RAG, chat, workflows, Claude Code, and Codex in one workspace

Confluye

A workspace where teams upload knowledge, ask Confluye Command, build agent workflows, and run local coding agents with full execution context.

Enter workspace Explore the demo

See RAG, chat, and nodes working together

Interactive product sections

Switch between the systems users actually operate.

The experience mirrors the product surface instead of a generic marketing carousel: each tab changes the prompt, evidence, metrics, and workflow path.

Managed knowledge

Documents become searchable context without user model setup.

Upload PDFs, docs, spreadsheets, or notes. Confluye indexes them with provider-managed embeddings, tracks reindex state, and exposes cited context to chat and workflows.

248 docsIndexed

LiveReindex

3 citedSources

Indexing and retrieving context

Which onboarding risk is highest in the uploaded Q3 support brief?

The highest risk is stalled enterprise onboarding: the support brief ties it to missing SSO docs, delayed security review, and repeated launch-date slips.

Q3 support brief.pdfSecurity checklist.docxLaunch notes table

1Upload docsPDF, Sheets, Drive

2Chunk + embedtext-embedding-3-small

3Answer with evidenceCitations in chat

What Confluye replaces

One operational layer for docs, chat, workflows, and runs.

Knowledge-native context

Knowledge bases, documents, and tables stay addressable from chat and workflow nodes.

Agent workflow canvas

Codex, Claude Code, MCP tools, conditions, webhooks, and approvals run as connected steps.

Provider-managed AI

Embedding infrastructure is invisible to customers while BYOK remains available for chat models.

Build directly on your agent runtime

Claude Code, Codex, MCP tools, RAG retrieval, approvals, and logs can share one graph.

Start in Confluye