Features
No-code agent builder with branching logic and conditional steps
Multi-model routing across Anthropic, OpenAI, Google, and open-source models
Organizational Memory (OM1/OM2) for persistent, permission-aware context
Customer Intelligence dashboard with AI health scores and churn detection
Meeting Intelligence with real-time action item detection and coaching insights
50+ native integrations (read/write) with Slack, Salesforce, Jira, Gmail, Zoom, BigQuery, Snowflake
Command Center for approvals, monitoring, evals, and optimization
Cloud sandbox for code execution and artifact generation
Multi-file code editing with repo-aware context
Automated polling triggers (every 12h/4h/1h) for long-running agents
Human-in-the-loop approval gates with progressive autonomy
MCP-compatible server for use with Claude Code, Cursor, and other MCP clients
Webhook triggers for custom event-based agent activation
Enterprise SSO (SAML 2.0/OIDC), SCIM, and role-based access control
SOC 2 Type II and GDPR compliance
Laguna XS.2 model (33B params, 3B active, on-device)
Laguna M.1 model (225B params, 23B active, via API)
256K context length for multi-step reasoning
Multi-agent orchestration with planning and tool use
Sandboxed agent execution environments
Developer surfaces: agents, TUI, IDE extensions, binaries
Custom foundation models deployed on-prem or in VPC
Data connectors to repos, databases, data warehouses
Role-based access control for humans and agents
Executive-grade governance and auditability
On-prem, VPC, and workstation deployment (defense only)
Forward Deployed Research Engineers embed with teams
Real-time observability with end-to-end traces
Air-gapped network support
Open-weight model weights available
