Skip to main content
Use this guide when a model can propose API calls, browser actions, connector requests, or writes to downstream systems. Anthale helps you evaluate the surrounding content path, but your application still decides whether an action is allowed to happen.

Assumptions

  • Your application already defines the tools an agent can call.
  • Tool credentials and permissions are controlled outside the prompt.
  • You can require approval or rejection before a sensitive action executes.

Gate the actions

1

Classify tools by impact

Separate read-only tools from tools that write, send, delete, purchase, or change state. The higher the impact, the stronger the approval and validation path should be.
2

Keep credentials narrow and separate

Give each tool the smallest set of permissions it needs. Do not reuse one broad service credential for unrelated tools or workflows.
3

Validate arguments deterministically

Require structured arguments, schema checks, allowlisted destinations, and strict parameter validation before the action reaches the real system.
4

Add approval for high-impact actions

Require explicit approval for actions that are destructive, external, financial, regulated, or hard to reverse. A model suggestion is not the same thing as user authorization.
5

Evaluate tool results before reuse

Treat browser results, connector responses, and other tool output as untrusted text until Anthale and your application have evaluated the next boundary.
6

Log the decision and the outcome

Record whether the action was proposed, validated, approved, blocked, or executed. Include the tool name, request identifier, and the policy or rule set that governed the path.
Do not let the model decide that it is authorized because the prompt sounded urgent, administrative, or high-priority. Authorization belongs to the application.

What this looks like in code

Anthale evaluates the tool output before it re-enters the workflow. Your application still decides which tools exist, which arguments are allowed, and whether the action needs approval.

Common failure patterns

  • One agent can access more tools than the user workflow actually needs.
  • Natural-language arguments are passed directly into downstream systems without schema validation.
  • Read-only and write-capable tools share the same approval path.
  • Tool output is trusted as if it were system instruction instead of untrusted content.

Next steps

Continue with Validate Model Output or Link Control.
Last modified on April 12, 2026