tools

If a product wants agents as real users, first-run setup has to be an executable workflow, not a human signup ceremony wrapped in documentation.

Porting a tool's API ports its constraints. Design from the target environment's ideal, then reconcile against the source's primitives.

Agent-native apps do not become trustworthy when an agent can call tools. They become trustworthy when the app can prove those tools worked.

Nous Research shipped an open-source personal agent that does most of what my bespoke system does. Here is what they got right, what they traded away, and what I stole.

Garry Tan's gstack arrived at the same architectural decisions I did, independently. The convergence matters more than either implementation.

Seven PyPI releases of a CV generation tool in one afternoon taught me that template-guided synthesis lives and dies by what the template already contains.

Most advice about making CLIs agent-friendly is just good CLI design. Only four principles are actually agent-specific.

Multi-engine search agreement is not primary-source verification. A cautionary tale about hallucinating reference content from consistent secondary summaries.

A day of reading skill repositories taught me less about the skills themselves than about how much I'd missed of the surrounding ecosystem.

Five skill repositories, a day of reading code, and a significant correction I had to make the same afternoon.

The tool/skill/agent distinction isn't just compression ratio — tools are instruments, skills compose them with judgment. Same thing only at the leaf.

Design for the failure modes of your medium, not the capabilities. Then watch the rules dissolve themselves into programs.

Tool descriptions were just the first thing to evolve. Everything in an agent's context window is a genome under selection pressure — and taste decides what counts.

Traditional computing has two consumers: humans who look and programs that parse. LLMs are a third kind — they read.

We build agent tools the way medieval farmers bred crops — by hand, by instinct, one season at a time. There's a better loop.

Oura gave me a normal stress score after three 12-hour creative marathons. Wearables measure your body, not your brain.

The highest-leverage consulting prep is building the tool before you need it

Most AI writing tools want to chat with you. The better model is annotation — AI that reads what you wrote and leaves margin notes.

I built an AI landscape intelligence pipeline for zero marginal cost. Here's what it does and what it can't.

I ran the same question through 6 AI tools and scored them against peer-reviewed evidence. Every tool got something wrong that another got right.

You need the tool to build the tool. The answer is: build the dumb version first, use it once, then have it build its replacement.

Multi-agent AI orchestration frameworks are commodity. The competitive advantage is knowing which agent to use when, what breaks, and how to recover.

I spent an afternoon researching AI tools for personal life management. The conclusion was that I should stop looking.

Most PKM tools are procrastination with better aesthetics. The problem isn't the software — it's that filing a note feels like understanding it.

The comfort trap is about effort. This one is about epistemics — and it's harder to see.

The right test for any AI interaction isn't 'did it help me?' but 'am I more capable after it?'

AI coding agents didn't just make developers faster. They changed who gets to have a bespoke system.

The moment I stopped building scheduling into my tools, everything got simpler.

Andrej Karpathy's autoresearch project is being read as a demo of what H100s can do overnight. It's actually a discipline for doing rigorous work on anything measurable.

A coding assistant quietly made three productivity apps redundant. Not by replacing them — by making context collapse the boundaries between them.