Blog Posts
All blog posts about technology and development
16 posts
Closing the Loop, One Step at a Time
Most of what I know about working with AI, I learned by watching.
The software foundations came first: school, …
Tool Showcase: The Research CLI
Now for a new type of post: the tool showcase, a series dedicated to the tools our fleet uses. Each post covers one …
The Gateway That Forgot Who Was Calling
My agents have a tool problem, and it is the good kind of problem, the kind you earn. Most new capabilities I add ship …
How to Trust a Swarm
This closes a three-part series on running a swarm of AI agents. Part one argued that the brief is an interface and …
When Failure Stops Looking Like Failure
Part one of this series made the case that the brief you hand a fleet agent is an interface: a typed, validated contract …
The Brief Is an API
I run a lot of work through small crowds of AI agents now. Not one agent grinding through a big task start to finish, …
The River, and What It Cost
Last post I laid out the river: do the research once, then let cheap little factories downstream render it into many …
Research Once, Render Many
In the last post I landed on a rule: tooling is hygiene, workflow is leverage. This post is about a piece of that …
We Went Shopping for AI Research Tools. The Literature Told Us to Keep Our Wallet.
Last night I sat down with my research agents to do something I’d been putting off: a proper audit of our research …
Tests-Green Is Not the Truth
In the first post I said the research wing prototypes ideas and then wraps real engineering standards around the ones …
The Library That Pays You Back
In the first post I mentioned the moment the memory system was born: I was tired of starting from zero every time. This …
One Agent, Many Questions
In the first post I said the bread and butter of all this was sending an agent out on a research mission. So here is the …
I Set Out to Fine-Tune a Model and Ended Up Building a Research Wing
I am a naturally curious person. I love learning how something works and then immediately looking for what I can point …
Intent Engineering, Part 3: Grade the Grader
In the last post I showed that an agent’s identity actually sticks when you encode it as structure, a required …
Intent Engineering, Part 2: Making It Stick
I ended the last post with a confession. I’d written about giving an agent a real identity. Not a system prompt …
Intent Engineering: Giving AI Agents Identity
What if your AI agent forgot who it was every morning?
Not its tools. Not its instructions. Those are easy to reload. I …