guardrails
148 talks
AI Engineer NYC 2026
Paving the Road to Production: Governed Enterprise AI Agents
Your AI Isn't the Problem. Your Infrastructure Is.
The Agent Works. Does Anyone Trust It?
Beyond RAG: Build a Relational Context Engine from Scratch
AI Agents Don't Read Your Policy Docs. They Hit Your APIs
The Lethal Trifecta Is Already on Your Laptops
AI Writes More PRs. Who Validates Them?
The 6 Pillars of an Agentic Harness for Production
Agents That Write Their Own Tools at Runtime
YOLO Mode, Safely: MicroVM Sandboxes for Any Agent
Scale the Judgment, Not the Model
I Gave an AI a Body
Opening Keynotes: Mistral, Langfuse & Sizzy
Loophole: Adversarial Agents To Stress Test Your Morality
We let an AI agent execute Bash and lived to talk about it
The Design-Code Roundtrip That Isn't
Build-Time vs. Run-Time: Why Dev Tools Fail in Production
From Coding to Knowledge Work Agents
Teaching agents to pay
Why Your AI Agent Needs a Wallet: USDC and Nanopayments
Your Agent Just Authorized What?!
Agents Are Where Microservices Were in 2015
AI Agents Are Just Distributed Systems Now
Productionizing LLM Gateways: Architecture, Tradeoffs and Hard Lessons
FinOps for AI Agents: Who Spent All the Tokens?
Give the Agent a Budget, Not a Token
What If Your Chip Design Team Moved Like a Single Body?
Agentic SDLC at Uber
IT Admin for the AI Workforce
The Last Human Code Review: Building Trust in AI-Generated Code
Unlock Agent Autonomy: The Runtime for AI-Native Systems
AI is the World's Largest Relationship Therapist
Guardrails First: Engineering Member-Facing Health AI
Healthcare's Agent Bytecode: X12 as the Harness for AI Agents
Security Firewall for Agents
From RL to IRL
Codex, Behind the Harness
Guide, Verify, Solve
Realtime multiplayer, automation, and you!
Reinforcement Learning without Verifiable Rewards
Verifiable Environments for AI in Biology
Build for the Memo, Not the Demo
How Kepler Built Verifiable AI for Financial Services
We Vetted 2,000 AI Skills Before They Reached Developers
Wearing the Agent: From Group Chats to Glasses
Evals-Driven Development for a Mental Health AI Coach
Building Closed-Loop Evals for a Multimodal Agent at Scale
Why Agentic Systems Need Ontologies
Active Graph Agent Runtime (BabyAGI 4)
Agentic Development Security
Agentic Security: Permissions, Provenance, and the Agent Supply Chain
AI's Jurassic Park Period
In the Land of AI Agents, the Verifiers Are King
Security Track Intro
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
Agents Need Feature Flags
The UX of AI: Making AI-Powered Apps Your Users Don't Hate
The Great Loops Debate
Claude Fable, Claude Tag, and Anthropic's Culture
I've Never Seen Anything Scarier Than an LLM with Tool Calls
The AI bugpocalypse is here. Now what?
What Does Done Even Mean? Agents and Paperclip's Liveness Model
Design Patterns for AI Trust: Juries, Libraries, and Agent Tiers
Every Solo Agent Builder Eventually Reinvents a Worse Version of CI/CD
From Writing Code to Designing Systems: How the Developer Role is Changing
Stop AI Agent Hallucinations: 5 Techniques + Production Patterns
The Factory That Dreams: 39 AI Agents, No Framework
Your LLM Deception Monitor Is Broken. The Fix Is in the Training Data
What if the harness mattered more than the model?
Deterministic Infra for Non-Deterministic AI Agents
Bypassing the Multimodal Tax: Hybrid RAG, SQL RRF & UI Telemetry
Agents in Production: How OpenGov Built and Scaled OG Assist
Stop Writing Tone Instructions. Layer Them.
Your Agent's Biggest Lie: "I Searched the Web"
Building Safe Payment Infrastructure for the Autonomous Economy
BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike
Spec-Driven Testing for Agents With A Brain the Size of A Planet
How I Deleted 95% of My Agent Skills and Got Better Results
Context Graphs for Explainable, Decision-Aware AI Agents
What the Best Agents Share
What Breaks When You Build AI Under Sovereignty Constraints
AI Engineer Singapore Day 2
Harnesses in AI: A Deep Dive
AIE Singapore Day 1
Human-in-the-Loop Automation with n8n
I Gave an AI Agent the Keys to My Life: Here's What Happened
Agents Need More Than a Chat
The Friction is Your Judgment
Harness Engineering: How to Build Software When Humans Steer, Agents Execute
$1 AI Guardrails: The Unreasonable Effectiveness of Finetuned ModernBERTs
Bending a Public MCP Server Without Breaking It
Platforms for Humans and Machines: Engineering for the Age of Agents
Claude Agent SDK [Full Workshop]
How Claude Code Works
Real World Development with GitHub Copilot and VS Code
How We Hacked YC Spring 2025 Batch's AI Agents
Securing Code-Executing AI Agents
Everything is ugly, so go build something that isn't
Why you should care about AI interpretability
Building Applications with AI Agents
From Copilot to Colleague: Trustworthy Agents for High-Stakes
How Intuit Uses LLMs to Explain Taxes to Millions of Taxpayers
How to Build Planning Agents without Losing Control
Critical AI Inference Your CIO Can Trust
Knowledge Graphs in Litigation Agents
Top Ten Challenges to Reach AGI
Building Effective Voice Agents
Real-world MCPs in GitHub Copilot Agent Mode
Automating Escrow with USDC and AI
Securing Agents with Open Standards
Building voice agents with OpenAI
Agentic Excellence: Mastering AI Agent Evals with Azure AI Evaluation SDK
AI Red Teaming Agent: Azure AI Foundry
Data is Your Differentiator: Building Secure and Tailored AI Systems
The Agent Awakens: Collaborative Development with Copilot
How to Build Trustworthy AI
The Robots Are Coming for Your Job, and That's Okay
Evaluating Domain-Specific LLMs for Real-World Finance
AI + Security & Safety
Personal, Local, Private AI Agents
Scaling Agents for Gen AI Products
Navigating AI's Frontier in 2025
OpenAI for VPs of AI + Advice for Building Agents
Building Multi-agent Systems with Finite State Machines
Let's Build an Agent from Scratch
Stop Guessing: Build Robust AI with Layered CoT
Agentic Workflows on Vertex AI
Building security around ML
GitHub's AI Powered Security Platform
Scaling AI in Education: A Khanmigo Case Study
LLM Safeguards: Security, Privacy, Compliance, and Anti-Hallucination
Navigating Challenges and Technical Debt in LLMs Deployment
Understanding AI Stakes to Break Production Code
AI Frontiers in Trust and Safety: Combatting Multifaceted Harm on Tinder at Scale
Iterating on LLM apps at scale: Learnings from Discord
The Multimodal Future of Education
Pydantic is STILL all you need
Lessons From A Year Building With LLMs
Trust, but Verify
Lessons from the First Viral CLIP App
Pragmatic AI with TypeChat
Building Blocks for LLM Systems & Products
Pydantic is all you need
The Future of Work
AI Engineer Summit 2023, Day 2 Livestream
AI Engineer Summit 2023, Day 1 Livestream