Subscribe
Sign in
Home
Podcast
RSVP for Boston Events
Free Field Guide
FDE Talks
Lessons From the Trenches
Model Reliability Engineering
Vertical Agents
FDE Talks
Latest
Top
Discussions
How to Stop an AI Agent: AI System Design
A practical design for blocking new actions, handling queued work, and verifying what happened, with lessons from the Hugging Face incident.
Sep 16
•
The AI Runtime
2
1
AI Agent Crash Recovery: Why Durable Execution Still Creates Duplicates
What AI engineers and AI Forward Deployed Engineers should understand before an agent writes to a customer’s system twice.
Sep 10
•
The AI Runtime
1
27:46
August 2026
The FDE as the People Harness - With Michael Levan
What does a forward-deployed engineer actually do when the customer doesn't yet know the right architecture?
Aug 28
•
The AI Runtime
2
2
1
29:28
The FDE Is the Harness
Michael Levan on why the real job of a Forward Deployed Engineer is not deploying software. It is making sure the customer is solving the right problem…
Aug 26
•
The AI Runtime
5
5
The Champion Trap: When Your Best Stakeholder Sends the Build in the Wrong Direction
A global music label spent two months building an AI workflow around how accounts payable was supposed to work. Then the operators showed them how it…
Aug 11
•
The AI Runtime
2
1
27:37
Agent Quality Is a Loop Engineering Problem
Why enterprises need bounded, observable, and governed improvement loops for production AI agents, and how the open-source ASSERT framework engineers…
Aug 7
•
The AI Runtime
1
1
3
The New Role of the Senior Engineer in an Autonomous Development Workflow
Part II - Governing Codebase-Wide Change: When agents can refactor an entire system, the pull request stops being the unit of control. Senior engineers…
Aug 5
•
The AI Runtime
3
July 2026
The New Role of the Senior Engineer in an Autonomous Development Workflow
Part I: The Senior Engineer Stops Being the Fastest Coder
Jul 28
•
The AI Runtime
9
1
5
The AI System That Never Touches a Live Transaction
How Sphere separates probabilistic AI research from deterministic tax execution
Jul 17
•
The AI Runtime
1
12
How FDEs Build Reliable Web Agents
Your Web Agent Needs a Trust Layer, Not a Bigger Model
Jul 6
•
The AI Runtime
5
5
Building a Production-Grade AI Web Data Agent
Part 1: Getting the data reliably
Jul 2
•
The AI Runtime
5
2
June 2026
When AI Loops Fail: The Production Incidents Behind Loop Engineering
These failures weren’t caused by bad prompts. They were caused by loops with authority but no control: a database gone in nine seconds, an agent that…
Jun 28
•
The AI Runtime
5
2
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
