# GPT-Astra in Architecture: Agentic AI Modeling with Astra, Fable, Rhino and Revit > The last three years of conceptual architecture with AI have been greatly influenced by images. Diffusion models gave us seductive pictures yet with little geometry to work with, nothing to properly measure, cost, or coordinate. That gap is now closing: AI models no longer descr… ## At a glance - Format: On-demand course - Price: €85.00 (list €120.00) - Difficulty: Beginner - Duration: 5 Hours - Schedule: Oct 4, 2026 - Instructors: Fredy Fortich - Categories: Artificial Intelligence - Software: Rhinoceros 3D, Autodesk Revit, ChatGPT, Claude AI - Students: 87 - Rating: 5.0 / 5 - Canonical: https://paacademy.com/course/GPT6-Astra-Architecture-AI-Modeling-Fable-Rhino-Revit - Enroll: https://paacademy.com/course/GPT6-Astra-Architecture-AI-Modeling-Fable-Rhino-Revit --- ## About this course This workshop teaches architectural designers how to move AI beyond conceptual image rendering and into live CAD and BIM production using Rhino 8, Revit, and Model Context Protocol (MCP) integrations. Over five hours, participants learn to convert spatial briefs into explicit parametric rule sets for a mid-rise mixed-use housing block. You will generate rule-checked massing studies and group definitions in Rhino while executing model audits, family parameter management, clash detection, and schedule exports in Revit. The curriculum also covers context engineering, token budgeting, and live dual-model benchmarking comparing GPT-6 Astra against Claude Fable 5. Designed for intermediate users with foundational Rhino and Revit experience, the course requires active Pro subscriptions to ChatGPT or Claude.zoo ## What you'll learn - How to install, configure, and triage Rhino MCP and Revit MCP setups - How to write project context files that guarantee consistent AI behavior - How to drive Rhino for automated massing generation and layer discipline - How to operate Revit for BIM querying, parameter auditing, and schedule exports - How to benchmark GPT-6 Astra against Claude Fable 5 on live tasks - How to optimize token costs and protect project models from prompt injection ## Methodology This workshop shifts AI-assisted architectural design from chaotic prompting to strategic execution by converting spatial briefs into explicit, parametric rule sets before any agent touches the project. Operating on a strict "read and plan first, write second" protocol, it requires every spatial connection and workflow strategy to be verified before granting write access to tools, serving simultaneously as a core safety habit and a debugging framework. The methodology prioritizes context engineering over prompt phrasing, recognizing that curated reference data, managed token budgets, and prompt caching dictate generation quality far more than stylistic language. Under this division of labor, the AI acts strictly as the draftsman managing tedious, repetitive, and automatable tasks, while the architect steps into the role of editor defining intent and auditing spatial outputs. To ensure rigorous standards, results are continuously validated through dual-model benchmarking, subjecting identical briefs and Model Context Protocol (MCP) setups to two separate models judged against a single custom rubric. ### Scope: This workshop focuses on a mid-rise mixed-use housing block on a constrained plot, where spatial logic relies on legible, testable rules rather than subjective intuition. Capitalizing on the AI's strength in consistent rule execution, participants translate constraints such as setbacks, unit mixes, cores, heights, and façade modules into deterministic scripts. Two technical tracks demonstrate rule enforcement across design phases. The Rhino track targets massing logic, stacking rules, variant generation, and group definitions for early-stage geometry. The Revit track focuses on model interrogation, family parameters, clash detection, and data scheduling for documentation. Throughout both, the AI serves as draftsman while the architect retains strategic editorial control. ### Program: - Setup: Installing Rhino MCP and Revit MCP, client configuration - The State of the Race: Frontier models, agentic versus generative AI, MCP as the AEC connective layer - Methodology, Tokens, and Cache: Mapping the approach, context packs, token budgets, prompt caching - Break Modeling with Rhino MCP: Toolsets, rule-checked massing, variants, and group definitions - Break Modeling with Revit MCP: Toolsets, live model auditing, and parametric family modeling - Dual-Model Benchmarking & Practice Roadmap: Model evaluation, cost comparison, and workflow implementation ## Curriculum ### Section 1 - Introduction &. PAACADEMY Updates (09:11) - MCP Installation (01:06:18) - Introduction to Agentic Modeling with AI (18:41) - Token-Efficient Modeling Strategies (37:50) - Advanced MCP Management: Security, Caching, and Agentic Delegation (56:26) - Advanced AI Prompting: Overcoming Limitations and Creating Parametric Elements (39:50) - AI System Design: Parametric Revit Families, Grasshopper Workflows, and Automated Documentation (42:08) - Final Thoughts, Limitations, and Q&A (14:50) ## FAQ ### Who is this workshop for, and what prerequisites are required? This workshop is designed for intermediate users with foundational knowledge of Rhino (layers, basic geometry) and Revit (families, parameters). The course focuses on AI tool integration rather than basic software navigation. ### Do I need active subscriptions to both ChatGPT and Claude? Having active Pro subscriptions to both ChatGPT (Desktop/Codex) and Claude (Desktop/Code) is recommended to participate in the live dual-model benchmarking exercises. However, having access to at least one of these platforms is sufficient to follow the curriculum. ### What software and hardware do I need to prepare beforehand? You will need a computer capable of running Rhino 8 and Revit (versions 2023 through 2026). The specific Rhino MCP and Revit MCP integrations will be provided during the setup portion of the workshop. ### How does this approach differ from standard text-to-image AI tools? Instead of generating static images or text descriptions, Model Context Protocol (MCP) allows AI agents to directly interact with CAD and BIM software. The output is a functional project file with native layer structures, parameters, massing definitions, and editable schedules. ### What practical skills will I take away from this session? You will learn to configure MCP integrations, write structured context packs to prevent AI errors, execute automated massing studies in Rhino, run model audits in Revit, and evaluate AI model performance and costs for office implementation.