ARCHIE — Web environment showing the four specialised workspaces and UK Building Regulations Desk
Figure 1 · The ARCHIE Web Environment The full online interface running on a tutor-owned local server. Four numbered workspaces (Tool, Code, Context, Render) are accessible from the navigation sidebar at left alongside quick reference panels for Approved Documents B, K, L, and M. The active pane displays the UK Building Regulations Desk with retrievable, legally grounded citations.

ARCHIE

An AI platform for architecture students: four specialised workspaces on a privately hosted server

AI Learning Platform Local Server Hosting Level 5 Studio 2025–present 25 Active Users

Overview

A student working on a studio project holds several kinds of question at once. Some are technical, such as how to set up a sheet in Revit. Some are regulatory, such as the permitted gradient of a ramp under Part M. Some are academic, such as what a brief is actually asking for. Some are visual, such as how a proposed material might read in an image.

These are different questions. They require different sources, different forms of reasoning, and different degrees of caution. In practice, students ask all of them in the same place. They open a general-purpose chatbot and type.

The result is predictable. The tool answers every question in the same confident register. A regulatory query returns a plausible number with no legal basis. A software query returns a workflow for a version that does not exist. The student cannot tell which answers are grounded and which are invented, because the interface gives no signal either way.

ARCHIE was built to separate these questions again. It is an online suite of specialised tools, organised into dedicated workspaces. Each workspace is configured for one class of task:

  • The Building Regulations Assistant is grounded in existing UK legislation through GOV.UK, so that it retrieves rather than recalls.
  • The Software Tutor is scoped to the specific packages taught on the programme.
  • Brief Me works directly from module documentation and assignment briefs.
  • The Visualisation Agent generates and edits imagery for exploratory purposes only.

A second concern shaped the platform as much as the first. Commercial AI services require student work to leave the institution. Design drawings, unpublished briefs, and assessment material pass to a third party under terms the student has not negotiated. ARCHIE therefore runs on a server I own and administer. Data is stored locally. It cannot be copied, exchanged, edited, or otherwise manipulated by any third party.

The platform is deliberately modest in scope. It does not attempt to replace the tutorial. It attempts to remove from the tutorial the questions that never needed a tutor.

The Platform & Workspaces

ARCHIE presents four workspaces from a single interface. The student selects a workspace and the system reconfigures around that task. The web (Fig 1) and mobile (Fig 2) versions carry the same tools, so that studio work and site work draw on the same support.

01 — Software Tutor

Guidance on AutoCAD, Revit, and SketchUp. The workspace covers setup, workflow, and technique. It answers the specific procedural questions that consume disproportionate studio time and rarely produce learning when answered by a tutor.

Software Tutor in operation: student requests AutoCAD guidance
Interactive Tool Demonstration · 01 Software Tutor in Operation A student requests step-by-step guidance on an AutoCAD workflow and works through the response. The exchange is procedural, self-contained, and previously would have occupied scarce tutorial time.

02 — Building Regulations Assistant

Real-time guidance on the UK Approved Documents, Parts A to S. The workspace is grounded in published legislation rather than model memory. It returns measurements, escape distances, riser dimensions, and ramp tolerances against a retrievable source. A reference panel gives direct access to the parts students consult most often, namely B (Fire Safety), K (Protection from Falling), L (Conservation of Fuel & Power), and M (Access to and Use of Buildings).

Building Regulations Assistant in operation: querying Approved Documents
Interactive Tool Demonstration · 02 Building Regulations Assistant in Operation A student queries a regulatory compliance requirement. The response is retrieved against published statutory legislation with exact clauses and limits, distinguishing this workspace from generic speculative AI models.

03 — Brief Me

Support with assignment briefs and lecture content. The workspace works from module documentation. Students use it to interrogate what a brief requires, and to revisit taught material at the point of need rather than at the point of delivery.

04 — Visualisation Agent

Image generation and editing, for inspiration and for rendering. The workspace supports visual exploration during early design development. Its outputs are explicitly positioned as exploratory material, not as finished proposals.

Infrastructure & Data Ethics

The hosting decision is pedagogic, not merely technical.

Student design work is unpublished intellectual property. Assignment briefs are institutional material. Neither should be transferred to a commercial provider as a condition of receiving help with a drawing.

ARCHIE therefore runs on a tutor-owned local server. Student interactions remain within that server. There is no third-party route to copy, exchange, edit, or otherwise manipulate the data held there. The arrangement removes the privacy objection that otherwise attaches to AI use in studio teaching, and it removes the risk of data loss through a change in a provider's terms.

The arrangement also carries an argument. Students who use ARCHIE encounter an AI system whose ownership and data handling are visible and accountable. That is itself a lesson about the tools they will meet in practice.

