curiosity

Comparison · App and agent builders

Curiosity and Microsoft Foundry
A workbench, or a layer to build on

Curiosity builds tools on your connected records; Microsoft Foundry is Azure’s workbench for building agents.

Their deployment Azure Their data model Agents on models and Azure services 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.

Microsoft Foundry

Microsoft’s platform on Azure, formerly Azure AI Foundry, for developers to build, evaluate and run AI agents and applications, with a large model catalog, Foundry Agent Service and Azure AI Search. It suits engineering teams building on Azure.

How Curiosity compares

Where the boundary falls

Foundry gives a development team the models and services to assemble an agent. Studio starts with the part they would assemble: records already connected, typed and filtered by permission, so a tool is grounded before anyone writes the retrieval.

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.

QuestionCuriosityMicrosoft Foundry

Deployment

Cloud or self-hosted, ready to use

Azure

Data model

Managed context layer and knowledge graph

Agents on models and Azure services

Industrial fit

Built for industrial and enterprise teams

Developers on Azure

Data reach

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

Azure services and connectors

Residency

EU hosted, or entirely your own infrastructure

Azure regions

Customization

What your team can change

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

QuestionCuriosityMicrosoft Foundry

Your own code

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

Hosted agents in Python or C# containers

Your own interface

Your own front end in C#, deployed from git

No app builder, publish agents to Teams, Copilot

Data model

Typed node and edge schemas you define

Not available

Configuration as code

Every change committed to git, pushed to your remote

azd projects in azure.yaml, immutable agent versions

APIs and SDKs

REST API, C# and Python library, connector SDK

REST API, Python, C#, JavaScript, Java SDKs

AI integration

What AI can build and reach

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

QuestionCuriosityMicrosoft Foundry

AI that builds

Sudo drafts endpoints, tools, schemas and screens

Foundry Skill lets coding agents scaffold, deploy agents

Review before it applies

Every change a diff a person approves, in a sandbox

Coding agent plans, you approve changes and commands

Model choice

Any major provider, or an OpenAI compatible endpoint

10,000+ catalog models: OpenAI, Anthropic, Meta, others

Models on your servers

Open weights on your servers, or air gapped

Foundry Local on Azure Local, disconnected, preview

Assistant permissions

Built in tools search as the user, per record

Per user OAuth passthrough or OBO, or agent identity

Agent protocols

MCP server and an OpenAI compatible API

MCP tools and server, A2A, OpenAI compatible Responses

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