Platform

How SetMeld Composer and SetMeld Pipeline fit together

SetMeld Composer is the design environment where sources are connected, scanned and mapped. SetMeld Pipeline is the execution engine that carries those mappings out and keeps the knowledge graph current. An AI assistant works alongside your team at every stage.

Architecture

The same workflow, wherever it runs

Both deployment models share identical components and stages. The choice between them is driven by your security, compliance and operational requirements. Feature availability is identical.

YOUR ON-PREM / PRIVATE CLOUD NETWORKNo data leaves your network Source systemsDatabases · APIs · filesSetMeld ComposerReasons with your LLMSetMeld PipelineExtract · transform · resolveKnowledge graphUnified · governed · queryableConsumersBI · apps · agents · analysts
Every component, including SetMeld Composer, SetMeld Pipeline, the knowledge graph and the reasoning model, runs inside your own environment.
YOUR NETWORKSETMELD CLOUD Source systemsDatabases · APIs · filesSetMeld ComposerReasons with SetMeld’s LLMSetMeld PipelineExtract · transform · resolveKnowledge graphUnified · governed · queryableConsumersBI · apps · agents · analysts
Both components run in SetMeld Cloud; the authoritative unified graph is still loaded back into your own network.
Compare deployment models in detail
The workflow

Four stages, one guided session

1

Connect

Credentials through a guided flow. SetMeld Composer scans each source and extracts an AI context describing every entity, field and datatype.

2

Generate schema

The AI pipeline designs the unifying ontology, the transformations, and the entity resolution rules, then shows you its work.

3

Sync

SetMeld Pipeline extracts, transforms, resolves entities across systems and loads the graph. Once, or continuously.

4

Query

Analysts, applications and agents query everything through one interface, with attribution back to source.

See it against your own systems.

The fastest way to understand SetMeld is to watch it scan two of your databases and propose a unified model.