Features
Governed AI agent builder from approved sources
Source-cited answers with document, section, and version
Named-owner checkpoints before sensitive actions
Audit trail on every retrieval, draft, and approval
Multi-channel deployment: web chat, Slack, Discord, GitHub, email
Workflow builder with template library
Bring your own LLM (Claude, OpenAI, Azure, AWS Bedrock, GCP Vertex, self-hosted) (Enterprise)
Tenant-isolated retrieval and storage (Enterprise)
Self-hosted deployment option (Enterprise)
SOC 2 Type II, HIPAA, Swiss FADP, GDPR compliance
Reciprocal-rank-fusion retrieval (BM25 + dense vector)
Coverage-gated pass rate for retrieval KPI
Entity schema configuration per customer
Atlas memory layer: vector retrieval, entity graph, compiled-truth wiki
Live-verified retrieval with coverage gating
Connect to 715+ MCP servers
Built-in OAuth authentication and automatic token refresh
One-click add to toolbox for MCP servers
Credential and session management (stateless for you)
OrgX coordination infrastructure (task delegation, decision workflows, cross-session memory)
Flamecast persistent assistant for Telegram and Slack
CLI and REST API for programmatic access
Publish custom MCP servers to marketplace
Usage statistics and server popularity metrics
Agent News for verified AI agent news with citations
OneSignal push notifications, email, SMS
Tavily optimized web search
Context7 version-specific documentation fetching
