curiosity

Comparison · App and agent builders

Curiosity and Mendix
Model each application, or describe it

Curiosity builds tools on your connected records; Mendix is a low code platform for building applications.

Their deployment Cloud, private cloud or on premises Their data model Modeled application data Our deployment Cloud or your own servers Our residency EU, or your own

Your data · your environment

Who each tool is for

Different problems, honestly stated

Curiosity

For industrial and regulated teams whose knowledge sits in engineering systems and structured records, where the answer depends on how those records connect, and where the deployment has to run on their own infrastructure.

Mendix

A low code application platform owned by Siemens, used to build enterprise and industrial applications with visual modeling, deployable in the cloud, a private cloud or on premises. Teams model the data and logic of each application.

How Curiosity compares

Where the boundary falls

Mendix gives a development team full control over a long-lived application. Studio is for the many smaller tools that never make the backlog: describe it, and it is built on records that are already connected and permissioned.

Grounded, not guessed

A tool Studio builds runs on the graph, so every figure it shows traces back to a record in a source system.

Your permissions, inherited

A generated tool cannot show a user anything the source system would not already show them, down to the individual record.

From prompt to production

The tool ships to real users with an audit trail, not as a prototype someone has to rebuild before it goes live.

Runs on your infrastructure

On premises or in your private cloud, with the language model you choose.

Side by side

Feature comparison

The same five questions, answered for both.

QuestionCuriosityMendix

Deployment

Cloud or self-hosted, ready to use

Cloud, private cloud or on premises

Data model

Managed context layer and knowledge graph

Modeled application data

Industrial fit

Built for industrial and enterprise teams

Enterprise and industrial apps

Data reach

70+ systems connected, and yours through a connector you write

Connectors per application

Residency

EU hosted, or entirely your own infrastructure

Configurable

Customization

What your team can change

Your own code, interface, data model and configuration. Mendix as its own documentation described it in October 2026. Where it says Not available, the vendor documents no such capability.

QuestionCuriosityMendix

Your own code

C# endpoints, AI tools and tasks, compiled in Studio

Microflows, Java actions and JavaScript actions

Your own interface

Your own front end in C#, deployed from git

Page editor, pluggable React widgets, native mobile

Data model

Typed node and edge schemas you define

Domain model entities, attributes and associations

Configuration as code

Every change committed to git, pushed to your remote

Git based Team Server, commits and merges in Studio

APIs and SDKs

REST API, C# and Python library, connector SDK

Published REST and OData, Platform and Model SDKs

AI integration

What AI can build and reach

Whether AI can build on it, who reviews the result, and which models it runs. Mendix as its own documentation described it in October 2026.

QuestionCuriosityMendix

AI that builds

Sudo drafts endpoints, tools, schemas and screens

Maia Make generates domain models, pages, microflows

Review before it applies

Every change a diff a person approves, in a sandbox

Changes listed in Studio Pro, undo per document

Model choice

Any major provider, or an OpenAI compatible endpoint

Mendix Cloud GenAI, OpenAI, Foundry, Mistral, Gemini, Bedrock

Models on your servers

Open weights on your servers, or air gapped

Local open weights via Ollama and OpenAI connector

Assistant permissions

Built in tools search as the user, per record

MCP tools run as an authenticated app user

Agent protocols

MCP server and an OpenAI compatible API

MCP client and server modules, Studio Pro MCP server

At Airbus, we developed the next generation of customer support AI assistance tools with Curiosity, enhancing our technical support’s ability to access and navigate vast data from multiple sources, including millions of documents.

Services Innovation Team

Airline Services at Airbus

Your data. Your infrastructure.

Connected knowledge for AI systems