Design a Scalable and Safe Agentic System

Quick Overview

Design a scalable service where an AI agent plans work and invokes approved tools without bypassing deterministic controls. Address durable execution, authorization, prompt injection, human approval, idempotency, auditability, budgets, and loop termination.

Design a Scalable and Safe Agentic System

Company: Google

Role: Software Engineer

Category: ML System Design

Difficulty: hard

Interview Round: Technical Screen

Quick Answer: Design a scalable service where an AI agent plans work and invokes approved tools without bypassing deterministic controls. Address durable execution, authorization, prompt injection, human approval, idempotency, auditability, budgets, and loop termination.

|Home/ML System Design/Google
Google logo
Google
Jul 10, 2026
hardSoftware EngineerTechnical ScreenML System Design
108
0
Loading...

Submit Your Answer to Earn 20XP

Sign in to leave a comment

Loading comments...