Features
Centralize engineering playbook with versioning
Distribute playbook artifacts to any AI agent (Copilot, Cursor, Claude, etc.)
Pre-commit rule violation detection and automatic rewrite
MCP server support for agent context injection
Drift detection and repair to maintain alignment
RBAC for playbook authorship and distribution
Audit trail for all technical decisions
Self-hosted deployment with air-gap support
Scales across monorepos, microservices, and enterprise codebases
SonarQube integration for code quality reports
Introducing Skills for governing AI coding agent workflows (June 2026)
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
