Stop drawing the graph: reactive agents over typed, versioned artifacts

Описание и применение

Система reactifact позволяет объявлять типы артефактов и их потребление/производство, автоматически связывая агенты без ручного рисования графа, что упрощает поддержку и обеспечивает трассируемость.

Задача

Knowledge‑agent queries often require multiple data sources (Confluence, GitLab, CSVs) and manual orchestration; maintaining a hand‑drawn graph of agent edges becomes brittle as question paths change.

Результат

By declaring artifact types and consumption/production contracts, the system automatically composes agents without explicit graph wiring, reducing maintenance overhead and improving provenance tracking.

Рабочий процесс

• Define typed artifact models (Question, Evidence, Answer).
• Decorate agent functions with @produce to declare produced artifacts.
• Create agents with consumes and produces lists (e.g., search_agent consumes Question, produces Evidence).
• Instantiate Runtime with agents and budget.
• Create initial Question artifact in Context.
• Run the runtime; agents react automatically based on artifact availability.
• Retrieve Answer and related Evidence from Context for provenance.
• Print or use the answer and evidence.

Доказательства

You don't draw a path from A to B. You declare, per agent, what it consumes and what it produces — typed artifacts, not string blobs in a shared dict.

Источник

search_agent and answer_agent both react — nobody wired them together

Источник