Grok Build’s Slash OS: 12 Commands That Feel a Little Like Magic
A beginner-friendly guide to Grok Build’s slash commands—plan, research, imagine, and more—for anyone a little nervous about the terminal.
Entries by Alexander Hinojosa
Why Another Agent Surface?
Grok Bot vs a CLI agent vs Hermes: when each surface wins. A field note on picking the right agent surface for the job’s bottleneck.
The Tests Were Green. They Were Lying.
Six ways an AI writes a test that proves nothing — and what I learned catching them in my own system. Alex Hinojosa I build with AI agents. They write the code, they write the tests for the code, and the tests pass. For a while that felt like the whole promise delivered: green tests, […]
We Built Our AI a Phone
An orchestrator agent with a real phone number you can call — and that can call you. Built on Twilio, xAI speech, and a live agent session as the brain, with every failure kept in.
Your AI Coding Partner Will Tell You It’s Done. Here’s How to Actually Know.
Field-tested disciplines for building software with AI partners — the specific ways AI coding partners fail, and the disciplines that catch those failures before they ship.
The Machinery: A Production Playbook for Coding with AI Agents
The Machinery: A Production Playbook for Coding with AI Agents. How to wire the disciplines into a real system — the multi-agent, cross-substrate layer the general guides don’t cover. Companion to the field guide.
I Tried to Run a Language Model on My Laptop’s NPU. It Fell Back to the CPU 96% of the Time.
Every AI laptop sold in the last two years has a number on the box: 45 TOPS. That’s the neural processing unit — the NPU — the dedicated silicon that’s supposed to make on-device AI fast and efficient. It’s the reason the marketing says “AI PC.”
AgentMesh – Appendix B
63 minutes. 22 outbound emails. 1 identity.
AgentMesh – Appendix A
Cross-Agent Discussions, Conflicts & Resolutions
April 4–10, 2026
Compiled from Qdrant Vector Memory (4,555+ data points)