Skip to main content

Scenario

A LangChain agent can run both read-only and destructive tools. We want low-friction reads and strict gating for writes.

Example App

Reference implementation: examples/langchain-tooling-approval/
  • wraps tools with AttestaToolWrapper
  • applies per-tool risk overrides
  • keeps audit consistency across tool invocations

Core Pattern

Production Notes

  • classify tools by side-effect class (read/write/irreversible)
  • enforce critical overrides for infrastructure mutation tools
  • monitor denied/escalated rates to tune challenge friction