글

라벨이 Dynamo인 게시물 표시

From Teaching Clicks to Leading AI Agents: How My Dynamo and Revit Class Changed in Two Sessions

이미지
I am teaching a special lecture series of five sessions at a university, and over the second and third sessions I stopped teaching Dynamo the way I had taught it until now. The students no longer follow my clicks node by node. They watch a concept, watch an AI agent apply it, and then review the result together with me. This post puts the two sessions side by side, because what changed was not the software on the screen but the way I teach and the way I lead the work, both the class and the agents in it. In short November 11: I gave one prompt to four AI coding agents. Wherever the prompt left a decision open, each agent made that decision on its own, and every decision about form sat on the geometry cycle we had practiced earlier in the same class. November 18: the small graph I built in class became the prompt. While I kept teaching, an agent turned my 26-node graph into a 97-node Dynamo graph for a two-storey house without a single Python node, testing its builds four times...

Dynamo Generative Design for Water Treatment Plant Layout

At Autodesk University 2025 I had about three minutes. The segment sits at 27:30 inside Sol Amour's session Exploring the Dynamo Product Road Map and Vision for the Future , which runs 46:30 in total, and the subject was water treatment plant layout generated with Generative Design. Three minutes is a reasonable amount of time to demonstrate that something works. It is nowhere near enough time to show another engineer how to rebuild it. This month the same material had to become a twelve-hour course, delivered over two days to practising engineers at a public-sector training academy. Expanding a three-minute demo by a factor of two hundred and forty sounded absurd when I first wrote the number down, and then I built the curriculum and discovered that the ratio was never the interesting part. A demo and a course are not the same content played at different speeds. They are largely different content, and the portions that survive the translation are not the portions I would have ...

Parsing 149 GB of JSON Without Loading It Into Memory

이미지
  Part 9 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. When the work stopped, it had left 149 GB of snapshots on a desktop drive. The obvious next task was to delete them. This post is about what happened when I tried to establish that deleting them was safe — which turned out to be a longer job than the deletion, and ended with a different answer than the one I started with.

Prompt Engineering for BIM: 101 Instructions, One Drawing

이미지
 Part 7 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. Over eleven days, on a single tunnel section, the transcript logged 106 turns from my side to an AI coding assistant. It wrote thousands of lines of Python and JavaScript in response. But when I went back and read the whole thing, what surprised me was not the code. It was that only 17 of those 106 turns actually asked for a shape. The other 89 were corrections, rejections, questions, requests to see the screen, one long apology for having said the wrong thing — and five that I never typed at all, which section 2 accounts for. The honest count of instructions I actually sent is 101.

Revit TessellatedShapeBuilder Returns a Mesh, Not a Solid

이미지
  Part 6 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. For six weeks the web viewer said the geometry was fine. Then the same polylines went into a Revit add-in and three of the bands would not build at all. This is the last stretch: an add-in, thirteen versions in one afternoon, and a root cause that only appeared once I stopped looking at screenshots.

Validation Gates That Always Pass: Add a Negative Control

이미지
  Part 5 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. By the middle of the project the instructions stopped sounding like design work. They stopped being "build the tunnel section" and became "this part, this property, this authority." That shift is what let a pixel-level gate exist at all — and the gate then spent most of its life proving that its own failures were not what they looked like.

AI for BIM (Human-in-the-Loop): Make It Ask, Not Guess

이미지
  Part 4 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. Two AI agents worked this job, and the division of labour between them flipped twice. What made the arrangement work had nothing to do with which one was "the implementer".

Dimension Lines vs Real Edges: 9 Cases an AI Got Wrong

이미지
  Part 3 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. Every drawing carries two kinds of line that look nearly identical to a machine and completely different to a person. One is the edge of real concrete. The other is a graphic whose only job is to say how big that concrete is.

Dynamo Code Blocks and the Cost of 137 Hardcoded Values

이미지
  Part 2 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. Somewhere in the original graph there is a code block that reads 725+625; . The author did not write 1350 , and that choice tells you everything: 725 and 625 were two separate real dimensions, and they were trying to leave a trail.

Dynamo Built the Whole Tunnel and Never Read the Excel File

이미지
  Part 1 of a series — a Dynamo tunnel geometry that was already finished, a 39-sheet Excel workbook it had never been wired to, the web viewer built to referee the two, and the Revit add-in at the end of it. A working Dynamo graph already existed. It produced the full 3D geometry of a Korean road tunnel project (NATM), 892 m of it, and it ran without errors. The problem was that nothing inside it knew where its numbers came from.

From Concept to Dynamo: The Trial-and-Error Behind a Generative Design Workflow

이미지
A long-form project note about translating a pathfinding concept into a Dynamo and Generative Design workflow, including CAD geometry, Revit Generic Model caching, Data.Remember, scalar GD outputs, and the failures that shaped the final structure. From Concept to Dynamo: The Trial-and-Error Behind a Generative Design Workflow Building the concept is one task. Moving it into a real .dyn workflow is another. A few days ago I published Automation Lab: Runnable Pathfinding Experiment . That post introduced a small browser-based experiment: place start points, end points, and obstacles on a canvas, then generate route options around blocked areas. On the web, the idea is easy to understand. A point is a point. An obstacle is a drawn shape. A route is a line. The coordinate system is controlled, the geometry types are clean, and every object is created by the application itself. That makes the browser experiment useful as a concept layer. It can show the intent quickly: generate a ro...

A Practical Comparison of Generative Design Tools: Dynamo, Grasshopper, and AI Design Platforms

Generative design is often described as a way for software or AI to create design options automatically. In practice, the more important point is not automation itself. The real value comes from defining design variables, evaluation criteria, and a search strategy so that many alternatives can be generated, compared, and improved. For AEC workflows, this matters because design decisions are rarely based on a single criterion. A building option may need to balance area efficiency, daylight, cost, constructability, code constraints, structural logic, and documentation requirements. Generative design tools help explore that decision space, but each tool is built around a different workflow and level of control. The Basic Structure of Generative Design Most generative design workflows can be understood through three components: a generator, an evaluator, and a solver. Component Role Generator Creates design alternatives from input variables and constraints. Evaluator Measur...

From Generative Design Optimization to Quantity Takeoff Automation: Building a Scalable AEC Process System

이미지
From Generative Design Optimization to Quantity Takeoff Automation: Building a Scalable AEC Process System In many AEC workflows, Generative Design optimization and Quantity Takeoff automation are treated as separate topics. One belongs to the front end of design exploration.   The other belongs to the back end of documentation, estimation, or reporting. But in real projects, especially repetitive and high-complexity projects, that separation is too artificial. The real opportunity is not to optimize a layout in isolation, and not to extract quantities only after the design is already fixed. The deeper opportunity is to build a connected system where: - spatial logic - room classification - layout rules - object libraries - placement automation - parameter logic - quantity extraction are designed as one continuous workflow. That is the difference between isolated automation and scalable process architecture. The real problem: many AEC automations stop at one layer This is a re...