> ## Documentation Index
> Fetch the complete documentation index at: https://docs.idemeum.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Architecture

> Endpoint Care architecture, design, and terminology.

# How Endpoint Care works

```mermaid theme={null}
%%{init: {"flowchart": {"useMaxWidth": false}, "themeVariables": {"fontSize": "16px"}}}%%
flowchart TD
    A["1 · Understand"] --> M{Skill match?}
    M -- yes --> B["2 · Plan"]
    M -- no --> T[Triage: diagnose, categorize, route]
    B --> C["3 · Check — security gates"]
    C --> D["4 · Execute"]
    D -.->|risky step| G[Preview + consent]
    G -.-> D
    D --> E["5 · Report — ticket with full trail"]
    T --> E
```

Every request follows the same lifecycle:

1. **Understand.** The employee types a request (or clicks a quick action). The agent interprets the intent and selects the matching skill. If nothing matches, the run becomes a triage run.
2. **Plan.** The agent reads the skill and produces an explicit, ordered plan of tool calls for this specific goal.
3. **Check.** The plan passes through the guardrail pipeline: intent screening, plan validation against the skill's allowed tools, and central policy evaluation.
4. **Execute.** Steps run one at a time on the device. Diagnostic steps are read-only. Corrective steps pause at gates: a preview of exactly what will change, and a consent prompt the user must approve.
5. **Verify and report.** The agent confirms the outcome (including asking the user), then produces a summary. Every run, resolved or not, is recorded as a ticket with the full diagnostic trail.