Comparison · Enterprise search
Curiosity and Squirro
Same building blocks, different estate
Curiosity models industrial records; Squirro brings enterprise search and AI to financial services.
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.
Squirro
A Zurich company’s enterprise AI platform combining search, retrieval and a knowledge graph, strongest in banking, insurance and the public sector, deployable in the cloud, a private cloud or on premises.
How Curiosity compares
Where the boundary falls
Squirro and Curiosity both combine search, a graph and AI, and both run where the data lives. Curiosity is built for industrial records: part data, revisions, maintenance logs and the engineering systems they live in.
A context graph, not document search
Document retrieval ranks files. Curiosity models the entities and relationships in your data, so what a model reasons over is the connected structure.
Structured records, not just text
Industrial knowledge lives in part data, revisions and serial numbers as much as in documents. Flattening it to text discards the part that matters.
Your infrastructure, your model
Runs where your data lives, with the language model you choose rather than a bundled one.
Side by side
Feature comparison
The same five questions, answered for both.
Deployment
Cloud or self-hosted, ready to use
Cloud, private cloud or on premises
Data model
Managed context layer and knowledge graph
Search and knowledge graph
Industrial fit
Built for industrial and enterprise teams
Financial services, public sector
Data reach
70+ systems connected, and yours through a connector you write
Enterprise content sources
Residency
EU hosted, or entirely your own infrastructure
Configurable
Customization
What your team can change
Your own code, interface, data model and configuration. Squirro as its own documentation described it in October 2026. Where it says Not available, the vendor documents no such capability.
Your own code
C# endpoints, AI tools and tasks, compiled in Studio
Python pipelets, loader plugins and agent tools on server
Your own interface
Your own front end in C#, deployed from git
Dashboard editor, widgets, Neo React bundles
Data model
Typed node and edge schemas you define
Item labels as keywords, knowledge graph endpoints
Configuration as code
Every change committed to git, pushed to your remote
Agent config as typed YAML files, CLI deploy
APIs and SDKs
REST API, C# and Python library, connector SDK
REST API, Python SquirroClient, JavaScript SDK
AI integration
What AI can build and reach
Whether AI can build on it, who reviews the result, and which models it runs. Squirro as its own documentation described it in October 2026.
AI that builds
Sudo drafts endpoints, tools, schemas and screens
Not available
Review before it applies
Every change a diff a person approves, in a sandbox
Not available
Model choice
Any major provider, or an OpenAI compatible endpoint
Any OpenAI compatible model with tool calling
Models on your servers
Open weights on your servers, or air gapped
On premises OpenAI compatible models, for example vLLM
Assistant permissions
Built in tools search as the user, per record
Agents and scheduled tasks act as the user
Agent protocols
MCP server and an OpenAI compatible API
MCP client for agents, no server documented
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
Enterprise search
Other comparisons in this group
Your data. Your infrastructure.