Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Securing Agents' Network Layer
This talk demonstrates practical methods for implementing network access controls for agents, moving from basic to more secure solutions to mitigate data exposure risks.
I’ll be presenting hands-on approaches to implementing network access controls for agents, specifically Claude Code. I’ll start with a simple built-in solution, show why that’s insufficient, and work up to a more secure solution.
LLM agents combining private data, untrusted input, and exfiltration risk prompt injection.
- Claude CodeAnthropic's agentic coding tool: Unleash Claude's raw power directly in your terminal or IDE to turn complex, hours-long workflows into a single command.Claude Code is Anthropic’s powerful agentic coding assistant, designed for high-velocity development. It operates natively within your terminal, IDE (VS Code, JetBrains), or via a web interface, allowing you to delegate complex tasks like feature building, bug fixing, and codebase navigation. The agent plans, edits files, executes commands, and creates commits, maintaining awareness of your entire project structure. Internally, Anthropic engineers using Claude Code reported a 67% increase in productivity, demonstrating its capacity to deliver significant gains for Pro and Max plan users.
- LinuxThe dominant open-source, Unix-like operating system kernel (created by Linus Torvalds in 1991), powering 90% of the public cloud, all top 500 supercomputers, and the Android platform.Linux is the robust, open-source, Unix-like operating system kernel, first released by Linus Torvalds in 1991. It serves as the core for countless distributions (e.g., Ubuntu, Fedora, Debian) and is the backbone of modern infrastructure. Specifically, Linux runs over 90% of the public cloud workload, powers all of the world's top 500 supercomputers, and is the foundation for the Android mobile OS (with over 3 billion active devices). Its stability, security, and free licensing model (GPL) drive widespread adoption across servers, embedded systems, and developer desktops globally: it is the industry standard.
- bashBash (Bourne-Again SHell): The ubiquitous command language interpreter and scripting engine for GNU/Linux and macOS systems.Bash is the GNU Project's powerful shell, serving as the default command interpreter for most Linux distributions and a widely used option on macOS. Developed by Brian Fox in 1989, its name is an acronym for 'Bourne-Again SHell,' signifying its compatibility with the original Bourne Shell (sh) while incorporating advanced features from shells like ksh and csh. The technology provides a robust environment for interactive command execution and non-interactive shell scripting, supporting critical functions like command-line editing, job control, and complex programming constructs (loops, conditionals, functions) for system automation.
- KubernetesKubernetes (K8s): Production-grade container orchestration: automate deployment, scaling, and management across your cluster.Kubernetes (K8s) is your control plane for planet-scale container orchestration: it automates the deployment, scaling, and management of containerized applications across your cluster. Built on 15 years of Google's production experience (Borg), K8s ensures your *desired state* is always maintained. Core resources like Pods, Deployments, and Services manage auto-scaling, load balancing, and self-healing for you. You interact directly with the API server using `kubectl` (the command-line tool) to execute zero-downtime rollouts and rapid rollbacks. As a CNCF project, it provides vendor-neutral flexibility for any infrastructure: cloud, on-premises, or hybrid.
- Google Cloud PlatformGCP delivers Google's global infrastructure (Compute Engine, BigQuery) for secure, scalable cloud solutions and AI/ML innovation.Google Cloud Platform (GCP) provides the core infrastructure and services for modern digital transformation. The platform leverages Google's global network, spanning 39 regions and 118 zones, to host critical workloads securely. Key services include Compute Engine (IaaS), Google Kubernetes Engine (GKE) for container orchestration, and BigQuery (serverless data warehouse) for petabyte-scale analytics. GCP integrates advanced AI/ML capabilities via Vertex AI, allowing developers to build and deploy models fast. Security is paramount: the platform uses Google's multi-layered security model, protecting data and applications with zero-trust principles. New customers can utilize the free tier and $300 in credits to deploy their next project.
Related projects
Securing Autonomous Agents: A Look Under The Hood Revo.pm
San Francisco
Explore experimental methods to prevent autonomous agents from leaking private data, covering prompt-time boundaries, token-level filtering, and knowledge…
Using HumanLayer to give agents safe access to high-stakes tools
San Francisco
Learn how to safely give AI agents access to powerful tools like sending emails or running SQL queries,…
Claudio: repo as agent
San Francisco
Explore Claudio, an experiment demonstrating persistent, self-improving agents created via forking and deploying processes onto VMs using cloud…
Given agents safe access to high-stakes tools with HumanLayer
Chicago
Learn how to give AI agents safe access to high-stakes tools using human approval workflows. Explore Python metaprogramming…
From Error to Agent: Automating Sentry Issue Triaging
San Francisco
See a demo automating Sentry error triaging into GitHub PRs using AI agents, turning runtime issues into actionable,…
Agentication: Turning Session Based APIs Into OAuth APIs Programatically
San Francisco
Learn how "Agentication" programmatically turns session-based APIs into OAuth APIs, enabling secure agentic access to services like LinkedIn…