Riven Chat

The conversational workspace. Cited answers grounded in live web search, file uploads, branching threads, artifacts, plugins, and per-conversation reasoning control.

Service

surfaces_chat

URL

rivenai.io/chat

Chat is the front door to the platform. Ask a question and get an answer grounded in live sources with citations you can check. Behind the ask box is a full reasoning workspace rather than a single text box.

Cited answers from the live web#

When a question needs current information, Chat searches as part of answering and cites inline. Retrieval runs through Riven Grounding over the Web Index, so citations point at documents the platform actually fetched rather than at model recall.

Pick a model, and how hard it thinks#

The picker switches models mid-conversation, and reasoning effort is tunable per thread — lighter for lookups, deeper for hard problems. Which models you see depends on your plan; the full roster with tier gating is in Models & usage.

Uploads, branching, artifacts#

• Uploads — attach documents and images in the composer; they join the thread context and carry through follow-ups.
• Branching — fork any turn to explore a second direction (different framing, model, or reasoning depth) without losing the original.
• Artifacts — when a thread produces a document, plan, or file, it opens beside the conversation with inline editing and change tracking.
• Plugins and tools — first-party and open tool integrations let the assistant act, not just answer. Tool surface comes from Riven Cortex.
• Memory — durable facts you share persist across threads via the Memory Bridge.

Chat or the API?#