Pedagogic Structure

ARCHIE was introduced into Level 5 Design Studio in Spring 2026 as a support layer, not as an assessed component. Four progressive stages structured its integration:

  • One: Framing. Students were introduced to the platform alongside an explicit account of what each workspace can and cannot do. The Building Regulations Assistant retrieves legislation and should be checked against it. The Visualisation Agent produces images that are not designs. The distinction between a grounded answer and a generated one was taught before the tool was used.
  • Two: Use at the point of need. Students used the platform independently throughout the project. Access was continuous across web and mobile, so that a regulatory query could be resolved on site and a software query resolved at the desk.
  • Three: Displacement of the tutorial agenda. Technical and regulatory questions were routed to the platform in advance of tutorials. Tutorial time was thereby freed for questions the platform cannot answer, namely those concerning design intent, spatial judgement, and the defence of a proposition.
  • Four: Evaluation. Student experience was gathered at the end of the module, and tutorial content was observed across the delivery period. Both informed the current development cycle.

Learning Theory in Practice

The design draws on constructivism and connectivism, and on a straightforward reading of cognitive load:

  • Constructivism: Constructivist teaching asks students to build understanding through their own activity. That activity is obstructed when a student stalls for an hour on a software setting. ARCHIE removes the obstruction without removing the task. The student still resolves the drawing. They simply do so without losing the afternoon.
  • Connectivism: Connectivism holds that knowledge resides partly in the networks a learner can draw upon. ARCHIE makes one such network explicit and legible. Its workspaces are separated so that students learn where a given kind of knowledge properly comes from. Legislation comes from legislation. Software procedure comes from documented practice. Design judgement comes from neither, and must be constructed by the student in tutorial.
  • Cognitive Load Theory: Novice designers in the middle years of a programme carry technical, regulatory, academic, and representational demands at once. Reducing extraneous load on the first two releases capacity for the third and fourth. The observed change in tutorial conversation is consistent with that expectation.

Outcome & Evaluation

ARCHIE has completed one deployment, in Spring 2026, with 25 active student users across Level 5 Design Studio.

The principal finding concerns the tutorial: tutorial conversations shifted away from technical troubleshooting and towards design reasoning. Students arrived having resolved procedural questions themselves, and used the tutorial for the architectural argument rather than the software. This was the outcome the platform was designed to produce, and it is the outcome most worth testing further.

Student evaluation reported high satisfaction with the platform across accessibility, clarity, and speed of guidance.

The platform was presented at the UCAS Creative Career Showcase in November 2025, where it was used to demonstrate the department's approach to AI in architectural education to prospective applicants and their advisers.

The evidence base is deliberately stated at its true strength: one module, one cohort, one semester. The finding is encouraging rather than established. Development continues, and further deployments will determine whether the effect holds across cohorts and levels.

DOCUMENTATION

Environment & Interface Design

Figure 1 · ARCHIE Web Environment showing four workspaces and UK Building Regs Desk
Figure 1 · Web Environment The full ARCHIE desktop interface. The four workspaces are listed at left as a numbered set labelled by function: tool, code, context, and render. The active workspace shows the UK Building Regulations Desk with statutory clause retrieval.
Figure 2 · ARCHIE Mobile Environment on handheld device
Figure 2 · Mobile Environment The same four workspaces optimised for handheld devices. Built because regulatory and technical questions arise away from the studio during site visits and measured surveys, maintaining full feature parity.
Significance

If a studio tutorial is the scarcest resource in architectural education, questions that do not require a tutor should not be asked in one

ARCHIE rests on a single argument: removing technical bottleneck questions from the tutorial frees educators and students to focus on spatial judgement, design intent, and propositional defence. Five claims follow from the work.

  1. Sustained Willingness to Try New Ideas that Improve Outcomes

    The platform was not adopted from an off-the-shelf catalogue. It was identified as a pedagogic need, designed, built, deployed, and evaluated. That sequence has been repeated across my teaching, and ARCHIE is its most recent instance rather than an isolated experiment.

  2. Continuous Pedagogical Development

    The platform is at alpha stage and is openly described as such. It is under active revision in response to a first deployment. Teaching development is treated here as an iterative practice with a version history, not as a completed reform.

  3. Scholarship of Teaching and Learning

    A pedagogic problem was defined, an intervention was designed against it, and the intervention was evaluated at module scale with a stated and testable finding. The limits of that evidence are declared. This is educational enquiry conducted on my own teaching, informing subsequent practice.

  4. Technical Capability Applied to Educational Ends

    I designed, built, and now maintain the platform alone, including its local server infrastructure. The privacy architecture was a pedagogic decision executed as a technical one. Few AI interventions in architectural education are authored by the educator who deploys them.

  5. Considered Position on Emerging Technology

    ARCHIE separates grounded retrieval from open generation, and teaches students to recognise the difference. It is a demonstration that AI can be introduced into a studio without ceding student data, student judgement, or the tutorial itself.