Author agents and skills — no code deploy.
Author agents and declarative skills in an admin console, teach the platform new skills interactively, and keep drafts as drafts until you publish.
Today, every change to what the AI can do usually means an engineering ticket and a release. The platform lets admins author agents and declarative skills — instruction body, allowed tools, required context, approval points, plan steps, and card types — as data in the console, run by one generic executor. New and updated behavior goes live with no code deploy, so the people who own a process can own its automation.
The admin console brings the moving parts together in one place: agents, skills, a live test chat, presentations, drafts, and settings, all gated by platform role. You can build a change, test it against a live agent, and govern it without leaving the console.
Teach mode lets you show the platform a new skill interactively. Captured agents, skills, and card templates land as drafts and stay drafts until you publish — so live agents never change silently, and nothing reaches your users before you say so.
What's included.
Permission, policy and audit on every tool call · ← Back to all features · Read the docs →
Explore the rest of the layer.
Analytics
A built-in GA4 conversion funnel across surfaces, with a hard PII blocklist that strips message content and credentials, plus opt-out.
The anchorGovernance & trust
Every side-effecting action flows through a single governance gate — permission ∩ policy ∩ approval ∩ audit — with no bypass, even across the language boundary.
Right, current, permitted dataContext engineering
Minimization, boundary enforcement, freshness detection, and output provenance so agents work on the right, current, permitted data and show their sources.
See governed agents in your own product.
Book a demo and we'll walk your team through the governance model, the two-seam integration, and a use case for your industry.