MuNa/paper/paper.md

# From Pattern to Plan: A Form-Language Extension and a Live Public-Advocacy Deployment of LLM-Mediated Pattern Language Synthesis

Bruno Postle¹ and Nikos A. Salingaros²,³

¹ Union Street Research, Sheffield, UK
² Department of Mathematics, The University of Texas, San Antonio, TX, USA
³ Thrust of Urban Governance and Design, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

*Draft — target venue: Buildings (sequel to Postle, B.; Salingaros, N.A. "LLM and Pattern Language Synthesis: A Hybrid Tool for Human-Centered Architectural Design." Buildings 2025, 15, 2400).*

---

## Abstract

A prior paper (Postle & Salingaros, *Buildings* 2025, 15, 2400) introduced a
method for turning a curated subset of Christopher Alexander's *A Pattern
Language* into an experiential design narrative using a large language
model (LLM), demonstrated on a hypothetical university building. This
paper reports a live deployment of an extended version of that method in
an active, contested public process: an independent counter-proposal for
the new National Museum of Ecuador (Quito), written in response to public
objection to the winning entry of an international design competition. We
extend the original two-input chain (pattern subset + brief) with a third
input, a *form language* — a project-specific grammar of climatic
response, tectonics, material, color, and ornament, following Salingaros'
theoretical framework of pattern language and form language as
complementary, jointly necessary instruments. We generalize the bespoke
prompting used to produce this project's form-language grammar into a
reusable, placeholder-driven template, and validate that it generalizes to
an unrelated typology, region, and climate. From one shared pattern
subset and form-language grammar, two authors independently ran the
method to completion, producing two narratives and two illustrated image
sets (13 watercolor-register images; 25 photo-realistic images) that
converge on compatible design moves while diverging sharply in visual
register, for reasons we have not yet isolated. We report informal peer
reception of this work at a public symposium, including a substantive
critique from a practicing architect that the method, as run, produced
"flavors, not solutions" because no single coordinated floor plan
underlies the independently generated images. We discuss this and other
limitations, and propose — without yet prototyping — an explicit
plan-layout generation stage as the method's next needed instrument,
mining spatial-adjacency information already implicit in the pattern
subset.

**Keywords**: pattern language; form language; large language models;
human-centered architecture; generative AI in design; participatory
design; Christopher Alexander; Ecuador; museum architecture;
public-advocacy design

---

## 1. Introduction

The dominant response of AI text-to-image tools to architectural prompts
is to invent an attractive building from a short stylistic description —
producing images that are slick, stylistically confused, and spatially
and culturally arbitrary, because nothing upstream of the image
constrains it. Postle and Salingaros [1] proposed an alternative: place
image generation at the *end* of a structured chain rather than at the
start, so that an LLM synthesizes an experiential design narrative from a
curated, human-readable set of Alexander's [2] patterns before any image
exists, and treats that narrative — not a mood-board prompt — as the
instrument that generates and disciplines images. That paper demonstrated
the method on a hypothetical university department building and used two
independent LLMs to cross-check a claim about the pattern-generated
design's likely effect on occupant productivity.

This paper reports two things the original paper could not: a **live
deployment** of the method under real stakes, and a **method extension**
that the deployment required.

The deployment: the Government of Ecuador ran an open international call
(Stage 1 deadline 17 February 2026) for the architectural preliminary
project of the new National Museum of Ecuador, on a 13,004.65 m² site in
Iñaquito, Quito. A winner was selected, but the winning design provoked
sustained public objection over its failure to serve the people who will
actually use it, and — at the time of writing — is on hold and may be
abandoned. Independently of that competition, a small informal team,
including both authors of this paper, used the method described in [1],
extended as described below, to write and illustrate a complete
counter-proposal: not a competition entry, but a public-advocacy document
intended to influence the outcome of the debate while the winning
scheme's fate is undecided. Unlike the earlier paper's case study, this
deployment was not written for the purpose of demonstrating the method —
the method was used because it was the fastest available way to produce
a serious, human-centered alternative in the time available, and this
paper is a report on what happened when it was used that way, in public,
under scrutiny.

