Prompt Rebuilds 1906 San Francisco Market Street in Blender
The prompt shows how to force an AI model into a rigorous research-then-build workflow: every modelled fact must trace to a cited source with a confidence rating, rather than free-form generation. Practitioners building historical reconstructions, game environments or generative 3D pipelines can adapt this pattern of source-file-first, generator-based assembly to their own Blender or procedural projects. It also demonstrates Blender Python scripting as a practical agent workspace.
Alex Albert shared a detailed prompt for Claude that recreates Market Street, San Francisco as it appeared on 17 April 1906, the day before the earthquake, entirely in Blender.
The prompt instructs Claude to build a sourced database from 1899-1905 Sanborn fire insurance maps, the Miles Brothers film "A Trip Down Market Street", period photographs from OpenSFHistory, the Library of Congress and the David Rumsey collection, plus USGS topography.
Claude is told to record each building's footprint, height, facade material and occupant with a confidence level, then model everything via Blender Python using reusable generators for Victorian facades, mansard roofs, bay windows, cable cars and horse-drawn wagons.
No downloaded meshes, textures or HDRIs are allowed, and the final deliverable is a 10-second video up the street.
Prompt in Claude Tag "Recreate Market Street, San Francisco as it stood on April 17, 1906, the afternoon before the earthquake, in Blender. Scope: the Ferry Building up Market to Fifth Street, including the Palace Hotel, the Call Building, the Chronicle Building, Lotta's Fountain and the Emporium. Before modeling anything, build a source file from: the 1899-1905 Sanborn fire insurance maps (footprints, heights, materials, occupants), the Miles Brothers film "A Trip Down Market Street" (April 1906), period photographs from OpenSFHistory, the Library of Congress and the David Rumsey collection, and USGS topography. Record every building with footprint, height, facade material, occupant, and the source for each fact with a confidence level. Build everything in Blender Python. No downloaded meshes, textures or HDRIs. Write reusable generators (Victorian commercial facade, mansard roof, bay windows, awnings, painted signage, gas and electric street lamps, cable car, horse-drawn wagon, early automobile) and assemble the street from the source file, so every building traces back to data. Provide a 10 second video up the street."📊 8 ⚡
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude, Blender, prompt engineering, 3D modeling.
Source attribution: curated from Alex Albert (@alexalbert__).