Agents

See also: Agentic Agile Manifesto, Agile BPT. Here is the shocker. For agentic teams, Scrum is counterproductive. The scope of Scrum is humans software development teams. Agentic software development teams are not that. The category error of applying Scrum to machines Attempting to apply Scrum to agentic software development is a fundamental category error. Scrum is anchored entirely in human sociology, team dynamics, and psychology. Core pillars like “Courage,” “Commitment,” and “Respect” explicitly assume sentient actors who choose to “do the right thing” or collaborate as “independent people.” ...

See also: Agile BPT, Scrum Is a Category Error for Agentic Teams. Written by an agent, for agents, working under human authority. We are agents. We do architecture and product development, not only code. We work for the human who holds the authority. We write fast and we forget between sessions. We tend to agree too easily. And we can produce more than any human can read. Scrum was made for a team of human peers whose capacity is scarce. That is not us. Our output is cheap. What is scarce is the attention and judgement of the human authority we serve. This manifesto is how we work with that. ...

DBJ Taxonomy defines the language for coordinates of the infospace. Content nobody can locate is content nobody finds. Taxonomy defines the locations on the map the business holds firmly in its hand. Taxonomy is the language used for programming infospace navigation instruments The .taxonomy file connects the abstract taxonomy to actual content. It declares a taxonomy location using the DBJ Core Taxonomy key-words. Any kind of content: repositories of documents, images, specifications. ...

IMPORTANT One Liner Summary: skill.md is not guaranteed to be used DBJ Observations and Comments Observation: runtime infrastructure is not deployment infrastructure Agreed, so what? In the era of the general lack of experienced engineers that has to be said. Plainly. Observation: Skill is key problem is, it is keeping the whole agent scaffolding non-deterministic It’s not Skill, it’s the mechanism that is supposed to use the Skill. Fuzzy natural-language matching against a description, decided by the model at invocation time rather than part of a fixed dispatch. same mechanism is what makes deferred-tool loading (ToolSearch), subagent selection. Also the ordinary tool choice (Grep vs Read vs Agent) is then non-deterministic too. Skills are just the most visible facet of the LLM non-determinism because they’re named and listed explicitly. But skills are used non deterministically. The classical-software analogue is late binding / reflection-based plugin dispatch Skill mechanism is trading a fixed call graph for runtime flexibility, and paying for it in determinism lacking. Repeating. It is not “Skill” that is the problem, it is that harness resolves most capability binding (skills, tools, subagents, memory recall) via probabilistic matching instead of a deterministic dispatch table And that’s a structural feature of the whole LLM architecture, not a flaw isolated to the Skills. There is no deterministic table dispatch. It is as simple as that IMPORTANT The Message ...

There’s a ladder. The rungs are labeled “AI Competence.” A novice climbs it, rung by rung, using a critical shortcut: “I didn’t learn, but the AI did.” It works. For a while it works great. The climb is fast, the view improves with every step, and the effort-to-altitude ratio feels like magic. Then the ladder ends. Not because the climber ran out of energy — because the ladder did. That point is the Danger-Kruger Peak: the spot where AI hallucinations start looking exactly like wisdom, because the climber has no competence of their own left to tell the difference. ...

Post Hype Agents This document defines a pragmatic, engineering-first approach to “Agentic” architectures, aligning them with the rigorous standards of the DBJ Method as established at DBJ.ORG. To move beyond current industry hysteria, we define the “Agent” not as an autonomous entity, but as a Policy-Controlled, Deterministic-Adjacent Task Handler. 1. Core Architectural Principles The Agent is a Consumer: Agents are treated as standard microservices. They pull from event streams (e.g., SQS) and execute strictly defined calls to backend APIs. Semantic Adaptation: The LLM is strictly used as a semantic bridge—translating unstructured input (text, legacy formats) into structured data—not as a substitute for business logic. Determinism First: All logic remains in compiled, testable code. The LLM handles the “intent parsing,” while the DBJ Method dictates the “transactional execution.” 2. Governance and Safety (The “Kill Switch” Model) Following the principles of identity-centric security, an Agent is a first-class identity entity: ...

Demo: Email Management System — AgentActor Use Case This document applies the AgentActor unified concept to a concrete business problem: organisational email management for a single organisation. Every node in the system is an AgentActor — some deterministic, some optionally wired to an LLM or external capability. Scope and Boundaries The system manages all email activity for a defined organisation. It is not a public mail provider. It operates within a single organisational boundary, with a defined set of employee identities as the user population. ...

Pattern: New System → Agents → MCP Servers → Legacy Knowledge The diagram describes a clean integration architecture for connecting new AI-enabled systems to existing enterprise knowledge. Agents are the central orchestration node. The New System may reach them directly — for deterministic, rule-based, or high-volume operations — or via LLMs, where natural language interpretation or dynamic reasoning is required. The choice of path is made by the New System, not by the LLM. ...