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?
The library
Everything we publish, in one place
The AI Runtime library brings together our weekly newsletter, the free field guides and playbooks, and Signal from the room: the questions practitioners are working through, answered. All free.
From the newsletter Issue The AI Runtime · Aug 28, 2026 Issue The AI Runtime · Aug 26, 2026 Issue The AI Runtime · Aug 11, 2026 Issue The AI Runtime · Aug 7, 2026 Issue The AI Runtime · Aug 5, 2026 Issue The AI Runtime · Jul 28, 2026 Issue The AI Runtime · Jul 17, 2026 Issue The AI Runtime · Jul 6, 2026 Issue The AI Runtime · Jul 2, 2026 Issue The AI Runtime · Jun 28, 2026 Issue The AI Runtime · Jun 24, 2026 Issue The AI Runtime · Jun 22, 2026 Issue The AI Runtime · Jun 20, 2026 Issue The AI Runtime · Jun 18, 2026 Issue The AI Runtime · Jun 15, 2026 Issue The AI Runtime · Jun 11, 2026 Issue The AI Runtime · Jun 8, 2026 Issue The AI Runtime · Jun 8, 2026 Issue The AI Runtime · Jun 7, 2026 Issue The AI Runtime · Jun 5, 2026
The AI Runtime, issue by issue
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 before the software gets deployed.
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 actually worked.
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 the half of the loop everything else depends on.
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 govern the transformation as a program.
The New Role of the Senior Engineer in an Autonomous Development Workflow
Part I: The Senior Engineer Stops Being the Fastest Coder
The AI System That Never Touches a Live Transaction
How Sphere separates probabilistic AI research from deterministic tax execution
How FDEs Build Reliable Web Agents
Your Web Agent Needs a Trust Layer, Not a Bigger Model
Building a Production-Grade AI Web Data Agent
Part 1: Getting the data reliably
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 rewrote its own timeout, a deletion during a code
What Is Loop Engineering? The Control System Behind Reliable AI Agents
The visible half of loop engineering is orchestration. The decisive half is the control system that keeps the loop bounded.
Architecting the Auto-Updating Enterprise AI Data Loop
Tackling the AI Information Silos problem
AI Made Individuals Faster. Why Are Teams Still Slow?
The Next Bottleneck in AI Systems Is Context Transfer
State Machines for AI Agents: A field guide from Forward-Deployed Engineering
Agents reason. State machines remember.
The "Self-Improving" AI Myth (And What 60 Production Deployments Actually Do)
Sixty production deployments converged on a three-layer architecture where the eval surface, not the base model, is the moat.
Dario Amodei’s “Policy on the AI Exponential” Describes a World Banking AI Already Lives In
His new essay asks regulators to build an FAA for AI models. If you ship AI inside a bank, you already work in that regime, and there is a five-minute test that tells you whether your agent is as far
Harness Half-Life: A Field Playbook for Catching Agent Decay
The harness engineering discourse names what to build. The Model Reliability Engineering arc names how long the build lasts, what kills it, and what to do at week six.
The AI Eval Gate Cheat Sheet
Most AI projects die in the gap between "works in the demo" and "works in production."
Two Ways to Shrink an AI Model. Only One Keeps the Output.
Quantization changes the numbers. Lossless compression removes the wasted bits and keeps every output identical, for about 30% less memory.
Two Ways to Shrink an AI Model. Only One Keeps the Output.
Quantization changes the numbers. Lossless compression removes the wasted bits and keeps every output identical, for about 30% less memory.
Guides & playbooks
Free, field-tested resources
Signal from the room
One question, one honest answer
Questions
Ask us a specific question
Working on something specific? Ask our team directly. We read every question.
Subscribe
Get it in your inbox
One free issue a week on Vertical AI Agents, Model Reliability Engineering, and lessons from the trenches of shipping AI.
The AI Runtime newsletter
Production-grade writing, in your inbox.
Read by AI practitioners at IBM, Amazon, Meta, Google, Nvidia, OpenAI, MIT, Harvard, and more for production learnings.
Free. No spam. Unsubscribe in one click. See past issues →