nao audits its own usage and tells you exactly where your context is missing, wrong, or unclear - then opens the fix as a pull request in your context repo. Online evals for your analytics agent.
Schedule your analytics agent to run in the background. Recurring reports, conditional alerts, proactive monitoring, and a new Feed to track all agent activity.
Interactive charts and stories render directly inside your AI agent. Same nao UI, no tab switch. Works with Claude, Cursor, and any MCP-compatible tool.
SSO (Microsoft, Okta), row-level security, white-label UI, SOC 2 Type II, and hands-on implementation support. The production-grade layer for teams deploying at scale.
nao exposes itself as an MCP server. Run governed analytics from Claude, Cursor, Codex, or any MCP-compatible tool. Three modes: sub-agent, context-layer, and story.
Five open-source skills to set up your nao project, audit context quality, write rules, build test suites, and add a semantic layer.
The first open-source analytics agent builder. Built on context engineering - the practice of controlling what your agent sees so it produces reliable, governed answers.
