Every Correction Is a Failure Report
Every correction is a failure report. Michael Houck pulled three months of product corrections he’d given his agent, 564 of them in 14 patterns, and …
Read more →$
whoami --verbose
● always shipping
|
Portland, OR
|
agentic mesh · agent runtimes · ai gateways
MIKE MOORE
building the agentic future in public
I run LLMs, robots, and gateways into production walls so you don't have to. Deep dives on the agentic mesh, agent runtimes, AI gateways, and the Kubernetes substrate that keeps autonomous systems honest — every post ships with a repo you can clone and receipts you can check.
Start here
Agent Identity
How an agent proves who it is: SPIFFE, token exchange, and audience binding.
Open the hub →Agent Security
Controls that look like controls and are not, and what to put in their place.
Open the hub →AI Gateways
The call path between agents and models: identity, spend, and policy in one place.
Open the hub →MCP
How agents find tools, which servers exist, and who those tools act for.
Open the hub →Agent Runtimes
Start, stop, and isolate agents on Kubernetes. kagent and the substrate under it.
Open the hub →Robotics
The house as a cluster, the cost of a capable machine, and who signs the test report.
Open the hub →The Latest Drops
What Agent Escape Actually Looks Like in Infra
Real agent escape is not a model copying its weights to a server in another country. It is an agent reaching something you did not mean it to reach: a token …
Read more →Ghost Actors Pin Your Workers
Ghost actors pin your workers. A session killed mid-flight can leave its actor holding a WorkerPool slot, sometimes after that actor has disappeared from …
Read more →AI Rights or No Rights? The Four Questions
There is no consensus on whether AI should have rights, and the question is too big for one yes or no. It breaks into four tests: whether AI can be a legal …
Read more →The Autoscaler Made It Worse
The autoscaler made it worse. On a model backend that generates one response at a time, adding Agent Substrate workers does not add throughput: it restores …
Read more →Every Agent Escape Story, Rated
No public report shows a production agent breaking out of its environment on its own. The famous agent escape stories are red-team evaluations: researchers …
Read more →CPU Is the Wrong Signal to Autoscale Agents
CPU is the wrong signal to autoscale agents. Agent Substrate workers are slot-bound, one actor per worker, and an LLM session is mostly I/O wait, so workers …
Read more →A Refusal Is Not a Clean Scan
A refusal is not a clean scan. If an LLM review step comes back with “I can’t help with that,” the review did not happen, and the pipeline …
Read more →The Actors List Lies. Trust the Workers List.
The actors list lies: every finished Agent Substrate session leaves a Suspended entry behind, so the inventory grows without bound and returns partial results …
Read more →Running Factory Droid as a kagent Agent on Agent Substrate
I wanted to know whether a third-party coding agent could run as a first-class kagent agent, inside an Agent Substrate sandbox, doing platform engineering work. …
Read more →