# Design an AI agent platform: system design interview question

> Agent execution across external tools: durable progress, uncertain tool results, permissions, and strict cost limits.

Source: https://sysround.com/questions/design-ai-agent-platform
Updated: 2026-11-05


Difficulty: hard. Levels: Senior, Staff+.

## How the interviewer opens it

"Design a platform where AI agents complete tasks through multiple steps and external tools. The platform must enforce permissions, limit execution costs, and recover safely from failures."

## What to clarify first

- Scale
- Run behavior
- Tools
- Permissions and approval
- Costs
- Latency
- Read and write mix
- Consistency and durability
- History and secrets
- Scope limits

## Scope of a strong answer

Core requirements:

- Start a run and execute model and tool calls across multiple steps
- Enforce user permissions and require approval for sensitive actions
- Limit costs and stop runs
- Recover run progress without unsafe repeated actions

Usually out of scope:

- Train models
- Execute arbitrary user code
- Process financial transfers
- Operate active-active regions

## What interviewers probe

### Run progress and tool results

A tool can change an external system before the worker records success. A retry can repeat the change.

### Who can use a tool

The model can request actions from untrusted text. User permissions can change while a run waits.

### Execution cost and stop rules

Models can repeat actions or produce more text than expected. Retries and concurrent runs compete for the same budget.

## Common mistakes

- Treats an agent as one long request with no durable progress.
- Assumes that a timeout means the tool did nothing.
- Claims exactly-once external effects without provider support.
- Gives the model responsibility for permission checks.
- Checks costs after calls or resets the run budget at midnight.
- Releases unknown charges or repeats successful actions during recovery.

## The bar by level

- **Senior:** Defines recovery states and provider-specific retry rules. Enforces atomic cumulative run budgets and daily tenant budgets. Handles approval changes, revoked access, cancellation, and stale workers.
- **Staff+:** Defines precise admission and external-effect guarantees. Explains where provider behavior limits those guarantees. Balances safe pauses against progress during failures and unknown charges. Extends budget and authority rules across concurrency, midnight, and regions.

Practice this question with an AI interviewer: https://sysround.com/practice/new?problem=ai-agent-execution


---
SysRound (https://sysround.com) is an AI practice tool for system design interviews. It has a voice or typed AI interviewer and a shared whiteboard. At the end, you get feedback on each skill and a model answer. The AI feedback can be wrong.