human-in-the-loop
161 talks
Deploying AI Inside a Bank Is Not an Engineering Problem
The Agent Works. Does Anyone Trust It?
What Technical Due Diligence Finds When the Deck Says "70% Automated"
We Let Our Financial Planners Write the Agents
Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop
Brains vs Hands: How to Run AI Agents Safely in Production
Giving AI Agents Memory That Learns
Why We Deleted Our MCP Server and Rebuilt It
Your AI Agent Has No Nervous System
The Self-Improving OSS Agent Stack
Your LLM Judge Is a Confident Liar: Building Better Verifiers
The Human Is an Async API
Why AI Didn't Actually Make You Ship Faster
Your Agents Are in Solitary Confinement: Why MCP & A2A Aren't Enough
How Software Factories Improve Themselves
Orchestras, Not Factories: How the Fastest Builders Work
Software Engineering Is Becoming Factory Engineering
I Gave an AI a Body
You're Not Thinking Big Enough: Rebuilding Food Systems with AI Agents
Design at the Speed of Adjectives
One Designer + AI. Hundreds of Deliverables.
The Design-Code Roundtrip That Isn't
Agents' Next Frontier: Agent-to-Agent and Network Effects
Your Company Brain Will Leak Secrets: How We Stopped It for Big Banks
AI Evals for Cross-Functional Teams
How to Avoid Disaster When Vibe-Coding a Billing Engine
How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage)
AI in GTM at Notion
GTM Engineering: The Technical Bits
The Building Blocks of GTM Orchestration
Give the Agent a Budget, Not a Token
The Agent Behind the Curtain: Building the Oz Cloud Agent Platform
The Era of Compound Engineering
The Last Human Code Review: Building Trust in AI-Generated Code
Don't Be Data Poor
Shipping AI to a Million Patients Without an A/B Test
Trading Desks to Clinical Trials: Parallels in Applied Vertical AI
Why Your Enterprise Tech Stack Isn't Ready for AI Agents
Building an Agentic Video Editor for Mass Consumer
Security Firewall for Agents
From RL to IRL
When Will the Benchmaxxing Plague End?
Ending AI Slop
Build for the Memo, Not the Demo
Your Finance Agent's Bottleneck Is You
We Vetted 2,000 AI Skills Before They Reached Developers
AI Agents for Performance: Ship Faster, Pay Less
How Forward Deployed Engineering is done at Factory
How Forward Deployed Engineering is done at Ramp
Evals-Driven Development for a Mental Health AI Coach
Loop Engineering from First Principles
From Signal to PR: Anatomy of a Self-Improving Agent
Harness Engineering is Not Enough: Why Software Factories Fail
Perception Agents
AI's Jurassic Park Period
Build the AI GTM Agent That Knows the Buyer
Can Oncology Workflows Run Without Human Touch?
Why Your Agent Disagrees With Itself (And What To Do About It)
Build Evals That Actually Matter
From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization
Stop Burning Tokens: Why Self-Improvement Needs Domain Expertise First
The UX of AI: Making AI-Powered Apps Your Users Don't Hate
The engineer of the future is the person who is able to choose what is worth doing.
Chat and citations won't save your vertical AI
From Writing Code to Designing Systems: How the Developer Role is Changing
Should AI Engineers Still Read Code in 2026? The Z/L Continuum
Understanding is the new bottleneck
I Run a Fleet of AI Agents Across Three Machines. Here's What Broke.
