WeeklyDynamo: Generative Design and Dynamo for AEC

 Research Log [2026 08 16]: Diagnosing and Automating a Phone-to-PC Remote Control Link for an LLM Agent 1. Objective Driving an LLM agent on a desktop machine from a phone is useful for a specific reason. The agent operates on the real files that exist only on that machine, including models, scripts, and drawings, so work started at the desk can be continued while away from it. A cloud session cannot do this, because the files are not there. The link had been in use for about a month and it stopped working one morning. This log documents the diagnosis, the three separate causes that were found underneath the failure, and the configuration that now survives a reboot. It also documents six errors in my own diagnostic reasoning, because those errors consumed roughly five hours and are more generally useful than the fix itself. 2. Summary of Work The failure had three independent causes that happened to coincide. A refresh token had expired on a thirty-day clock, an autostar...

 Over the past year I built five different 3D viewers for AEC work - routing, structural review, tunnel sections, a Revit perspective tool, a spreadsheet-to-3D viewer. Before I trusted my own instincts about how to build them, I did two things: I profiled all five on the same GPU, and I studied how 32 other AEC 3D tools - Autodesk Forma, Speckle, TestFit, xeokit, Bentley iTwin, and more - solve the same problem. This post is both halves: what the industry chose, and then what my own measurements showed. The short version is that rendering is a commodity, and the interesting decisions are everywhere else. Part 1 - What 32 AEC viewers actually chose I expected a mess of proprietary engines. Instead the choices collapse into six patterns, and the deciding question is never "which renderer is best" - it is "what is our actual moat."

  [Part 1] Current Status & Strategic Direction: [<Newsletter Link] We ruthlessly dissect the legacy flow distribution analysis process. Here, we pinpoint the exact parametric automation triggers required to validate fluid dynamics at intersection zones. (Goal: Stop bleeding senior engineering hours on manual setups.) [Part 2] Deep-Dive into Test Samples (The Architect's Logic): An architectural autopsy of the operational mechanics behind our test models. We will break down the 5-stage Python pipeline integrated with our custom math/physics engine (Faux-CFD). (Warning: Strictly high-level logic and data structures; no basic hand-holding.) [Part 3] Generative Design & Revit Automation: We deploy AI algorithms for multidimensional analysis, hunting down the absolute optimal baffle configurations, and executing seamless Revit automated generation (Baking). (Perspective: Redefining GD from a simple optimization tool to your firm's synthetic data factory.) [Part 4] ...

 A Case Study on Tunnel Alignment and Geologic Constraints https://www.linkedin.com/pulse/alignment-optimization-how-inputoutput-settings-drive-wonho-cho-kg0qc Introduction: Generative Design is Not a Slot Machine There is a common misconception that Generative Design (GD) is simply a tool for creating thousands of random alternatives. However, the true power of GD lies in its ability to "Converge" —to self-evaluate, discard inferior options, and evolve toward a superior solution. In this post, we analyze a civil engineering case study (Tunnel Alignment Optimization). We will explore how to transition from simple geometry generation to a sophisticated optimization engine that accounts for geological strata and construction costs. 1. From Simple Geometry to Real-World Data The initial phase of any automation script usually involves simple geometric rules: "Draw the shortest line from A to B while avoiding obstacles." However, real-world infrastructure requires more...

  How we stopped AI from writing bad code and taught it to generate geometry. https://www.linkedin.com/pulse/geometry-image-to-geometry-workflow-dynamo-gemini-wonho-cho-4u3yc Introduction: The Evolution of Image-to-Geometry Four years ago, we first tested automated modeling from images using simple edge detection. Today, we are pushing the boundaries further by integrating Generative AI (Gemini) to not just "trace" lines, but to understand and reconstruct geometric patterns. In this post, I share the technical journey of developing a "3-Stage Decoupled Pipeline" that translates 2D images into parametric Dynamo geometry, and how we solved the chaos of AI-generated code. 1. The Failures: Why "AI Coding" Doesn't Work Phase 1 (The 'AI Coder'): We initially asked AI to write Python code to draw the image and executed it blindly. Result: Total system failure. A single syntax error crashed the entire script. AI is creative, but code requires stri...

Integrating Human Design Intent into Automated Layouts (feat. CAD to Revit Workflow) https://www.linkedin.com/pulse/layout-review-wonho-cho-ubjgc Introduction: The Missing Piece in Automation The central water treatment process varies depending on the situation, but the flow is critical according to the exact plan. When implementing integrated flood control plans, we often turn to Generative Design (GD) to find the optimal layout. However, a common pitfall exists: raw algorithms often produce results that are mathematically "correct" but practically useless. In this post, we review a case study conducted with Kunhwa Engineering, exploring how to bridge the gap between algorithmic generation and human engineering judgment using Dynamo and Revit. 1. The Workflow: From CAD Lines to Dynamo Logic The process begins with legacy data. We separated the CAD area of the alternative into site boundaries, spaces, and facility areas. CAD > Revit > Dynamo: instead of drawing from scr...

  [September 13, 2025] Today’s Research Log: Verifying the Integration of Dynamo with the Gemini Vision API and its Limitations 1. Objective 🎯 The goal was to build an automated workflow within the Autodesk Dynamo environment. This workflow would use Python scripts to connect with Google’s multimodal AI model, aiming to receive image files from the AI that were either modified or newly generated. 2. Summary of Work 💡 I wrote a Python script to call the Google Gemini Vision API from Dynamo and attempted to integrate the API while resolving a series of network and model errors. Through systematic debugging and testing, I discovered that the initial goal of generating images with the ‘Nano Banana’ (Gemini 2.5 Flash) model is not currently supported by the API. As a result, while I successfully created a stable workflow that takes an image as input and returns a text analysis, I concluded that the original goal of image output could not be achieved. 3. Detailed Process & ...

  https://www.linkedin.com/pulse/modular-placement-usability-review-generative-design-wk4zc E(ent) entrance, T(1x2), T(1x1.5), R placement and shortest distance generation 이미지 최소화 이미지 변경 이미지 삭제 The shortest distance was output to confirm that the bathroom's position was as far as possible. However, with L, K, M, and F not yet placed, it was confirmed that many variables exist to determine an appropriate placement. 이미지 최소화 이미지 변경 이미지 삭제 As a result of confirming the furthest L value, the justification for R's placement was also found to be insufficient. After placing K and L, additional review of R's placement suitability is needed. 이미지 최소화 이미지 변경 이미지 삭제 Even with a close L value, it is possible to derive the conclusion that a long distance can be calculated in reverse depending on the placement of R, F, and M. Finding Usable Space Through Additional Placement of F, M 이미지 최소화 이미지 변경 이미지 삭제 Confirm GD results to consider L, K placement in the remaining space after placing E, ...