A conversation.
A complete engineering pipeline.
Explore the local CAD architecture, open-source engines, modeling flow and evidence behind every accepted revision.
How Intact comes to life
Intact Simulation connects a conversation in ChatGPT to a local engineering workspace. ChatGPT interprets the design brief and chooses tools. Intact coordinates those tools, builds real geometry, records revisions and returns measured evidence. The CAD kernel constructs the shape; a numerical solver computes supported analysis results. The viewer makes both inspectable.
The system brings together Python engineering tools, a typed Model Context Protocol (MCP) interface, isolated workers, versioned project storage and a browser viewer. Intact’s contribution is the workflow between them: preserving design intent, binding edits to actual geometry, checking exports and keeping results associated with the revision that produced them.
Three boundaries that matter
- Conversation
- Your signed-in ChatGPT client provides AI reasoning. Intact does not contain trained language-model weights and does not retrain ChatGPT on your models.
- Local engineering
- CAD and supported numerical work execute in the installed native Windows runtime. Linux source installations retain their own isolated runtime. Projects and runtime files are separate from the installation package.
- Public website
- The Finished Work viewer displays prebuilt examples and recorded evidence. New custom CAD and new numerical studies run through the installed plugin.
The flow from a geometry request to a saved model
The workflow applies to supported parts, assemblies and sampled structures. “Any geometry” is a design ambition, not a guarantee that every requested shape or operation can be constructed. Essential missing dimensions or ambiguous references must be resolved before committing a design.
- Define the brief. State units, the envelope, components, hole patterns, mating interfaces and intended output. Separate exact dimensions from assumptions.
- Save checkable design requirements. Record supported checks for dimensions, placement, component count, holes and clearances. Missing criteria remain unverified.
- Choose a representation. Use native solids for exact CAD operations, constrained sketches and a feature graph for explicit parametric relationships, or a sampled mesh for implicit TPMS geometry.
- Prepare the build. ChatGPT supplies a bounded Python program and named numeric parameters, or structured sketch/feature operations. Existing designs retain their model identity, unrelated parts and revision guard.
- Execute in an isolated worker. The server checks input policy and dispatches computation. Generated CAD Python runs in Windows AppContainer with bounded Job Objects, or Linux bubblewrap for source installations, with filesystem/network restrictions, resource limits and a timeout.
- Audit the candidate and exports. Check topology, finite coordinates, positive volumes, mesh integrity where applicable and preservation through export. Only bounded repairs that preserve geometric invariants are allowed.
- Evaluate saved requirements. Measure supported acceptance criteria against native exported geometry. A known failed requirement blocks publication of that proposal.
- Decide: publish or repair. A successful proposal becomes a new revision. A rejected build preserves the last saved design; repair the failed feature without removing requirements merely to pass.
- Inspect and deliver. Compare measured facts and rendered views with the brief. Export the appropriate native or mesh formats and disclose assumptions and unverified checks.
The engineering stack and each tool’s job
| Layer | Technology | Why it is used |
|---|---|---|
| Tool contracts | Python, MCP, Pydantic | Typed requests, explicit operations, validated settings and structured responses. |
| Native geometry | build123d 0.13, OpenCASCADE | Solids, booleans, holes, fillets, assemblies and native STEP geometry. |
| Constraints & history | Pinned FreeCAD runtime | Actual sketch-solver diagnostics and explicit supported feature rebuilds. |
| Isolation | Windows AppContainer + Job Objects; Linux namespaces/bubblewrap | A restricted filesystem and network boundary for generated Python; AST policy checks add another layer. |
| Numerical arrays | NumPy, SciPy | Sampling, matrix operations, sparse solves and numerical diagnostics. |
| Implicit geometry | scikit-image, trimesh, Manifold3D | Sampled isosurfaces, mesh inspection and bounded mesh operations. |
| Finite elements | Gmsh, scikit-fem, meshio | Tetrahedral meshing, supported finite-element formulations and result exchange. |
| Local service | FastAPI, Uvicorn | Loopback viewer delivery, model requests and job/result transport. |
| Interactive display | JavaScript, Three.js | Orbit, sectioning, native-reference selection, component controls and result fields. |
| Reports & exchange | python-pptx, ReportLab, ezdxf, LibreDWG, OpenUSD | Review decks, documents and supported drawing/scene formats. |
| Repeatable installation | uv, locked dependencies, checksum-pinned downloads | Consistent environments and explicit runtime versions. |
| Regression evidence | pytest, JavaScript tests, Playwright Chromium | Backend checks, interaction contracts, browser behavior and export inspection. |
Optional PicoGK adds a pinned voxel-based TPMS path through its Linux runtime and .NET. Its output is a mesh approximation with voxel-resolution evidence. It does not create an exact smooth STEP surface.
