Skip to main content
Back to News & Events
· Webinar

Free Zoom | AI-Native Agent Security & Compliance #3: Least Privilege on Real Products (Guest Zachry · Jev)

Forwarded by NACUAA Northern California Chapter.

主办单位：北卡浙大校友会、北美高校联盟AI创业公益俱乐部

Free Zoom | AI-Native Agent Security & Compliance #3: Least Privilege on Real Products (Guest Zachry · Jev)

Free. Zoom. 60 minutes including a break.

Lecture 3 of 5 in AI-Native Agent Security & Compliance.
Lecture 1: risk moves from bad text to bad actions.
Lecture 2: walls live in the harness, sandbox, and human-in-the-loop.
Lecture 3: least privilege on real products. Before each tool call, the system must make a bounded decision: allow, deny, or escalate.

Formula: Agent = Model + Harness + Tools + Permissions + Data. This session focuses on Permissions.

Guest Zachry Xiong, 15 minutes on Jev (TypeSafe AI, Sep 2026): state plus typed questions in; choice, score, or yes/no with probabilities out. Use it as a tool gate. It does not replace a sandbox or human review. Type safety is not correctness. Confidence is not authorization.

官方报名入口

🎟️ RSVP & Direct Zoom Access

公益免费

Location: Zoom Online Webinar. Guests are invited to register on Luma to add to calendar and receive event reminders.

Watch Recording (YouTube) Download Slides Luma Page
Direct Zoom Credentials
会议号：917 5338 1992
密码：18970521

📅 Date & Time (When)

Saturday 3 October 2026, 5:30–6:30 PM PDT

  • • PDT: Sat 3 Oct 2026, 5:30–6:30 PM
  • • EDT: Sat 3 Oct 2026, 8:30–9:30 PM
  • • Beijing: Sun 4 Oct 2026, 8:30–9:30 AM

⏱️ Agenda

5:30–5:48 Least privilege in four questions: who, which tool, which resource, default deny
5:50–6:05 Guest Zachry: Jev as a tool gate
6:05–6:10 Break (5 minutes)
6:10–6:25 Write the decision into the permission map and the log; send/delete/pay still requires human confirmation
6:25–6:30 Q&A and Discussion

📝 Assignment

Pick an agent you currently use and list three tools. For each, specify: who can call it, its target scope/resource, and how it stops on failure. Flag high-risk actions with "typed gate + human review" or "not yet implemented".

Lecture Materials & Recording (Dual Mirror Channels)

PDF Format · Free Download

Lecture 3 Full Event Recording (YouTube)

Complete 60-minute session: Least Privilege on Real Products & Decision Model Jev Tool Gating

Watch Video

Lecture 3 Core Slides 1: Least Privilege for AI Agents

AI-native agent security and compliance lecture notes: Least privilege architecture on real products

Local Download zjuaanc.org Mirror

Lecture 3 Core Slides 2: AI Agent Least Privilege

AI Agent Least Privilege: Decision Model Jev, Tool Gating & Permissions

Local Download zjuaanc.org Mirror

🗺️ Series Roadmap

  • • Session 1 Sep 5: From Bad Text to Bad Actions: Where Agent Risk Begins
  • • Session 2 Sep 19: Harness, Sandbox, and Human-in-the-Loop
  • • Session 3 Oct 3: Least Privilege on Real Products (Current Session)
  • • Session 4 Oct 17: Cross-Border Compliance: US, China, and EU
  • • Session 5 Oct 31: Production Checklist Workshop
Speaker: Michael Huo ｜ Guest: Zachry Xiong

📚 Past Recordings & Resources

Free community webinar. Never asks for payments or verification codes. Does not teach offensive exploits.
🤝 Organizers & Partners

Organizers: Zhejiang University Alumni Association of North Carolina (ZJUAANC), NACUAA AI Venture & Impact Club

Organized by: VI AI Foundation, VI AI For Good Foundation, AI Agent Alliance

Co-organized by: NACUAA NC, SC, SV, NorCal, DC, WA Chapters; ZJU Alumni Associations of TN, Philadelphia, RI, FL

Synergy: ZJU Agents

📰 媒体支持

North Alpha Post