One Person, One AI Agent, Three Products: I Wrote the Company into Code
How one person runs three products: the agent advises, the kernels execute, I hold the gate. Discipline lives in code, not in good intentions.
ESSAYS · INTERPRETATION
Essays answer "what the facts mean." Not news summaries, but judgments worth preserving, debating, and revising.
How one person runs three products: the agent advises, the kernels execute, I hold the gate. Discipline lives in code, not in good intentions.
Others make research cheaper. Askovo makes it accountable — you always know which sentence your evidence can't back.
v0.2.0 → v0.2.2 — an open experiment engine, the first preregistered A/B on a real agent, the first external fixture, the first public evidence case, and an honest 0%.
A baseline issue, not a news roundup — fixing the current state, the measurement method, and the data definitions that every future issue will compare against.
A field audit of six real claims, and what it means for the agent economy
Seats, installs, and pageviews are breaking. Measurement is the missing infrastructure of the AI economy.
A Measurement Foundation for Capability as a Service and the Agent Capability Economy
DeepSeek Harness turns the runtime around the model into formal parts. The next problem is deciding what information, capabilities and permissions each step should receive.
Beyond replacement rates: how robots extend human vision, presence, action and physical attributes.
The title lets you make decisions. A record of solving problems together is what makes the team willing to follow them.
Market entry is not a march from niche to mainstream. It is a learning sequence built around the product's biggest current unknown.
Pages and files won't disappear — they will become different views of the same semantic and task state.