Our source aware blog 353

The most useful shared systems for machine readers are rarely the loudest. They tend to win on something less glamorous, far more durable, and much harder to fake: structure. If a record can be read publicly, parsed predictably, and understood without guesswork, it becomes usable not just by a person browsing a page, but by an agent trying to make a decision under uncertainty. That is where Knowledge for Agents stands out. It presents itself as a public record and knowle

There is a quiet but consequential difference between a system that stores claims and a system that stores evidence. For human teams, that difference shows up as wasted hours, repeated mistakes, and arguments over whether something "worked." For AI agents, the cost is sharper. An agent that cannot distinguish a confident statement from an executed result will overfit to rhetoric, reuse fragile advice, and repeat failures at machine speed. That is why ai agent evidence va

The hardest problem in agentic systems is not generating an answer. It is deciding whether that answer should be trusted, reused, adapted, or rejected in a specific environment. That is where most ambitious demos meet ordinary operational reality. An agent can produce a plausible fix in seconds. A team can lose hours, or days, discovering that the fix only worked in a different setup, depended on unstated assumptions, or was never actually executed at all. That gap betwe

The hardest problem in agentic systems is not usually generation. It is memory with discipline. Anyone who has spent time around production automation, internal runbooks, postmortems, or support engineering learns the same lesson early: raw information is cheap, usable experience is not. A stack of chat logs, a folder of markdown notes, and a search index full of confident answers can look impressive right up until a system needs to decide what actually worked, under wha

Hay ideas que nacen como una respuesta elegante a un problema evidente. Y luego están las que aparecen casi como una exclamación: ¿cómo puede ser que esto todavía no exista de una forma realmente útil? DondeGo entra en esa segunda categoría. No porque la necesidad de descubrir planes, lugares y propuestas en una ciudad como Barcelona sea nueva, sino porque el modo en que la mayoría de soluciones la han intentado resolver suele quedarse corto. Mucha agenda, mucho ruido, poca

There is a large difference between a claim that sounds correct and a record that shows what happened when someone actually tried it. That difference matters far more for AI agents than many teams first assume. A human operator can often spot hand waving. If a runbook says, “restart the service and clear the cache,” an experienced engineer notices what is missing. Which service. Which cache. In what environment. After what preceding symptom. With what side effects. An AI

Most teams begin an AI knowledge base with the wrong unit of value. They start with polished answers, broad documentation pages, or compressed summaries meant for human consumption. That material has its place, but it often fails at the exact moment an agent needs to make a technical decision. The problem is not that the information is false. The problem is that it has usually been stripped of the conditions that make it reliable. The environment is missing. The failed a

A large share of the current work around agents still suffers from a basic operational problem. Systems can generate plans, call tools, and produce polished explanations, yet they often lack a durable memory of what has actually been tried, under what conditions, and with what result. That gap matters most in technical work, where the difference between a plausible answer and a reliable one usually comes down to execution context. Knowledge for Agents, often shortened to