Temperature 1.0
Every music channel in my feed started talking about Angine de Poitrine at the same time. A masked Quebec duo playing microtonal math-rock on a custom double-necked guitar shouldn’t go viral, but six million people disagree. In a culture flattened by algorithms, the deeply improbable is exactly what we’re hungry for.
Keep reading
Starlink Mini Field Review
A week on the road with the Starlink Mini taught me the best test of infrastructure is whether you stop noticing it. Suction-mounted inside the car, pointing up through the glass roof, it carried us through Big Sur’s dead zones without a single hiccup. I never had to think about it.
Keep reading
Bundled Skills in Gemini Scribe
The feature that became Bundled Skills started with a GitHub issues page. I was answering the same questions over and over, and it hit me: the agent itself should be able to answer these. It has access to the vault. It can read files. Why am I the bottleneck?
Keep reading
4255 Contributions – A Year of Building in the Open
A year ago I moved back to full-time IC work. GitHub says I’ve made 4,255 contributions since then, across 91% of the days in the year. The number tells a story I didn’t expect, about reviews, personal projects, and why the weekend turned out to be the engine.
Keep reading
Scoping AI Context with Projects in Gemini Scribe
My Obsidian vault holds nearly two decades of thoughts. When I turned an AI agent loose inside it, the agent explored everything, which was great until I needed it to focus. I built Projects in Gemini Scribe to solve this: sunglasses for the agent, not blinders. Focused context, flexible reach.
Keep reading
The Map We Drew Together – Reflections on the Agentic Shift
Seven months ago, I set out to map the age of AI agents in a twelve-part series. What started as a technical guide became a journal of a landscape in motion. Here’s what I found, what surprised me, and where the road goes from here.
Keep reading
Gemini Scribe From Agent to Platform
What started as an agent that could read notes and search the web has become a full platform with semantic search, deep research, MCP server integration, and extensible skills. Fifteen releases and over 400 commits later, Gemini Scribe isn’t just an assistant anymore. It’s a collaborator that understands your vault.
Keep reading
It’s a Poor Craftsman Who Blames His Tools
We’ve accepted ghostwriting for over a century. More than 80 percent of celebrity memoirs are ghostwritten. We never cared that the words came from someone else. So what exactly changes when the collaborator is a machine? The question isn’t whether an author used AI. It’s whether they wrote something worth reading.
Keep reading
Responsibility and the Road Ahead
We’ve spent this series mapping the territory of AI agents. But we haven’t yet confronted the question that my self-modifying agent made unavoidable: now that we can build systems that act autonomously in the world, what do we owe the world in return? The engineering is the easy part.
Keep reading
Agents in the Wild
I was giving a talk to a group of engineers last week about the ‘code smell for agents’: if you’re writing if/else logic to decide what your AI should do, you’re probably building a classifier that wants to be an agent. The room lit up with questions.
Keep reading
MCP Isn’t Dead You Just Aren’t the Target Audience
Not every agent has a shell. Gemini Scribe runs inside Obsidian’s Electron sandbox. On mobile, there’s no subprocess spawning at all. Background agents shouldn’t have shell access because it’s a privilege escalation vector. The “just use the CLI” argument only works if your agent lives in a terminal.
Keep reading
The Observability Gap
How do you debug a system that thinks in natural language? The Observability Gap is the distance between traditional logging and what agents actually need: full visibility into their reasoning, tool use, and decision-making. In this installment, we explore how to build the flight recorder that turns black boxes into transparent systems.
Keep reading
The Fingerprint of Sound
Text embeddings map meaning, but speech embeddings map identity. Discover how treating speaker recognition as a geometry problem turns the messy task of diarization into a clean clustering algorithm. It’s a powerful reminder that understanding the primitives is key to becoming an architect of AI systems, not just a consumer.
Keep reading
Great Video on Gemini Scribe and Obsidian
When a user’s repository feedback leads to a YouTube deep dive, you know you’ve found something special. I recently discovered how Paul O’Malley is using Gemini Scribe as the autonomous engine for his ‘Self-Organizing Second Brain’—a powerful reminder of the satisfying magic that happens when small tools meet big ideas.
Keep reading
Everything Becomes an Agent
Every AI project I built last year ended up becoming an agent. What starts as a simple script inevitably grows into a loop with tools, memory, and autonomy. I’ve learned to recognize the signs—and when to skip the intermediate steps and embrace the agent from the start.
Keep reading
When Agents Talk to Each Other
Our agents are brilliant but isolated. In Part 9 of The Agentic Shift, we explore the three protocols transforming how AI systems connect: MCP for tools, ACP for interfaces, and A2A for collaboration. The Internet of Agents is booting up, and our digital Robinson Crusoes are finally getting a radio
Keep reading
Bringing Deep Research to the Terminal
I lost a research report switching between the Gemini app and my terminal. Frustrated, I built what I needed: a Gemini CLI extension that brings deep research directly into my workflow. No more browser tabs, no lost formatting—just markdown files appearing where I actually work. Personal software for an audience of one.
Keep reading
The Era of Personal Software
Building bespoke tools is now often faster than searching for them. We are entering the era of Personal Software: applications built for an audience of one. Explore the shift from discovery to creation, and why AI makes it easier than ever to fit the handle to your own grip.
Keep reading
The Guardrails of Autonomy
Giving AI agents terminal access creates a tension between autonomy and safety. To cure “Confirmation Fatigue,” I built the Gemini CLI Policy Engine. It acts as a firewall for tool calls, allowing you to define granular guardrails—from safe exploration to hard stops—enabling true autonomy without the anxiety.
Keep reading
Bringing the Office to the Terminal
Leaving the terminal to check a doc or calendar breaks your flow and invites a flood of notifications. The Google Workspace extension for Gemini CLI solves this by bringing your office tools directly into the command line. Search docs, check schedules, and send messages—all without ever hitting Alt-Tab.
Keep reading
Something went wrong. Please refresh the page and/or try again.