SUPERWISE v1.25.0: AI agents, guardrails, and observability
Review SUPERWISE v1.25.0 features for multi-agent systems, including security controls and observability for monitoring AI agents.
What's in this video
- This November 2025 release video presents SUPERWISE v1.25.0.
- It covers multi-agent system features and security controls available in that release.
- The walkthrough shows observability for monitoring and managing AI agents.
Frequently asked questions
Topics from this video and why governed AI matters.
- What guardrails did SUPERWISE add in v1.25?
- Five new guardrails: competitor check (block discussion of named companies), correct language (allowed/disallowed languages), string check (reject expressions), jailbreak detection (prompt manipulation), and PII detection with dozens of categories including credit card, phone numbers, and identifiers.
- Why does agentic AI need jailbreak detection?
- Users can try to manipulate prompts to bypass guardrails. Jailbreak detection flags those attempts so you block or audit them. Governed AI requires that the platform defends the rules and the data.
- How does SUPERWISE support Flowise agents?
- SUPERWISE supports both chat-flow (single-agent) and agent-flow (multi-agent) Flowise builds. You register the implementation and get out-of-the-box dashboards, customized queries, and full guardrail coverage for each deployed agent.
- Why is PII detection critical for production agents?
- Agents that handle user input can leak names, emails, or payment data. Built-in PII detection in SUPERWISE stops that at the platform layer so every integration benefits without custom code.
Related Videos
Sentinel: AI systems your auditors already trust
Meet the SUPERWISE Sentinel AI gateway, which redacts sensitive data, applies guardrails, and reports what passed, changed, or was blocked.
demo
SUPERWISE® Council builds governed AI systems
See SUPERWISE Council turn plain-English requirements into an AI architecture, visual system map, versioned guardrails, tests, and deployment gates.
demo
How Claude builds SUPERWISE agents for you (MCP demo)
See Claude Code use SUPERWISE API and SDK documentation over MCP to build an agent, attach guardrails, and create working notebooks.
demo
Agentic System of Record POC: governance for enterprise AI agents
See a SUPERWISE Agentic System of Record proof of concept with dashboards for agent performance, cost, risk posture, and governance status.
demo
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.
update
How SUPERWISE stops patient data leaks
Watch SUPERWISE detect a patient's Social Security number and block the PII in real time, before it ever reaches the LLM.
vertical