liveBook · Manning

Dependency ladder

As explained in AI Governance

A dependency ladder is an ordering of generative AI exposure factors in which lower factors are prerequisites for higher factors to matter.

A dependency ladder orders generative-AI exposure factors by prerequisites, not severity: lower factors must be present for higher factors to matter. Every system has environmental risk, and every LLM application adds another baseline. section 4.2

As exposure rises, additional capabilities create new paths to harm:

  • Factor 3 enables AI-specific attacks such as prompt injection; Factor 4 data access can amplify them by exposing sensitive information. section 4.2
  • Factor 5 lets the model take actions that can change or destroy data; Factor 6 agency adds multistep goal pursuit, typically involving lower layers. section 4.2

From chatbot to autonomous agent

A simple chatbot involves Factors 1–3; an action-enabled assistant adds Factors 4 and 5. A fully autonomous agent may handle untrusted input, access sensitive systems, take consequential actions, and rely on unaudited integrations. section 4.2

Figure 4.2 Security Risk Factors. Each additional factor compounds the risk.

Use the figure to see how adding exposure factors compounds risk. section 4.2

How AI Governance covers it

How deep it goes
Explains factor dependencies and deployment examples, while explicitly distinguishing the ladder from a severity ranking.
Examples
Contrasts a simple chatbot, an action-enabled assistant, a closed system, and a fully autonomous agent.
What you can do after
Evaluate a deployment by identifying applicable factors and recognizing which higher-level risks depend on lower factors.
How it connects
Connects prompt injection with data access, consequential actions, and autonomous-agent agency.

This explainer was generated by Manning's knowledge graph from the text of AI Governance. The section links point to the parts of the book it draws on.