SUPERWISE v1.27: self-service Starter tier and full guardrails
Review the SUPERWISE Starter tier announcement, including built-in guardrails and Remote MCP support for deploying and governing AI agents.
What's in this video
- This December 2025 release video introduces SUPERWISE v1.27.
- It presents the self-service Starter tier available at that time.
- The walkthrough also covers built-in guardrails and Remote MCP support.
Frequently asked questions
Topics from this video and why governed AI matters.
- What is the Starter edition?
- The Starter edition is free with limited resources. You provide basic details and are ready to go. It includes runtime guardrails, real-time observability, and community support so you can govern AI without a credit card.
- How do guardrails work in SUPERWISE?
- SUPERWISE guardrails are designed for using public models safely. They are rule-based policies that combine one or more rules to keep LLM outputs safe and accurate. You define them independently from agents, manage version history, and use a playground to test under different inputs and outputs before publishing. You can block when a rule is violated or let it through and audit it, with visibility into usage. See docs.superwise.ai/docs/guardrails-1.
- What is MCP integration in SUPERWISE?
- MCP (Model Context Protocol) is the standard for exposing agent capabilities. SUPERWISE supports remote MCP with configurable header parameters for authentication so you can connect and govern MCP-based agents in one place.
- Why does governed AI need a guardrail playground?
- A playground lets you test how rules apply to different values before going live. Governed AI requires that you verify behavior in advance and revisit published versions. SUPERWISE gives you that control so violations are caught during design.
- Does SUPERWISE support private or open-source models for PII and PHI?
- Yes. SUPERWISE guardrails are designed for using public models safely. SUPERWISE also supports privately hosted and open-source models so customers can build sophisticated AI solutions that handle PII and PHI while keeping data in their control.





