liveBook · Manning

Sub-agent isolation

As explained in AI Governance

Sub-agent isolation separates agents or agent workflows through distinct permissions, credentials, or execution boundaries.

Sub-agent isolation limits prompt-injection risk by separating work involving untrusted external content from work involving sensitive internal data, using distinct permissions. section 4.8.8

Separate sessions or subgraphs so each workflow has only the access it needs:

  • Give a research agent web access but no internal-system access; give an analysis agent internal read access but no outbound network access. section 4.8.8
  • In LangGraph, assign different credentials to subgraphs; AWS Bedrock multi-agent orchestration offers per-agent IAM scoping. section 4.8.8

How AI Governance covers it

How deep it goes
Defines a permission-separated workflow and names implementation options without providing code or configuration steps.
Examples
Uses web research followed by internal-data analysis, with LangGraph subgraphs or Bedrock agent scopes.
What you can do after
Apply the pattern through LangGraph subgraphs with distinct credentials or Bedrock per-agent IAM scoping.
How it connects
Connects prompt injection, access control, credentials, orchestration frameworks, and IAM.

Related concepts

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.