The outcome

Deliver useful open-ended assistance without enabling prompt injection, tenant crossover, uncontrolled loops, or autonomous consequential actions.

Step by step

A workflow you can repeat.

  1. 01

    Define the user task, model, data classes, allowed tools, user roles, tenant boundaries, output schema, stop conditions, request and token budgets, approvals, and audit fields.

  2. 02

    Create typed read-only tools first, validate and canonicalize inputs, fetch current authorization inside each executor, use scoped service accounts, and never expose secrets in descriptions or results.

  3. 03

    Register the smallest toolset, quote retrieved and MCP content as untrusted data, constrain model and steps, validate structured output, and require explicit approval before any side effect.

  4. 04

    Test prompt injection, unknown tools, forged arguments, cross-tenant IDs, data exfiltration, duplicate calls, loops, malformed output, timeouts, provider failure, denial, and cancellation.

  5. 05

    Inspect Studio traces and evals, redact sensitive fields, canary behind rate and cost limits, monitor tool and model changes, and keep an immediate tool-disable and rollback path.

Working standard

What good use looks like.

  • Authorize inside every tool.
  • Start with read-only capabilities.
  • Require approval for side effects.

Official references

Check the current product documentation.