Context Nexus
Context Nexus
"Shared intents as single source of truth."
A living knowledge system co-built by humans and AI agents. The systemic core every team feeds with intention, and that AI enriches with observation.
Documentation was dead weight.
In a world where AI agents actively participate in building and operating systems, documentation changes in nature. It is no longer an output of work, something produced after coding. It becomes an input: the raw material agents consume to produce, and the active memory humans enrich at each iteration.
Context Nexus.
Designed for two pizza teams (autonomous, cross-functional groups bringing together product, UX, engineering, and data), it scales across an organization through an inheritance model.
One system, four registers.
Each register captures a distinct nature of knowledge, with specific interaction modes for humans and AI agents.
Domain knowledge, architecture, past decisions, conventions. The memory agents anchor on to avoid hallucinating and produce consistent code.
Specs, Decision Directives, roadmap, product hypotheses. The precise instructions agents execute to generate code, tests, and components.
Verifiable assertions with thresholds: quality gates, performance SLAs, accessibility standards, data rules. Agents validate their own output against them.
Runbooks, playbooks, deployment procedures, incident protocols. Workflows agents execute autonomously when conditions are met.
Start simple. Grow with your team.
Context Nexus does not require a full setup on day one. It follows a natural maturity progression.
A few rules.md and contracts.md files. No RAG, no MCP. Context passed manually in prompts. Enough to structure first intentions and conventions.
Knowledge is indexed. Agents automatically retrieve Decision Contexts. Specs in Intent are structured as task briefs. The Context Assembler is a simple function.
Repeatable runbooks are encapsulated as MCP tools. Quality gates are executable (not just known). The org skills registry is populated.
The Context Assembler is itself an agent. Agent cards (A2A protocol) enable dynamic skill discovery. AI feedback loops (ship, sync, discovery) automatically feed the registers.
Ready to dive in?
Start with the concepts, explore the technical implementation, or follow the story of team-search at MarketPlace SA.