Skip to main content
Artifacts are what a store actually knows: the clean, structured output Clara consolidates from your interviews and sources, and what AI clients draw on. You don’t usually edit them by hand, you refine them through Work with Clara. Every artifact has a purpose (what it is for) and a format (how it is stored and shown). Clara proposes a starting set when you scope the project, typically a brief, a project plan, a mental map, general knowledge, playbooks and a library description, and you add custom artifacts for anything your methodology needs, such as a process blueprint or a business rules table. The purposes vary by project; the formats are fixed.

​
Formats

  • Document: free-form text with sections and lists. Used by the brief, project plan, general knowledge and library description.
  • Concept map: a graph of domains, classes and relations. Used by the mental map.
  • Playbook list: an ordered set of stepped workflows.
  • Design template list: a collection of output templates.
  • Process diagram: a BPMN 2.0 diagram, the usual format for a process blueprint.
  • Table: rows and typed columns, the usual format for business rules or any curated reference list.
Artifacts are versioned and keep the evidence they were built from. Where two contributors disagree, both versions are kept and flagged. When an AI client consumes the store through the Clarifeye skill, or when you use Chat or Task inside Clarifeye, these artifacts guide the answers. Keeping them accurate, through Work with Clara and signals, is what keeps the store trustworthy.