My model said no. That isn't the control.
Three always-on agents behind AgentMinder. My model refused every planted email and brief; when I hijacked the agents, AgentMinder still said no.
An agent becomes more interesting when it can change something outside the chat. It also becomes easier to break. These experiments cover the permissions, memory, recovery paths and human supervision needed when an agent operates infrastructure or a live application.
Rhodes introduces the infrastructure guardrails; Supra and the Markdown memory store explore persistence and interruption. The publishing postmortem and the overlapping Sleeper drafts show why software completion and a useful outcome need separate measurements. The failures are part of the record.
Start here
- Giving Rhodes write access to my infrastructure
- I built a personal AI that decides when to interrupt me. In 30 days it decided no 1,784 times.
- I didn't give my agents a vector database. I gave them 126 text files.
- The upgrade worked. Turning the machine back on is what failed.
- I built a machine that wrote 278 articles. Nobody read them.
- DELPHI: a Monte Carlo agent for my Superflex fantasy draft
- I let Astra draft two fantasy teams. I kept a hand on the mouse.
Field notes on this topic
Securing my agents starts with where they run
I already run always-on agents. My microVM experiment starts a series on controlling their environment and testing where each security protection applies.
How I moved the Field Signal newsroom into VKS on the Dell.
The Dell VKS build behind my Field Signal newsroom: Avi, storage, private Spark inference, migration failures, and verified publication.
I rebuilt Field Signal around my local AI.
I rebuilt Field Signal around a local model API on my Spark, with workers on Dell VKS and Paperclip for review. More room to build and learn.
I bought a Spark. Now I want to put local agents to work.
My DGX Spark now runs Field Signal’s text agents. Next: practical agent workflows for VCF Operations, vDefend security reviews, and Avi application health.
I forked OpenClaw. Now I’m handing agents my errands.
After forking OpenClaw, I’m using Instinct, Muse, and Grok Bot for emails, refunds, flights, and business work. What good UI changes, with sourced specs.
My lab has an IT support team now. Nobody on it is allowed to touch anything.
A read-only AI IT support team for a private cloud lab: VCF Operations evidence, typed Jev judgments, and six bounded read-only specialists that end every investigation by asking a human. What is live, what is only planned, and the night the cluster it runs on ran out of memory.
My homelab was beefy. It still wasn't enough.
A homelab update: why I outgrew a rack of old enterprise hardware, the MINISFORUM MS-A2 I bought to replace it, what NVMe memory tiering does for a small box, and where this blog is headed next: on-prem AI workloads, agents, and how to run them safely.
I let Astra draft two fantasy teams. I kept a hand on the mouse.
I gave Astra two overlapping Sleeper drafts and my DELPHI analysis project. The picks, missed turns, uneven results, and baseline for weekly updates.
The upgrade worked. Turning the machine back on is what failed.
An agent-driven ESXi upgrade that succeeded, a restore step that failed on a precondition nobody checked, and a rollback that retried the exact action that had just failed. What I got wrong.
Agents are a new class of workload. Private cloud is where you contain them.
An agent with a kubeconfig is not an information system, it is an operator. Part 1 of a series on why least privilege, RBAC and audit logs all quietly assume the actor is deterministic, and how VCF and VKS primitives bound something that is not.
I didn't give my agents a vector database. I gave them 126 text files.
A working design for agent memory that survives the restart: one fact per Markdown file, an index loaded every session, wiki-links instead of a graph database, and the ways it quietly rots. Measured from a real store of 126 memories.
I built a machine that wrote 278 articles. Nobody read them.
Apollo published 278 articles in 14 weeks to zero subscribers. A postmortem of a pipeline that worked as software and failed as a publication.
I built a personal AI that decides when to interrupt me. In 30 days it decided no 1,784 times.
A build log for Supra, my personal AI system: skill dispatch via tool use, a proactive judge stuck in cold-start deadlock, and a self-improvement loop that mined a test fixture.
DELPHI: a Monte Carlo agent for my Superflex fantasy draft
How I built DELPHI, a Monte Carlo simulator for a ten-team Superflex PPR fantasy football league, used it to rank draft strategies against the room, and then audited its four modeling flaws: correlation, circularity, frozen in-season assets, and floored-Normal scoring.
Giving Rhodes write access to my infrastructure
What it took to let an agent restart VMs and delete snapshots on real infrastructure: the tier model, the guardrails in code, and the bugs found along the way.