security
136 talks
Your AI Isn't the Problem. Your Infrastructure Is.
Agents in Orbit: Workflows, Not Autopilot
Claude Managed Agents Q&A: Evals, CI/CD and Multi-Tenancy (Part 4 of 4)
The Next Trillion Internet Users Still Don't Have an Identity
Your Agent Is a Lethal Trifecta (And What to Do About It)
An AI Future Without the Lock-In
AI Agents Don't Read Your Policy Docs. They Hit Your APIs
Beyond RAG: A Relational Context Engine That Cuts Token Burn
The Lethal Trifecta Is Already on Your Laptops
Let Anyone at Your Company Ship Internal Apps with AI
AI Hackers Are Faster Than Your Pen Test
How AI Agents Pay: Checkout in ChatGPT and Google AI Mode
How Many Credentials Should Your AI Agent Have? Zero.
How I Learned to Stop Worrying and Love the Sandbox
AI Coding Agents Are Breaking Big Codebases
YOLO Mode, Safely: MicroVM Sandboxes for Any Agent
Your LLM App Returned 200 OK. It Was Still Wrong.
Opening Keynotes: Mistral, Langfuse & Sizzy
Connect AI to Billions of Legal Documents
Agents Without Code: Skills, YAML, and Filesystems Replaced Python
We let an AI agent execute Bash and lived to talk about it
Build-Time vs. Run-Time: Why Dev Tools Fail in Production
Tethered: Our Agents Are Us
Agent Spending Without Controls
Beyond the Lethal Trifecta: Agentic Commerce on the Open Internet
Teaching agents to pay
When AI Agents Pay and Sellers Monetize: Building x402 Apps on AWS
x402 Isn't Good (Yet)
Your Agent Just Authorized What?!
Which AI startups actually land enterprise contracts?
AI-Native Organisations Run on Skills: How to Structure and Scale Them
Give the Agent a Budget, Not a Token
IT Admin for the AI Workforce
Unlock Agent Autonomy: The Runtime for AI-Native Systems
Guardrails First: Engineering Member-Facing Health AI
Why Your Enterprise Tech Stack Isn't Ready for AI Agents
Security Firewall for Agents
Multiplayer agentic engineering
Open Source Is Dead. Long Live Open Source.
Gadgets: Personal app vibe coding that is actually safe
Teaching AI to Find Real Vulnerabilities
We Vetted 2,000 AI Skills Before They Reached Developers
Training Frontier Models to Out-Think Hackers
Notion's Token Town
Better Auth
Agentic Development Security
Agentic Security: Permissions, Provenance, and the Agent Supply Chain
In the Land of AI Agents, the Verifiers Are King
It's 10pm. Do You Know Where Your Agents Are?
Privacy-Preserving Intelligence
Security Track Intro
Skills are the New SDKs
Through the AI Fog: The Architectural Decision Agentic Security Depends On
We Gave an Agent Production Code Access and Then Tried to Sleep at Night
Your LLM Stack Is a 2008 Database With Better Marketing
You Didn't Ship a Bug. You Just Wrote It for a Human.
Software engineering is not about writing code
Using LLMs to Secure Source Code
From fork() to Fleet: Designing an Agent Sandbox Cloud
I've Never Seen Anything Scarier Than an LLM with Tool Calls
Stop Evaluating Models Like It's the 50s
remobi.app: Don't Change Your Terminal Workflow for Mobile
The Agentic Web and the Bazaar Era of AI
The AI bugpocalypse is here. Now what?
Claws Out: Securing and Building with OpenClaw
Your LLM Deception Monitor Is Broken. The Fix Is in the Training Data
Harness Engineering & Startup Battlefield
The Future Is Domain-Specific Agents
Why MCP and ChatGPT Apps Use Double Iframes
Why Eval++ Is the Next Great Compute Primitive
Building Interactive UIs in VS Code with MCP Apps
Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents
Beyond Components: Designing Generative UI for MCP Apps
What if the network was the sandbox?
Can LLMs Generate Enterprise Quality Code?
Spec-Driven Testing for Agents With A Brain the Size of A Planet
Lobster Trap: OpenClaw in Containers from Local to K8s and Back
Combine Skills and MCP to Close the Context Gap
Skill Issue: How We Used AI to Make Agents Actually Good at Supabase
Context Is the New Code
LLM codegen fails and how to stop 'em
One Login to Rule Them All: Cross-App Access for MCP
Gateways are All You Need
Scaling GitHub for your Agents
MCP = Mega Context Problem
The New Application Layer
Code Mode: Let the Code do the Talking
State of the Claw
$1 AI Guardrails: The Unreasonable Effectiveness of Finetuned ModernBERTs
AIE Europe Keynotes & OpenClaw
Cognitive Exhaust Fumes, or: Read-Only AI Is Underrated
Why, and how you need to sandbox AI-Generated Code?
Your Insecure MCP Server Won't Survive Production
Identity for AI Agents
AGI: The Path Forward
From Arc to Dia: Lessons Learned Building AI Browsers
Government Agents: AI Agents Meet Tough Regulations
Hacking Subagents Into Codex CLI
How to Defend Your Sites from AI Bots
How to Secure Agents using OAuth
How We Hacked YC Spring 2025 Batch's AI Agents
Securing Code-Executing AI Agents
The Unofficial Guide to Apple's Private Cloud Compute
Software Development Agents: What Works and What Doesn't
CIAM for AI: Authn/Authz for Agents
Prompt Engineering and AI Red Teaming
2025 in LLMs so far, illustrated by Pelicans on Bicycles
MCP Is Not Good Yet
Agents, Access, and the Future of Machine Identity
Securing Agents with Open Standards
AI Red Teaming Agent: Azure AI Foundry
Building agent fleet architectures your CISO doesn't hate
What Does Enterprise-Ready MCP Mean?
Building Protected MCP Servers
Remote MCPs: What We Learned from Shipping
The Geopolitics of AI Infrastructure
MCP: Origins and Requests For Startups
How to Build Trustworthy AI
Arrakis: How to Build an AI Sandbox from Scratch
GPU-less, Trust-less, Limit-less: Reimagining the Confidential AI Cloud
AI + Security & Safety
Privacy First Enterprise AI: Building AI Agents that Never Leave Your Security Boundary
The Hidden Costs of Building Your Own RAG Stack
AI Leadership
Building security around ML
GitHub's AI Powered Security Platform
How to Add Secure Code Interpreting in Your AI App
Building efficient hybrid context query for LLM grounding
LLM Safeguards: Security, Privacy, Compliance, and Anti-Hallucination
Enhancing Quality and Security in CI
Realtime Data Connectivity for AI
Open Challenges for AI Engineering
Open Questions for AI Engineering
Move Fast Break Nothing
The AI Evolution
The Future of Work