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
No-code agent builder (Invent) with natural language description
Drag-and-drop multi-agent workflow canvas (Workforce)
Built-in agent evaluation and quality scoring (Evals)
Human-in-the-loop oversight with approval gates
Real-time monitoring dashboard with Timeline view
Role-based access controls (RBAC) and audit logs
PII masking and data residency controls
LLM-agnostic: supports Claude Sonnet, GPT-5.5, Claude Opus 4.7, Gemini 3.5 Flash
Gemini 3.5 Flash with 1M-token context and 64K-token output
100+ pre-built integrations including HubSpot, Gmail, Salesforce, Confluence, Notion
Agent escalation when confidence is low
Scheduling and triggers for automated execution
Confluence Knowledge Sync for auto-updating knowledge bases
MCP access for Member role
Version control and rollback for agents and tools
