Foundations

Foundations



Builder Primary Sources


© TinyFish, Inc.. All rights reserved.




Builder Primary Sources


When an AI agent stops mid-task to ask a human something, it often reads as a failure of autonomy. In one study, letting coding agents ask about bug reports stripped of key details won back most of the lost ground, lifting solve rates from about 55% to 69.4%. But the "human" answering was another model, holding the full report and standing by. Real people are in meetings, or asleep. The design work is in the ask: who gets it, what it says, and what happens while it waits.
When an AI agent stops mid-task to ask a human something, it often reads as a failure of autonomy. In one study, letting coding agents ask about bug reports stripped of key details won back most of the lost ground, lifting solve rates from about 55% to 69.4%. But the "human" answering was another model, holding the full report and standing by. Real people are in meetings, or asleep. The design work is in the ask: who gets it, what it says, and what happens while it waits.
Before a web agent clicks anything, somebody has already decided which version of the page it gets. The usual choices are a screenshot, the accessibility tree browsers build for screen readers, or the DOM, the browser's full model of the page. Each one makes some questions easy and others impossible.
One benchmark agent abandoned a purchase because Add to Cart sat just below the screenshot. Some business-software pages, read as DOM, run to half a million tokens. When an agent screws up, what it was shown is the first thing to check.
Before a web agent clicks anything, somebody has already decided which version of the page it gets. The usual choices are a screenshot, the accessibility tree browsers build for screen readers, or the DOM, the browser's full model of the page. Each one makes some questions easy and others impossible.
One benchmark agent abandoned a purchase because Add to Cart sat just below the screenshot. Some business-software pages, read as DOM, run to half a million tokens. When an agent screws up, what it was shown is the first thing to check.
Some words in a spec look too ordinary to need defining. “Active customer.” “On behalf of.” “Scheduled.” Each one settles a question that someone answered earlier, often years earlier: which twelve months count, whose name goes in the audit log, what happens if a government changes the clocks.
A colleague who meets the word fills the gap from context, or walks over and asks. An agent does neither. It acts on whatever definition sits closest in the data, the token or the code, and the result looks like a correct answer.
The filings, standards and papers below had to write their choices down. They suggest where yours may still be implicit.
Some words in a spec look too ordinary to need defining. “Active customer.” “On behalf of.” “Scheduled.” Each one settles a question that someone answered earlier, often years earlier: which twelve months count, whose name goes in the audit log, what happens if a government changes the clocks.
A colleague who meets the word fills the gap from context, or walks over and asks. An agent does neither. It acts on whatever definition sits closest in the data, the token or the code, and the result looks like a correct answer.
The filings, standards and papers below had to write their choices down. They suggest where yours may still be implicit.
Past Articles

Agent frameworks keep bolting on memory, self-reflection, and libraries of saved skills, and the benchmark numbers usual...

Wire AI agents together and every hand-off lands in a transcript, which people tend to read as proof the messages matter...

When an AI agent uses a website today, it reads the page much the way you would, scanning buttons, labels, and form fiel...

For thirty years, "user agent" meant one thing: software that fetches web pages. Your browser sends the string, the serv...