AI Tinkerers - San Francisco - November 2024 Meetup - Securing Agentic Systems
AI Tinkerers is back in San Francisco on November 21st, 2024!

Join us for the AI Tinkerers San Francisco November Meetup, hosted and sponsored by Okta at their office in SF.
As a reminder to the community, AI Tinkerers is not a pitch forum or a demo day. There are plenty of other meetups well suited to that. AI Tinkerers is akin to the Homebrew Computer Club of today’s technology. We want your messy side projects, works-in-progress, and experiments that are on the cutting edge.
One theme that has emerged recently is Agentic systems. One of the big unanswered questions in Agentic systems is how are we going to secure these systems?
Join us at November’s AI Tinkerers - SF monthly meetup where we’ll be diving deep into the messy reality of securing agentic AI systems. As our autonomous agents grow more capable of acting independently, making decisions, and interacting with real-world systems, we face unprecedented security challenges. How do we prevent a rogue agent from escalating its own permissions? What happens when collaborative agents start sharing capabilities without human oversight? Some people say that since OAuth was designed for humans and AIs behave like humans, we’ll be okay. Others disagree. What happens when an agent needs to delegate temporary permissions to another agent? How do we handle permission scope expansion as agents learn new capabilities? These are the thorny questions we need to tackle.
Bring your experimental authentication protocols, your half-baked security frameworks, and your wildest ideas about agent-to-agent trust mechanisms, your examples of current generation agent framework security exploits and more. Whether you’re building something that works (sort of) or have spectacularly failed at solving these challenges, we want to see it.

🥽 What is AI Tinkerers?
AI Tinkerers is a meetup designed exclusively for practitioners who possess technical, machine learning, and entrepreneurial backgrounds and are actively building and working with foundation models, such as large language models (LLMs) and generative AI. If you’re deeply passionate about creating LLM-enabled applications, have hands-on experience in building such systems, and are eager to connect with like-minded individuals who share your level of commitment, then this group is the perfect fit for you.
🌍 Who is this for?
👉 It’s AI Tinkerers, not AI enthusiasts. We screen attendance to active builders with a shared level of expertise in order to create a collaborative environment ideal for early-stage discovery and innovation. Prior attendee stats: This elite community of 7,317 technical professionals features a powerful distribution of skills: 48% specialize in agentic systems and multi-agent orchestration, 42% in advanced model engineering and PyTorch, and 38% in high-performance AI infrastructure and MLOps. Distinguished by a high density of venture-backed founders and researchers from top-tier labs like Google DeepMind and Meta, members actively collaborate on cutting-edge Model Context Protocol implementations and verifiable AI governance.
🎙️ DEMO SIGNUPS 🎙️
We’re on the lookout for speakers! Want to showcase your latest AI project or share your findings?
Demos are capped at 5 minutes. No pitches! We’re eager to see your raw and exciting WIPs! 🛠️
Best code walk-through / demo of the night will win a pair of Meta Raybans. No pitches!

🕕 Tentative Schedule:
- 5:00 PM: Doors Open
- 6:00 PM - 7:00 PM: Community Code Walk-Throughs and Demos
- 7:00 PM - 8:00 PM: Networking
- 8:00 PM: Doors Close
🥽 Speakers
Okta Ventures: Supporting Builders
Austin Arensberg
Head @ okta ventures
Bismuth Agent Context Selection
Ian Butler
AI Researcher @ XBOW
Principle Engineer
Jim Clark
principle engineer @ Docker
Squire.ai: Agentic Code Review
Karl Clement
CIO @ Squire AI
Revo.pm: Securing Agent Knowledge
Mehdi Djabri
CEO @ Revo.pm
Secure Agents: Stripe/Coinbase Payments
Dexter Horthy
CEO @ HumanLayer
Dendrite: Agent-Accessible Websites
Charles Maddock
CEO @ Dendrite Systems Inc.
Agentication: Session APIs to OAuth
Josh Mayer
founding team @ tollbit
Paige: AI Frontend Automation
Raghav Pillai
Co-Founder @ Speck
AWS Nitro: Secure AI Inference
Tanya Verma
Co-Founder @ Tinfoil
🤖 Connect, Collaborate, and Create 🤖
This meetup is your chance to:
- Showcase your latest AI projects: Share your work with the community during our demo session. Submit your proposal for a 5-minute presentation and inspire others with your innovative ideas.
- We are encouraging the community to share demonstrations related to securing agentic systems (including exploits or emerging approaches and frameworks that can play a role in this.)
- Network with fellow tinkerers: Meet and collaborate with other active builders, AI engineers, entrepreneurs, and researchers who share your passion for building the future with AI.
- Learn from industry experts: Gain insights and inspiration from our sponsors and other leading figures in the AI space.
🍕 Sponsors
This event is generously sponsored by Okta Ventures.
Okta Ventures - Okta Ventures invests in and supports cutting-edge companies advancing the future of secure digital interactions, with a focus on AI, identity, and security innovation. Beyond capital, they offer portfolio companies strategic access to Okta’s extensive APIs, engineering expertise, and network of 15,000+ customers, making them an ideal partner for startups building the next generation of secure autonomous systems. Their track record of backing transformative technologies in identity verification, security automation, and distributed trust frameworks demonstrates their commitment to shaping the future of secure AI systems.

RSVP Today!
Space is limited, so don’t miss out on this incredible opportunity to connect with the Bay Area AI community. RSVP now.