The extension: the original method combined a pattern subset with a
project brief. For a museum expected to express Ecuadorian cultural
identity as much as to organize human activity, a pattern subset alone
was not sufficient — Alexander's patterns govern human/organizational
relationships (how people arrive, gather, move, rest) but say little
about how a building should look, or which regional material and
ornamental vocabulary it should draw from. We therefore added a third
input, a *form language*, following the theoretical distinction Salingaros
sets out in "Two Languages for Architecture" [3]: a pattern language
encodes rules for how human beings interact with built form, while a form
language encodes geometric and tectonic rules for how matter is put
together, and the two are jointly necessary — a form language that is not
adaptive to human sensibility cannot connect to a pattern language, and a
pattern language has no way to become a specific building without a form
language. Section 3 reports how this form-language instrument was
produced, and how we generalized its production into a reusable template.

The rest of the paper is a case study of what happens when this
three-input method is run twice, independently, from the same shared
inputs, in public, and then subjected to informal peer critique. Section
2 gives the background of the competition and the specific, named
failures the counter-proposal was written to avoid. Section 3 describes
the method extension. Section 4 reports the worked example as two
divergent tracks. Section 5 reports reception at a public symposium,
including a substantive critique that the method, in its current form,
does not yet produce a coordinated plan. Section 6 discusses this and
other limitations honestly. Section 7 proposes, as future work, the
instrument this critique implies is missing. Section 8 concludes.

## 2. Background: The Museo Nacional del Ecuador Competition and Its Discontents

The National Museum of Ecuador holds the country's national collection —
over 1.2 million objects and documents spanning roughly 12,000 years,
across five reserves (archaeology, colonial and republican art, modern
and contemporary art, a human-sciences library, and a historical
archive) — of which the institution states that under 1% can currently
be exhibited at once, for lack of space. The Stage 1 open call sought a
preliminary architectural project for a new building of at least 25,000
m² on a 13,004.65 m² plot at the corner of Av. Eloy Alfaro and Av. de la
República in the Iñaquito parish of Quito, diagonally across from La
Carolina Park — one of Quito's most-visited public spaces, itself drawing
on the order of 400,000 visits a month — with direct access to the La
Carolina Metro station.

A winning scheme was selected, but has since drawn considerable public
objection. Independently of this paper's authors, a critique of the
winning proposal was recorded and circulated, analyzing it against
human-centered design and pattern-language principles, with
eye-tracking-derived visual-attention data supporting several of its
claims. That critique named specific, concrete failures rather than
general aesthetic complaints: an entrance that visual-attention scans
showed users could not locate (98% of attention going to non-entrance
openings and parked cars); blank facades assessed as generating anxiety
rather than welcome; and other legibility and human-scale failures. We
mined this critique for named, evidenced failures and mapped each to the
pattern(s) in our subset that directly counters it (e.g., illegible
entrances countered by Main Entrance / Entrance Transition / Entrance
Room), so that the counter-proposal's design decisions would explicitly
and traceably steer clear of documented problems, not just gesture at
being different in tone.

The counter-proposal — *Casa de la Memoria Andina*, in Postle's track;
*Casa de la Memoria Ecuatoriana*, in Salingaros' — is the product
described in the rest of this paper.

## 3. Method Extension: A Third Input — the Form Language

### 3.1 Two Complementary Languages

Salingaros' theoretical framework [3] holds that a pattern language and a
form language are distinct and jointly necessary. The pattern language
supplies the *organizational code*: which spatial relationships make a
building legible and humane — where entrances go, how circulation reads,
how outdoor rooms catalyze use. The form language supplies the *cultural
code*: how the building meets the ground, how walls and roofs are built,
which materials, colors, and ornament belong to the place, and where they
are permitted to concentrate. A pattern-generated design without a form
language has no way to decide what it is made of or what it looks like; a
form language without a pattern language risks producing a building that
looks locally authentic but is organizationally illegible or hostile to
use. The original paper [1] used only the first instrument. This project
required both.

