The Proof Pack.

One real Mendix™ app, authored end-to-end by AI through mxto, and every layer of evidence behind that, downloadable and inspectable. Not stronger claims; the artifacts themselves.

1. The reproducible loop, on Claudius

Claudius is a complete IT-asset / request tracker (25 entities · 68 microflows · 9 modules · MX 11.6.4) built by an AI agent driving mxto, no Studio Pro in the loop. The whole loop is reproducible from the artifacts below:

extract the modelauthor a change with AIcommit to Team Servermxbuilddeploytestdiff: 0 unexpected
your-agent / mxto

Every line above is verbatim captured output (Claudius round-trip, 2026-06-08). The companion "AI adds working logic live" sequence (author → mxbuild 0-CE → behaviour appears, DB-confirmed) is captured on the Comotion app. See the method.

2. Why your AI can read it: the same flow, three ways

This is the core claim, made concrete on one real Claudius flow (ACT_ApproveRequest, all three files in the data pack). Your AI today gets the left column. With mxto it gets the right.

The raw model graph

2,592 tokens · ~29 resolutions
"startNodeId": "2693b9bf-cf9d-…"
"edges": [
 { "originNodeId": "f6167db7-…",
   "destinationNodeId": "11aabc75-…",
   "caseValue": "true" },
 … 8 more edges, each a
   pair of opaque IDs …
]
# no order, no names

mxto typed intermediate form

1,148 tokens · −55.7%
flow: ACT_ApproveRequest
params: [Request]
nodes:
  - guard: status in
      (Submitted, InReview)
  - change: Request.Status
      = Approved
  - commit: Request
  - call: CreateAuditEntry
# typed + ordered

mxto read-optimized flow

145 tokens · −94.4% · 0 resolutions
flow ApproveRequest(Request):
  if not Request.Status in
      (Submitted, InReview):
    show_warning(…); return
  Request.Status = Approved
  Request.Reviewer = CurrentUser
  commit(Request)
  call(CreateAuditEntry)
  close_page()

Measured with tiktoken o200k_base; resolution counts from the graph's own structure. Reproduce it + the full method: 04-comprehension-benchmark-method.txt. The three files ship in the data pack: ApproveRequest-model-graph.json, ApproveRequest.mir.txt, ApproveRequest.axon.

3. Download & inspect

The Claudius data pack

The Mendix project, the full model graph (our JSON), the readable flow + typed IR (shipped in the data pack), and mxto's own flow renders. Import it; rebuild it.

data-pack/README.txt →

Tools & capability map

~140 MCP tools by phase, the read/write coverage map, and what we don't cover yet.

02-tools-and-capability-map.txt →

Mendix versions tested

Auditable: the exact versions (7.23 → 11.6), 100% round-trip, 4/4 build-gated, and what's not yet witnessed.

01-mendix-versions-tested.txt →

System requirements

A Mendix PAT + Project ID, a Mac/Linux/CI box sized to your model, and your own AI subscription.

03-system-requirements.txt →

What mxto doesn't do yet

The honest boundaries: what needs a human, and "structurally safe ≠ semantically correct."

boundaries →

Security & enterprise readiness

Local processing, the AI-agent data boundary, credentials, auditability, SOC 2 (not certified, by design).

security →

Why not Mendix™ Maia?

How mxto and Mendix™ Maia fit together: the native IDE assistant alongside the external, headless delivery engine for estates, CI, and agents.

vs Maia →

4. Prove it on your own estate

The strongest proof is your app, not ours. Send us a sample module (or run mxto locally) and we produce a read-only round-trip report: what extracted, the construct coverage, and the zero-loss diff, against your own model. No Studio Pro, nothing leaves your machine without your say.

Request a read-only report →