Commands ChatGPT uses on your behalf
Users can describe the outcome in ordinary language. The assistant selects the relevant tool; there is no need to paste backend commands into the chat. The installed catalog exposes 65 MCP tools in version 0.19.0.
| Task | Representative tool calls |
|---|---|
| Check readiness and recover a project | status, list_models, get_model |
| Create or change CAD | build_model, update_parameters, import_cad |
| Preserve design intent | solve_sketch, edit_feature_tree, set_design_requirements |
| Measure and check | measure_model, validate_model, verify_design, audit_model |
| Try an alternative | preview_parameters, parameter_configuration, apply_configuration |
| Inspect and share | snapshot_model, export_model, create_presentation |
| Run a supported study | configure_simulation, submit_engineering_job, run_virtual_analysis |
How the Auditor and V&V improve confidence
Accuracy begins with the right requirements and a valid representation. Auditing detects invalid geometry and broken exports. Design verification checks supported requirements against measured geometry. Validation asks whether the geometry, assumptions and study represent the real intended use. These are related, but passing one does not establish the others.
1. Check the geometric object
For native CAD, the audit examines B-rep validity, finite positive volumes, dimensions and tessellation. For sampled meshes, it checks finite coordinates, watertightness, winding and positive volume. Bounded kernel healing or orientation corrections must preserve counts, bounds, volume and area within strict invariants; larger changes require revising the model.
2. Check the files you actually receive
Export checks reopen STEP geometry and inspect preservation of part identity, dimensions and volume. GLB structure and 3MF integrity are checked too. A beautiful viewport cannot compensate for an export that drops a part or changes the envelope.
3. Check against design intent
Saved requirements can test supported bounds, placements, counts, hole patterns, clearances and sampled wall-thickness locations. Native geometry supplies the evidence. “Six holes” must mean six holes at the requested centers and diameters, not merely six items with convincing names. Finite thickness samples do not certify a global minimum wall thickness.
4. Keep status honest
The stated supported check met its criterion.
The measured result violated a criterion; a known failed design requirement blocks that proposal.
The criterion is missing, unsupported, incompletely sampled or lacks sufficient evidence.
Review opens the measured envelope, component count and audit context. Its AI checks and alternative ideas are read-only requests. Suggestions become geometry only through a subsequent requested edit. Human visual review and suitable external engineering validation remain necessary.
Simulation has its own evidence chain
Mechanical Analysis supports bounded 3D steady conduction, small-strain linear elasticity and creeping-flow Stokes problems. A study needs the actual solid, material, selected boundaries, units and physical conditions. Geometry is audited before solving; result audits inspect finite fields, residuals, conservation, refinement and supported regimes before a report is published.
An unrefined solution remains unverified. A failed numerical check is not a successful solve. Display deformation is a visualization scale; it does not change the CAD. Virtual Analysis provides kinematic motion previews, not gravity, collision, tire traction or suspension-contact dynamics.
Reliable changes leave a trail
Stable part names, guarded revisions and artifact-bound face/edge references reduce accidental edits to the wrong geometry. Results carry their source identity. History previews are read-only; restoring is an explicit action. Parameter previews rebuild in scratch space, so exploring an idea need not overwrite the accepted model.
Intact does not claim universal CAD generation, whole-assembly contact, turbulent CFD, nonlinear mechanics or certification. Open-source engines make the computation inspectable; requirements, regression tests and measured evidence make its limits visible.
Explore further
Follow the ChatGPT tutorial, read the engineering guides, or set up the plugin.
Engine references: build123d · OpenCASCADE · FreeCAD · Gmsh · scikit-fem · Three.js. Dependencies retain their respective licenses.
Install once.
Design through conversation.
Download Intact v0.20.0 for Windows. Install privately in Codex with your own account; CAD runs on your computer.
Follow the installation procedure →