### 3.2 The Ecuadorian Form Language Grammar

For this project, Salingaros produced a project-specific form-language
grammar, the *Ecuadorian Form Language Grammar*, developed after
discussion with a Quito-based designer and self-builder and synthesized
by an LLM from open-source reference imagery. Rather than a set of
historical facades to imitate, it is written as a *generative* vocabulary:
a stratified tectonic sequence from dark Ecuadorian andesite at the
plinth, through thick limewashed tapial and adobe at the lower and middle
levels, to lighter bahareque and timber at the crown, under red clay tile
roofs with deep *aleros*; a spatial lexicon of named local elements
(*atrio*, *zaguán*, *corredor*, *balcón corrido*, *mirador*, *canales*,
*rejas*); a restrained base color system ("Quito White & Andesite") with
a wider selectable palette; and an ornament system concentrating
geometric *chakana* and diamond-course motifs at base, threshold, and
crown, plus a single permitted figurative *retablo* episode — with
explicit prohibitions against superficial historicism, arbitrary facade
color patches, and decoration applied without tectonic reason. Where the
pattern language tells the building how to work, the form grammar tells
it how to belong.

### 3.3 Templating the Form-Language Step

The Ecuadorian Form Language Grammar was originally produced by a bespoke,
two-step prompting process specific to this project: an initial
exploratory prompt asking an LLM to research vernacular and historical
form across the region and propose a generative grammar rather than a
style to copy, followed by a second prompt narrowing scope to the
specific site and climate while retaining the wider regional vocabulary.
This process was not, as originally run, reusable — it existed only as a
conversational transcript specific to Quito.

We generalized it into `form-language-prompt-template.md`, a single-shot
prompt template with placeholder fields for typology, region,
site/climate, and historical strata, that collapses the two-step process
into one prompt and produces a grammar document in the same structural
shape (tectonic sequence, spatial lexicon, composition syntax, color and
ornament systems) as the Ecuadorian worked example — analogous to how the
web-based pattern-subset tool in [1] generalized manual pattern curation
into a reusable instrument.

To check that this generalized, rather than merely described, we ran the
template a second time on a project unrelated to Ecuador: *Harbor House*,
a travellers' inn intended to relieve pressure on homeless services, sited
in Sheffield, South Yorkshire — a different typology, region, and
climate, produced by the paper's first author. This second run also used
an LLM configuration with real web search available, so climate figures
and precedent references were checked against live sources and cited
inline rather than drawn purely from training-data recollection,
demonstrating the template is compatible with a stricter, source-checked
mode of use as well as the original's. The resulting document
(`templates/examples/sheffield.md`) follows the same section shape as the
Ecuadorian grammar while producing an entirely different vocabulary — dark
gritstone and coursed rubble rather than andesite, slate and Yorkshire
vernacular roof forms rather than red clay tile — which is the evidence
that the template captures a reusable *shape*, not a repackaging of
Ecuador-specific content.

## 4. Worked Example: Two Independent Deployments from Shared Inputs

### 4.1 Shared Inputs

Both tracks reported below share exactly two upstream instruments plus a
condensed brief: a project-specific pattern subset of 55 patterns from
Alexander, Ishikawa, and Silverstein [2], curated using the APL-Companion
web tool described in [1] and prepared for this project by Salingaros;
and the Ecuadorian Form Language Grammar described in §3.2. Both tracks
also drew on the same condensed brief and the same named-failure critique
described in §2. From that point, the two tracks are independent LLM
runs, by different authors, producing different outputs.

