curiosity

Comparison · App and agent builders

Curiosity and Salesforce Agentforce
The customer record, or the engineering record

Curiosity builds agents on industrial records; Agentforce builds agents on customer data.

Their deployment Salesforce cloud Their data model Agents on CRM and Data 360 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.

Salesforce Agentforce

Salesforce’s platform for AI agents in sales, service and marketing, grounded in CRM records and Data 360. It runs on Salesforce’s cloud and suits organizations whose customer processes live in Salesforce.

How Curiosity compares

Where the boundary falls

If the agent’s work is the customer relationship, Agentforce sits where that data is. Industrial questions reach past the CRM into part data, maintenance logs and supplier notices, which is the graph Studio builds on.

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.

QuestionCuriositySalesforce Agentforce

Deployment

Cloud or self-hosted, ready to use

Salesforce cloud

Data model

Managed context layer and knowledge graph

Agents on CRM and Data 360

Industrial fit

Built for industrial and enterprise teams

Sales, service and marketing

Data reach

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

Salesforce and Data 360 sources

Residency

EU hosted, or entirely your own infrastructure

Salesforce regions

Customization

What your team can change

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

QuestionCuriositySalesforce Agentforce

Your own code

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

Apex and Lightning Web Components, run in Salesforce

Your own interface

Your own front end in C#, deployed from git

Lightning App Builder and custom LWC components

Data model

Typed node and edge schemas you define

Custom objects, fields and relationships

Configuration as code

Every change committed to git, pushed to your remote

Salesforce DX source, DevOps Center with GitHub

APIs and SDKs

REST API, C# and Python library, connector SDK

REST, SOAP and Bulk APIs, Salesforce CLI

AI integration

What AI can build and reach

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

QuestionCuriositySalesforce Agentforce

AI that builds

Sudo drafts endpoints, tools, schemas and screens

Agentforce Vibes generates Apex and LWC from prompts

Review before it applies

Every change a diff a person approves, in a sandbox

Plan Mode approval and inline diff review

Model choice

Any major provider, or an OpenAI compatible endpoint

OpenAI and Anthropic models, BYOLLM via Einstein Studio

Models on your servers

Open weights on your servers, or air gapped

Your own endpoint via LLM Open Connector

Assistant permissions

Built in tools search as the user, per record

Employee agents use the user's permissions

Agent protocols

MCP server and an OpenAI compatible API

Hosted MCP servers, agents callable through MCP

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