> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.adid.dev/llms.txt.
> For full documentation content, see https://docs.adid.dev/llms-full.txt.

# Agent Autonomy Ladder

**Used in:** §6.6 Trust Scores & Autonomy Levels
**Audience:** Agent Operator
**IA ID:** D10

```mermaid
graph LR
  L1["L1 Observer (read only, no side effects)"] --> L2["L2 Suggester (proposes actions, human approves)"]
  L2 --> L3["L3 Assistant (executes pre-approved templates)"]
  L3 --> L4["L4 Agent (autonomous within capability scope)"]
  L4 --> L5["L5 Delegate (can delegate to sub-agents, full chain authority)"]

  classDef low fill:#dcfce7,stroke:#15803d
  classDef mid fill:#fef9c3,stroke:#b45309
  classDef high fill:#fecaca,stroke:#b91c1c
  class L1,L2 low
  class L3 mid
  class L4,L5 high
```

**Reading guide:** Each step right increases capability scope and risk. L5 is the only level that can issue further IBCTs to sub-agents.

***