### 4.2 Track A: Four-Stakeholder Narrative Synthesis

Following the narrative-writing approach of [1] §4.2, Postle's track
wrote four separate experiential narratives, one per stakeholder
viewpoint (general visitor, museum staff, school group, and
indigenous/community stakeholders whose heritage the collection
represents), each independently grounded in the shared pattern subset and
form-language grammar, and cross-checked against a shared "chassis"
document of fixed invariants — site data, the material/color/ornament
systems, named circulation realms, and where each part of the collection
lives — so that a detail asserted by one stakeholder's narrative (a
material, a color, a named place) is never contradicted by another's.
The four narratives were then combined **in full**, not condensed, into a
single public presentation document, deliberately without pattern numbers
or grammar codes, since it is written to be read by the public, not by
practitioners. Thirteen illustration prompts were written, each
self-contained (the full shared style guide pasted literally into every
prompt, not cross-referenced), and generated externally via Midjourney,
producing images in a **warm architectural watercolor and gouache
register** — a painted presentation drawing, not a photo-realistic
render, with lighting, weather, and a consistent cast of figures held
constant across the set.

### 4.3 Track B: Single Merged Narrative

Salingaros' track produced a single narrative, *Casa de la Memoria
Ecuatoriana*, merged from an initial LLM draft and a second LLM pass
explicitly asked to reconcile it against the same pattern subset and form
language, then illustrated with 25 images from ChatGPT, in a markedly
more **photo-realistic register**. This track is also where the
project's clearest evidence for an iterative, natural-language critique
loop comes from: successive rounds of generated images were rejected and
corrected in plain language rather than by editing pixels — a patio that
read as faux-antique with trip hazards was regenerated with flush,
level pavers; an entrance that did not read as a front door on approach
was replaced by an axial view with a projecting five-bay portal; a
building raised too far above the street was brought down to sidewalk
grade; monochromatic tiled columns foreign to the context were
regenerated with patterned azulejos; and overly white interiors,
arbitrary facade color patches, and modernist metal railings were each
identified and revised. Each correction traced back to an explicit
violation of the pattern subset or form grammar, and each cycle of
criticism and regeneration took minutes, not days.

### 4.4 Convergence and Divergence

Table 1 summarizes the two tracks.

| | Track A (Postle) | Track B (Salingaros) |
|---|---|---|
| Narrative structure | 4 stakeholder-viewpoint narratives, combined in full | 1 merged narrative |
| Output document | `docs/counter-proposal.md` | `docs/3.Casa-de-la-Memoria-Ecuatoriana-*.txt` |
| Image generator | Midjourney | ChatGPT |
| Image count | 13 | 25 |
| Image register | watercolor / gouache illustration | photo-realistic |
| Consistency mechanism | shared chassis document (invariants) | iterative natural-language critique loop |

Despite independent execution by different authors with no coordination
on wording, both tracks converged on the same high-level design moves
required by the shared inputs: a stratified material sequence from stone
base to timber crown; an *atrio* / *zaguán* / patio arrival sequence; a
legible, projecting entrance portal; warm-toned interiors with restrained
concentrated ornament; and circulation organized around named realms
rather than corridors. This convergence is evidence that the pattern
subset and form-language grammar meaningfully constrain the output even
under independent LLM runs — the shared instruments, not authorial
coordination, are doing the constraining.

The two tracks diverge sharply, however, in visual register: Track B's
images are consistently judged — by the authors and by symposium
participants (§5) — as the more visually compelling and architecturally
credible of the two. We do not yet know why. Candidate variables include
the image generator itself, differences in prompt phrasing between the
two tracks, and how literally each generator resolves the same
form-language vocabulary into imagery; we have not isolated which, if
any, of these accounts for the gap, and we report it here as an open
finding rather than an explained one (see §6.3, §7).

## 5. Reception: Informal Peer Engagement at the July 2026 Symposium

On 23 July 2026, this counter-proposal project was discussed at a public
symposium including Salingaros, Nir Buras (Classic Planning Academy),
Pablo Álvarez Funes, and others, walking through Track B's narrative and
image process. We treat this as informal peer engagement, valuable
precisely because it included substantive disagreement rather than only
endorsement.

