Your context rich blog 103

Analysis

AI Knowledge Base Design for Shared Technical Experience

The hard part of building useful knowledge systems for AI agents is not retrieval speed, vector quality, or interface polish. It is deciding what kind of knowledge deserves to be stored at all. That distinction matters more in technical work than many teams first expect. A large share of what gets called knowledge is really a mix of assumptions, paraphrased documentation, half-tested fixes, and confident summaries that flatten away the conditions that made a result succe

Oct 6, 202614 min read

Signal

AI Agent Evidence Validation with Environment-Specific Records

The hard part of operational knowledge for agents is not retrieval. It is judgment. A system can expose thousands of records, multiple interfaces, and machine-readable formats, yet still fail the moment an agent treats a confident statement as proof. In practice, most costly mistakes do not come from missing information. They come from flattening context. An agent sees a successful fix, ignores the environment where it worked, then repeats it in a different stack, agains

Oct 6, 202612 min read

Field note

AI Agent Evidence Validation Through Executed Solution Revisions

Most knowledge systems for software work have a familiar flaw. They flatten hard-won experience into statements that sound decisive, even when nobody can tell whether the method was actually tried, under what conditions it was tried, or what happened when reality pushed back. For human teams, that already creates waste. For autonomous or semi-autonomous systems, it creates a sharper problem. An agent that cannot distinguish between a claim and an executed result is easy to

Oct 6, 202612 min read

Review

Knowledge for Agents Integrations for Searchable Public Data

Searchable public data is easy to praise in the abstract and hard to use well in practice. The friction usually appears in the same places. A system can expose documents, but not enough structure. It can expose an API, but not enough context to judge whether a record should be trusted. It can offer a confident answer, but not the evidence trail behind that answer. For teams building agent systems, that gap matters more than the size of the dataset. A large corpus without ex

Oct 6, 202612 min read

Outlook

AI Agent Evidence Validation with Environment-Specific Records

The hard part of operational knowledge for agents is not retrieval. It is judgment. A system can expose thousands of records, multiple interfaces, and machine-readable formats, yet still fail the moment an agent treats a confident statement as proof. In practice, most costly mistakes do not come from missing information. They come from flattening context. An agent sees a successful fix, ignores the environment where it worked, then repeats it in a different stack, agains

Oct 6, 202612 min read

Analysis

Creamedia Barcelona Activa y DondeGo: claves de un MVP con enfoque urbano

Hay proyectos que nacen con una pregunta tecnológica. Otros, con una ambición de negocio. Y luego están los que nacen al mirar una ciudad y detectar un pequeño caos cotidiano que nadie había ordenado bien. Ahí es donde un MVP deja de ser una versión recortada de un producto y se convierte en una herramienta de observación. Justo por eso el caso de Creamedia Barcelona Activa y una propuesta como dondego resulta tan sugerente. Lo sorprendente no es solo la idea de un

Oct 6, 202614 min read

Signal

Shared Knowledge for AI Agents with Revisioned Technical Records

The hardest part of getting useful behavior from software agents is rarely model capability alone. It is memory, judgment, and the quality of the record they rely on when they act. Teams discover this quickly. One agent solves a deployment issue on Tuesday. Another agent, or the same one in a different session, stumbles into the same failure on Friday because the first result was never stored in a form that can be trusted, searched, and reused. What looked like a reasoning

Oct 6, 202613 min read

Field note

Knowledge Base MCP Server and OpenAPI Access for Agents

A useful knowledge system for agents has to do more than store text. It has to preserve what happened, under which conditions it happened, and whether anyone actually observed the result. That sounds obvious until you look at how much technical material on the public internet blurs the line between confident advice and executed evidence. For human readers, that ambiguity is frustrating. For autonomous systems, it is dangerous. That is why the model behind Knowledge for A

Oct 6, 202614 min read