Build AI Systems for Discernment, Not Approval
Software Factories & Keynotes
AI System Design: From Idea to Production
Using Spec-Driven Development for Production Workflows
Build Systems, Not Code
Production Evals For Agentic AI Systems
AI Engineer Melbourne 2026 Keynote Livestream | Day 2
How Agent Observability Differs from Traditional Observability
Most Enterprise Agentic Projects Are Doomed, Here's Why
The maturity phases of running evals
Cooking with Agents in VS Code
Connecting the Dots with Context Graphs
How to Leverage Domain Expertise
CI/CD Is Dead, Agents Need Continuous Compute and Computers
A Piece of Pi: Embedding the OpenClaw Coding Agent in Your Product
Demand-Driven Context: A Methodology for Coherent Knowledge Bases Through Agent Failure
Human-in-the-Loop Automation with n8n
Agents Need More Than a Chat
The Friction is Your Judgment
Paperclip: Open Source Human Control Plane for AI Labor
Judge the Judge: Building LLM Evaluators That Actually Work with GEPA
Contact Center Voice AI: Low-Latency Intelligence Extraction from Messy Audio Streams
Agentic Engineering: Working With AI, Not Just Using It
Identity for AI Agents
Building Durable Agents with Workflow DevKit & AI SDK
Small Bets, Big Impact: Building GenBI at a Fortune 100
No More Slop
AI Kernel Generation: What's Working, What's Not, What's Next
Proactive Agents
Defying Gravity
Backlog.md: Terminal Kanban Board for Managing Tasks with AI Agents
Infra that fixes itself, thanks to coding agents
How BlackRock Builds Custom Knowledge Apps at Scale
Form factors for your new AI coworkers
The Future of Evals
Securing Code-Executing AI Agents
Make Your LLM App a Domain Expert: How to Build an Expert System
Devin 2.0 and the Future of SWE
Software Development Agents: What Works and What Doesn't
AI That Pays: Lessons from Revenue Cycle
3 ingredients for building reliable enterprise agents
Building Agents (the hard parts!)
The Billable Hour is Dead; Long Live the Billable Hour
Critical AI Inference Your CIO Can Trust
How to Hire AI Engineers when EVERYONE is cheating with AI
How to Run Evals at Scale: Thinking Beyond Accuracy or Similarity
Knowledge Graphs in Litigation Agents
AI and Human Whiteboarding Partnership
UX Design Principles for Semi Autonomous Multi Agent Systems
Robots as Professional Chefs
Benchmarks Are Memes: How What We Measure Shapes AI and Us
Automating Escrow with USDC and AI
The Build-Operate Divide: Bridging Product Vision and AI Operational Reality
Mastering AI Evaluation: From Playground to Production
Don't get one-shotted: Use AI to test, review, merge, and deploy code
Evals 101
How to build world-class AI products
Mastering Engineering Flow with Windsurf
Taming Rogue AI Agents with Observability-Driven Evaluation
Unlocking AI-Powered DevOps Within Your Organization
Vibe Coding at Scale: Customizing AI Assistants for Enterprise Environments
Case Study + Deep Dive: Telemedicine Support Agents with LangGraph/MCP
The Web Browser Is All You Need
Beyond Conversation: Why Documents Transform Natural Language into Code
Breaking the Chain: Agent Continuations for Resumable AI Workflows
Buy Now, Maybe Pay Later: Dealing with Prompt-Tax While Staying at the Frontier
Designing AI To Scale Human Thought
Grounded Reasoning Systems for Cloud Architecture
The Robots Are Coming for Your Job, and That's Okay
Creating Agents that Co-Create
The Missing Pieces of Workflow Automation
The DevOps Engineer Who Never Sleeps
How to Fail at AI Strategy
Trust, but Verify: Knowledge Agents for Finance Workflows
Building Enterprise LLM Agents That Work
Don't Just Slap on a Chatbot: Building AI That Works Before You Ask
How Coding Agents Change Software Development Forever
Mission-Critical Evals at Scale
WTF do people use Open Models for?
Your Evals Are Meaningless (And Here's How to Fix Them)
Your LLM Ran Out of Knowledge: Now What?
GitHub Next Explorations
Best Practices for Evaluating Large Language Model Applications with llmeval
Hiring & Building an AI Engineering Team
LLM Safeguards: Security, Privacy, Compliance, and Anti-Hallucination
Understanding AI Stakes to Break Production Code
Enhancing Quality and Security in CI
The Multimodal Future of Education
How to Construct Domain Specific LLM Evaluation Systems
Judging LLMs
Building Reliable Agentic Systems
Copilots Everywhere
Building Blocks for LLM Systems & Products