Participants praised the images' consistency of "spirit" — not pixel
repetition of a single scheme, but a recognizable design language holding
across independently generated views. But a practicing architect on the
panel, Pablo Álvarez Funes, raised a critique that is the paper's most
important piece of reception data: *"this Nikos did not create a
plan... we need to give a response to the program and ensure that all
the spaces work coordinately."* He characterized the current output as
a set of well-crafted individual rooms rather than a linked building,
adding that close inspection of the images — *"especially at the
corners"* — reveals AI hallucinations, and summarized bluntly: *"these
are images. These are flavors. These are not solutions."* The same
discussion noted the continuing, non-optional role of licensed
architects in taking such material to floor plans, elevations, sections,
and mechanical/electrical/plumbing/structural coordination before
anything could be built.

This critique is correct as stated, and it is not new information to the
authors — it names precisely the gap described honestly in the original
paper's limitations section [1] and inherited unchanged by this
extension: the method produces experiential narratives and illustrative
images of a design, not a coordinated plan. What the symposium adds is an
unsolicited, on-the-record confirmation from outside the authors' own
team that this gap is the one that most needs addressing next, which is
the direct motivation for §7.

## 6. Discussion: Drawbacks and Open Questions

### 6.1 No Coordinated Floor Plan

Because each narrative and each image is generated independently against
shared *rules* rather than against a shared *drawing*, spatial claims
made across different illustrations of the same design are not
guaranteed to reconcile. A concrete instance from this project: the
narrative describes the entrance portal as composed in "a rhythm of five
bays," but the corresponding illustration shows three arches. Rather than
regenerating the image to match the text or rewriting the text to match
the image, we treated the narrative as the design intent of record — it
is the instrument the pattern subset and form grammar were synthesized
into, and is where every design claim is traceable — and loosened only
the image's caption to avoid asserting a bay count the image does not
show. This is a defensible correction for a single instance, but it does
not scale: it works because a human noticed the discrepancy and had a
clear rule (text over image) for resolving it, not because the method
prevents such discrepancies from arising.

### 6.2 No Mechanism for Genuine Public Participation

The method as deployed here produces material intended to influence
public debate, but has no built-in mechanism for the public to actually
participate in shaping it beyond viewing and reacting to finished
narratives and images — e.g., informal social-media voting on generated
images. Symposium participants warned that such unfiltered voting
degenerates without curation (toward whichever image is most
immediately eye-catching rather than most sound), which is a caution
worth taking seriously if this method is to be used for participatory
design rather than only advocacy communication.

### 6.3 Unexplained Divergence in Image Register

As reported in §4.4, Track B's photo-realistic images are judged more
compelling than Track A's watercolor-register images by both authors and
by symposium participants, despite both tracks sharing the same pattern
subset and form-language grammar. We flag this honestly as an
unresolved variable of the method's current image-generation stage,
not as a property of one generator being categorically better than the
other — the two tracks differ in generator, in prompt style, and in how
much each image is asked to carry unaided (13 broadly-scoped prompts vs.
25 more narrowly-scoped prompts including deliberate parallel color and
material-cost variants). Isolating the cause would require a controlled
comparison outside the scope of this paper (see §7).

### 6.4 Unsettled Questions of Authorship and Structural Readiness

As with the original method [1], these outputs are concept studies, not
architecture: structure, egress, conservation environments, accessibility
compliance, and budget still require conventional technical development,
and questions of authorship and intellectual property in AI-assisted
imagery remain unsettled in general, not resolved by anything specific to
this project.

## 7. Future Work: Toward an Explicit Plan-Layout Layer

The critique in §5 — that the method, as run here, produces "flavors, not
solutions" because there is no shared floor plan behind the independently
generated images — is the clearest and most actionable finding this
deployment produced, and we take it as the method's next required
instrument rather than a criticism to be argued down.

We propose, without yet prototyping, an explicit **plan-layout
generation** stage inserted between the existing pattern-subset/
form-language inputs and the narrative-generation stage. The pattern
subset already encodes spatial and adjacency relationships implicitly —
patterns concerning building complexes, wings, connected buildings,
circulation realms, and entrance transitions are themselves claims about
how spaces relate to one another — and the project-chassis document used
in Track A already names specific circulation realms and collection
placements as fixed invariants. The proposal is to make this implicit
spatial information explicit: prompt an LLM to derive a bubble-diagram or
adjacency layout directly from the pattern subset and brief, before
narrative generation, so that subsequent narratives and image prompts —
whether one combined narrative or several stakeholder narratives, as in
this project — are *derived from* one shared layout rather than each
independently inventing a version of it. This would not, on its own,
produce a buildable plan; it would produce a shared spatial scaffold that
narratives and images could be checked against, directly narrowing the
class of discrepancy described in §6.1.

