New Paradigms for Agentic Data Orchestration in Multi-Platform Design Workflows and Performance Evaluation Nov 16-17
When
Where
Hosted By
Panelists
Synopsis
The current status quo of large language models (LLM) and emerging trends in agentic orchestration provide new opportunities for early design investigation, geometry optioning, and performance evaluation. Although the LLM itself deals with uncertainties, these new paradigms enable opportunities for connecting and using actual developed and reviewed tools (like Grasshopper files or Python modules) while having the LLM as an assistant to chat with and connect different pieces.
Based on Walter P Moore’s (WPM) well-known reputation in stadium design, this workshop aims to focus on designing a stadium roof based on a real-world project and its constraints. The primary objectives include truss exploration and form-finding of a given span while optimizing material efficiency and depth reduction. To achieve this, we will orchestrate design exploration through agentic data coordination. Parametric models will be connected to the orchestration server so we can navigate through design iterations via chat while updating the main geometry. In the case of the arena roof, we are optimizing material efficiency and depth while allowing for a flexible rigging system below, which will change for various event types. As part of the process, WPM’s in-house tools - reviewed calculators inside a web-based workflow we call Emulation Lab - will be connected locally and through APIs to the orchestration server for structural analysis and embodied carbon investigation.
The workshop will combine theoretical presentations that provide a thorough understanding of agentic automation concepts driven by large language models with practical, hands-on sessions focused on constructing various components of the orchestration hub. The program will conclude with a session where participants present their projects and explore how to implement relevant protocols and develop custom tools to address their specific design challenges.
Learning Objectives
Participants will be introduced to the agentic automation concept powered by large language models and find out about the differences between common scripting approaches and execution nodes via API gateways or external software. The workshop will focus on real-world-inspired architectural geometry as a case study, as the participants will build their first orchestration hub to form a communication bridge to control the parametric exploration of architectural design options through chat. The coupled API integration, as well as an external database/calculator for performance evaluation, will be added to the pool of execution nodes to enrich the design exploration.
Participant Prerequisites
Required skills: Advanced Rhino/Grasshopper knowledge and Python programming skills. Basic knowledge of data structures and API integration.
Required software: Rhinoceros 8, Visual Studio Code (or similar IDE), Microsoft Excel.
Required hardware: Personal laptop with Windows 10 or later