17 docs tagged with "context-phase"

Agents are specialized AI profiles — not generic instances. Each one has a defined role, clear limits, and a protocol for when information is insufficient.

The five failure patterns that derail Context Phase: Over-Context, the Silent Agent, Aspirational Context, the Broken Chain, and Frozen Context.

How the Solution Brief translates into AI-processable context: the transition from human thinking to Context Phase.

When the Gate Review is complete, the team has a system of Agents, Rules, and Skills. The construction phase doesn't start with a briefing — it starts with context.

Context Phase effort is measured by the quality and completeness of the Rules, Agents, and Skills system, not by calendar time invested.

Context Phase is complete when the outputs of the system are recognized as correct by stakeholders — not when the documents look polished.

Operational guide: step-by-step process, context system anatomy, artifacts, gate review, anti-patterns, and effort estimates.

Agents, Rules and Skills: the operating system of the AI project. The discipline of translating human thinking into a system that AI can process.

Rules are the norms that apply to the entire project. They are what turns a collection of independent Agents and Skills into a coherent system.

Skills are the 'what gets done concretely.' Self-contained work units with all the context an Agent needs to complete them without ambiguity.

The complete structure of the context system: project-context.md template, PRD sections, Architecture Document, Agent definitions, and Skill specifications.

Six artifacts that form the operating system of the AI project: project-context.md, Agent Definitions, PRD, Architecture Document, Story Files, and Decision Log.

A prompt is a point-in-time instruction. Context is an information architecture composed of Agents, Rules, and Skills. Confusing the two is the most common mistake.

A structured process with five steps: establish Rules, design the Agent chain, generate strategic documents, decompose into Skills, and validate through outputs.

The team begins thinking about how AI will process the solution, without writing a single line of context.

The Context Engineer is the architect of the Agents, Rules, and Skills system. Not a prompt engineer — a system designer who works across three dimensions simultaneously.

The gap between what a team understands and what AI can process is the context. Context Phase is the discipline of crossing it.