongoing inquiry into what is supplied, what is inferred, and what a designer encounters in the work.
Read 2025 paper ↗While teaching architecture in Miami, I explored how people could learn to use tools through experiences tailored to them. My early research considered visualization and gamification as ways of making learning interactive, with climate education as an initial context. The emphasis subsequently moved toward personalized education and how learning could respond to individual needs.
As generative practice became a stronger focus, my attention shifted toward what designers encounter while working with these tools. The Inference Resolution Map sits within this longer inquiry into people’s relationships with tools; the current dissertation focuses on the designer’s response to inferential discovery.
Literature review and research-paper drafts examined 3D visualization, gamification, and AI-supported personalization in climate education.
A Digital Futures paper considered prospective changes to architectural education, curricula, and relationships between educators and students.
Personalized Learning in Higher Education: AI-Driven Analytics and Competency-Based Models as Catalysts for Reform placed adaptive learning and individual needs at the center of the inquiry.
Listening is an important part of how I learn and develop my work. My reading and listening span technology, creativity, perception, culture, and lived experience.
78 titles
Working bibliography across the research. Inclusion does not mean a source is cited in the proposal.
110 sources