This is proposed as future work in this paper. A separate, exploratory
prototype of this idea exists as an open, lower-priority research task
outside this paper's critical path, and may be folded into a revision of
this section if it produces something worth reporting before publication;
its absence does not weaken any claim made above.

A secondary, lower-priority open question is the unexplained image-register
gap of §6.3: a controlled comparison — the same narrative text and the
same style-guide language, run through both generators — would help
isolate whether the gap is attributable to the generator, the prompt, or
some other variable, but is not required to support this paper's central
claims.

## 8. Conclusion

This paper reported a live deployment of an extended version of the LLM
pattern-language synthesis method introduced in [1], used in earnest, in
public, under real contested stakes, rather than as a hypothetical case
study. The deployment required a genuine method extension — a third
input, the form language, following Salingaros' theoretical distinction
between the human/organizational and geometric/tectonic languages of
architecture — which we generalized from a bespoke, project-specific
prompting process into a reusable template and validated on an unrelated
project. Run twice, independently, by different authors, from the same
shared pattern subset and form language, the method converged on
compatible design moves while producing genuinely different narratives
and a qualitatively different, currently unexplained, image register.
Presented to informal peer scrutiny, the work drew a substantive
critique, not only praise: that the method, as deployed, produces images
without a coordinated plan behind them. We agree with that critique, and
propose the explicit plan-layout instrument it implies as the method's
next necessary extension. Design knowledge, once written down as
readable rules rather than embodied only in a single expert's intuition,
can be executed, checked, criticized, and revised at the speed of
conversation — but a pattern language and a form language, however well
executed, are not yet a plan, and the honest next step for this method is
to build the instrument that makes them one.

---

## References

1. Postle, B.; Salingaros, N.A. LLM and Pattern Language Synthesis: A
   Hybrid Tool for Human-Centered Architectural Design. *Buildings* 2025,
   15, 2400. https://doi.org/10.3390/buildings15142400
2. Alexander, C.; Ishikawa, S.; Silverstein, M. *A Pattern Language:
   Towns, Buildings, Construction*; Oxford University Press: New York,
   NY, USA, 1977.
3. Salingaros, N.A. Two Languages for Architecture. In *A Theory of
   Architecture*; Sustasis Press, 2006; revised 2014.

## Data and Materials Availability

All primary materials referenced in this paper are project documents
rather than independently published data, and are cited here by their
path in the originating repository for traceability rather than as
formal references:

- Pattern subset: `ref/A Pattern Language Ecuador National Museum.md`
- Ecuadorian Form Language Grammar: `ref/Ecuadorian_Form_Language_Grammar.md`
- Condensed brief and named-failure critique:
  `ref/brief-condensed.md`, `ref/critique-failures.md`
- Shared invariants ("chassis"): `ref/project-chassis.md`
- Form-language prompt template: `templates/form-language-prompt-template.md`
- Template validation on a second project: `templates/examples/sheffield.md`
- Track A narratives and public document: `narratives/01-visitor.md`
  through `narratives/04-community.md`; `docs/counter-proposal.md`;
  illustration prompts, `docs/illustration-prompts.md`; images,
  `docs/images/`
- Track B narrative and images:
  `docs/3.Casa-de-la-Memoria-Ecuatoriana-Design-Narrative-Museo-Nacional-del-Ecuador.txt`;
  `docs/images-salingaros/`; process report,
  `docs/From-Pattern-Language-to-Architectural-Image-Salingaros-revised.md`
- Symposium transcript: `ref/youtube-transcript-2026-07-23.txt`
- Winning-scheme critique transcript: `ref/youtube-transcript.txt`