Remodeling by talking: editing a house plan with a Hermes agent
The short version. A friend just bought a house and is planning a remodel. The architect laser-scanned the house and is sending him exact drawings of it as it stands today. He doesn't want pretty pictures. He wants to type something like this and get a real answer:
“Put a 6' by 8' bathroom in the front-left corner of the room in the right rear of the house, and show the related changes in room dimensions.”
- AI is good with words and bad at exact math. It can work out which room "right rear" means. It shouldn't be trusted to work out where a wall lands to the inch.
- So we split the job. His AI assistant (a Hermes agent he already uses) reads the request, repeats it back in feet and inches, and waits for him to say yes. Then ordinary code draws the change on a copy of the architect's file.
- He gets back a before-and-after drawing with measurements, a list of every room that got bigger or smaller, and warnings about things a drawing can't answer, like plumbing.
- Cost: one new skill added to the assistant he already has. No new app or subscription.
The catch: the architect has to send the actual CAD file, not just a PDF. Asking for it is step one.
Figure 1. How one change works. Step 2 matters most: nothing gets drawn until the owner agrees with how the assistant understood him.
Why not just use an AI floor-plan app?
We looked. Several apps let you type changes in plain English, and they're fun for sketching ideas. None of them does this job well. They either work from a picture of the plan instead of the real measurements, or they make new designs instead of editing the house that exists.
| App | Good at | Why it doesn't fit |
|---|---|---|
| Maket | Typed changes, 3D view | You upload your plan as a PDF or image, so it traces a picture. Maket itself says its plans are for early ideas, not for building. |
| Luw.ai Studio | Typed changes, nice renders | Reading architects' 3D files is still an early test feature. Its output is labeled "not for construction or renovation". |
| Snaptrude | A real architect's tool with an AI helper | Built for architecture firms. Too much for a homeowner. |
| SketchUp's AI connector | Building 3D models from a description | It makes new models from scratch. It doesn't edit the architect's drawing. |
| Revit add-ons (Autodesk, others) | Real edits in the architect's own program | Revit only runs on Windows. He uses a Mac. |
We also looked at Grok Bot, xAI's assistant that runs on its own computer in the cloud. It could run the same code, but it can't reach files on his Mac (source). It would also be a second assistant to learn and pay for. He already uses Hermes every day, so that's where this goes.
Step one: get the right file from the architect
Figure 2. What laser-scan firms typically hand over (iScano, ViBIM).
A PDF is a picture of the plan. A CAD file is the plan itself: every wall has an exact position the code can measure. The request to the architect is one sentence: "Could you send the as-built floor plans as a DWG or DXF file along with the PDFs, plus an IFC file if you made a 3D model?" If only a PDF arrives, the assistant can still trace it. But every measurement it gives is then marked approximate.
What he gets back
Figure 3. A made-up example room, not his house. The numbers were worked out the same way the skill will do it. New walls are 4½" thick (a normal interior wall), and that space comes out of the room too.
Each change is saved as its own option (A, B, C…), so he can try a few ideas and ask "compare A and B." The architect's original is never changed. Every option starts from a fresh copy.
Who decides what
Figure 4. If two rooms could match what he said, the assistant asks instead of guessing. It also warns him when a change touches an outside wall, anything the architect marked as plumbing or structure, or leaves less than 30" to open a door.
Getting started (about 10 minutes, once)
- Hand over the files. CAD files are usually too big for a chat app, so they go into a shared folder.
- Name the rooms. The assistant numbers every room (R1, R2…), marks the front of the house, and lists each room's size. He fixes any names it got wrong. After that, "the guest room" and "R7" mean the same thing.
- Check its accuracy. The assistant measures three rooms and compares them with the architect's PDF. If any is off by more than ½", it stops and says so.
The plan
| Step | What happens | It worked if… |
|---|---|---|
| 1 | The architect sends the CAD file and PDFs | The files open and the sizes read correctly |
| 2 | We build the skill and test it on a copy, on our own machine first | Three rooms match the architect's PDF within ½" |
| 3 | We try his real request: the 6×8 bath | The drawing and the room list check out by hand |
| 4 | We give it a vague request ("the back room" when there are two) | It asks which one instead of picking |
| 5 | We back up his assistant, add the skill, and try it with him | The architect's file is untouched afterward |
For the technical reader: what's under the hood
The AI never moves a wall itself. It turns the sentence into a short instruction, and code carries it out:
# Option A, after the owner said yes
add_room_in_corner(room="R7", corner="front-left",
width_ft=6, depth_ft=8,
wall_in=4.5, door_side="long")Python libraries: ezdxf reads and writes the CAD file and makes the PDF. IfcOpenShell reads the 3D model file. shapely works out room shapes and areas, including L-shapes. The free ODA File Converter turns DWG into DXF when needed. First version handles: add a room in a corner, move a wall, add a wall, add a door, and resize a room. Anything else gets "I can't do that yet" instead of a guess.
Still open
- What the architect actually sends. All of this assumes a CAD file exists.
- Whether the house has more than one floor in the scan. Changes that cross floors, like stacking a bath above another, aren't in the first version.
- Whether the architect's file names the rooms. If it doesn't, the assistant finds rooms from the walls around them, and he names them once.