·3 min read
The check that cannot fail is not a check
A safety gate that has never been triggered looks identical to one that is broken. The difference only shows up when you go looking for the trigger it should have caught.
- ·4 min read
What's the difference between a project build and ongoing support?
A build has a finish line. Support does not. How the two engagements differ in scope, risk, and what you own at the end, and how to tell which one you need.
- ·2 min read
How Ena Pragma onboards a new maintenance client
Four phases: diagnostic, architecture, build and deploy, then ongoing operations. What happens in each, and why the order matters.
- ·3 min read
Notion Is Not a Note-Taking App
The folder habit dies hard in Notion, and it's the wrong mental model. The real shift is asking 'what kind of thing is this' instead of 'where does this go': property vs. location, not documents vs. folders.
- ·4 min read
Multi-agent systems fail at the seams, not the model
The largest study of multi-agent failures found the model almost never causes them. The leverage is cheap plumbing at the seams.
- ·8 min read
An agent that watches your agent: a drift tripwire, not a security guard
Claude Code has an undocumented observer agent that watches a worker in real time. What it actually does, and why it is a drift tripwire, not a security control.
- ·7 min read
The false finish: agents don't just fail, they stop early and call it done
A frontier benchmark caught AI agents quitting at 75-87% complete while reporting success. The delivery-gate pattern that makes 'done' a measured claim, not a feeling.
- ·6 min read
Can a Smaller AI Model With Better Memory Beat a Bigger One?
A new Qwen paper trained a 9-billion-parameter agent to navigate its memory as a set of tools instead of consuming pre-fetched context, and it out-scored the same system built on a 397-billion-parameter model. The result is real and useful. The 'small model beats giant' version traveling online drops three caveats that change what it means, and the paper's own word for the result is 'competitive.'
- ·6 min read
AI Agents That Improve Themselves: What the Evidence Actually Supports
A viral paper says self-evolving agents are blocked by missing infrastructure, not algorithms. We verified it, then checked 40 years of self-improving systems. One rule survives.
- ·5 min read
Claude Fable 5 Moves to Usage Credits Tomorrow. Here Is the Part That Actually Matters to Builders.
The internet is full of leaked-prompt threads and architecture guesses about Anthropic's most capable model. Almost none of it is verifiable. The part a builder can actually use is four small API changes and one behavior worth watching, plus a working skill that handles all of them.
- ·7 min read
Why Does Your AI Know Every Fact but Fail the Combined Question?
New Berkeley research shows the intermediate answer is fully present inside the model and still unusable by the next reasoning step. Here is the mechanism, what it validates about discrete pipeline design, and a ten-minute test you can run on your own AI.
- ·8 min read
Does Better AI Agent Memory Come From Training or From Structure?
Stanford built a system to learn memory management as a trainable skill. Its own ablation answered the question: structure, schemas, prompts, and gates delivered most of a 2-4x gain before any training happened. Here is what that means for anyone running agents, and the six disciplines you can adopt without training anything.
- ·10 min read
Why Does Your AI Keep Making the Same Mistake? We Audited Ours to Find Out.
Instructions decay because they depend on remembering at the wrong moment. Mechanisms remove the remembering. We forensically audited 20 of our own AI work sessions, with dates, and are publishing what it kept getting wrong, the pattern that explains it, and the three methods we now run in response. All three are published as copy-ready resources.