Klarity organizes operational intelligence into three layers. Each maps to a distinct set of MCP tools and is best for a different kind of question.Documentation Index
Fetch the complete documentation index at: https://developers.klarity.ai/llms.txt
Use this file to discover all available pages before exploring further.
| Layer | What it contains | Example questions |
|---|---|---|
| Process Index | Hierarchy, versions, steps, policies, dependencies, observations | ”How does our vendor onboarding work?” |
| Context Graph | Entities, relationships, communities, claims | ”What systems does the finance team depend on?” |
| Artifacts | Documents, videos, screenshots, session timelines | ”Find the latest SOX compliance checklist.” |
How they fit together
The Process Index and Process observations are higher-order abstractions built on top of the Context Graph — the graph supplies the raw entities and relationships, and the Process Index reshapes them into a hierarchy of processes the agent can reason about. For most agent work, prefer the Process Index; reach for the Context Graph directly only when a question is purely relational and the index can’t answer it. The most useful answers still chain across all three layers in a single session:“Give me the full picture on month-end close — process hierarchy, key entities, recent observations, and the most relevant docs.”That single prompt fans out into a process search, hierarchy traversal, knowledge graph entity lookup, and artifact search. Ten-plus tool calls, orchestrated automatically, answered with grounded evidence.
When to start at each layer
- Start at the Process Index when the user names a workflow, team, or business outcome — this is the default for almost every question.
- Start at Artifacts when the user names a document, screenshot, or recording.