•SYSTEM DESIGN

Anthropic System Design Questions

Every system design problem candidates reported at Anthropic between September 2025 and September 2026, most-asked first. Each one links to a full solution.

Problems

15

Candidate reports

26

Asked more than once

6

start here

Question type

15 HLD

Topics Anthropic tests

Start Anthropic System Design Interview →
✅Track which Anthropic problems you have solved
Open tracker →
1

Design a Resilient Chat System

5 reportsHLDAdvancedReal-timeMessagingDistributed Systems

Design a real-time chat system like WhatsApp or Slack supporting one-to-one and group conversations (and, for Slack variants, workspaces, channels and threaded replies). Users send and receive messages with low latency, see…

last seen Jul 2026·also asked at 8 other companies

Also worded as: Design a One-on-One Chat Service · Design a One-to-One Chat System +2

2

Design Large Model-Weight Distribution to GPU Workers

4 reportsHLDAdvancedAI / MLDistributed SystemsStorage

Design a system that distributes very large immutable model-weight artifacts (hundreds of GB, e.g., 500 GB) from a source to thousands of GPU workers as quickly and reliably as possible, for example when deploying a new model…

last seen Aug 2026

Also worded as: Design Peer-to-Peer Model Distribution Under a Shared Link Cap · Deploy a Large Model to GPU Workers +1

3

Design a Dynamically Batched Inference API

2 reportsHLDAdvancedAI / MLConcurrencyScheduling

Design a high-concurrency LLM inference API that dynamically batches compatible requests onto a limited GPU pool. Individual requests arrive continuously; the batching layer groups them (same model, compatible parameters) into…

last seen Jul 2026

Also worded as: Design an LLM Request Batching System

4

Design a Prompt Sharing Product

2 reportsHLDIntermediateAI / MLSecurityDatabases

Design a prompt-sharing product where users publish prompts privately, to specific people, or publicly; others can view, run, fork or remix them. Requirements: stable immutable versions, a permission model (owner, editor, viewer,…

last seen Jul 2026

Also worded as: Design a prompt-sharing platform

5

Design a Concurrent Image Processing Service

2 reportsHLDIntermediateData PipelinesSchedulingStorage

Design an image-processing job service (e.g., resize, filter, or run a model on images) that starts with one worker and evolves safely to many concurrent processors and large batch jobs of millions of images. Requirements: job…

last seen Jul 2026

Also worded as: How would you scale batch image pipelines?

6

Design a prompt playground

2 reportsHLDIntermediateAI / MLFrontendStorage

Design a web-based prompt playground (like the OpenAI or Anthropic console) for developers and prompt engineers. Users write prompts, pick a model and generation parameters, run the prompt and watch the response stream in real…

last seen May 2026·also asked at 1 other company

Also worded as: Design An AI Playground For Very Large Prompts

7

Design Telemetry Ingestion and Reconcile Metric Names

HLDAdvancedObservabilityData PipelinesStorage

Design an internal metrics monitoring platform like Datadog or Prometheus. Agents on hosts and services emit metrics (counters, gauges, histograms with tags); the system ingests millions of data points per second, stores them as…

1 report·last seen Aug 2026·also asked at 6 other companies
8

Find a Distributed Mode Efficiently

HLDIntermediateAlgorithmsDistributed SystemsData Pipelines

Design an exact distributed algorithm to find the mode (most frequent value) of a huge multiset partitioned across many workers, without shipping every raw item to one machine. Discuss hash-partitioning values so each value's…

1 report·last seen Jul 2026
9

Design a Distributed Rate Limiter

HLDIntermediateRate LimitingDistributed SystemsAPI Design

Design a distributed rate limiter that protects APIs by limiting requests (or consumed units such as LLM billing tokens or storage quota) per user, API key, tenant, or IP. It must support configurable rules (e.g., 100…

1 report·last seen Jun 2026·also asked at 12 other companies
10

Design Instagram (Feed, Photos, and Friend Recommendations)

HLDAdvancedDistributed SystemsMediaSearch

Design the home feed of a social network like Instagram or Twitter. Users create posts (text, photos, video), follow other users, and open a personalized feed of recent posts from people they follow, possibly mixed with global or…

1 report·last seen Jun 2026·also asked at 5 other companies
11

Scale Duplicate File Detection

HLDIntermediateStorageAlgorithmsDistributed Systems

Design a system that finds duplicate files across a very large file system or storage fleet (billions of files, petabytes). Return groups of files with identical content. Discuss a cheap-first filtering pipeline (group by size,…

1 report·last seen May 2026·also asked at 1 other company
12

Review and Improve a Flawed Design Document

HLDIntermediateDistributed SystemsSecurityObservability

You are given an existing architecture or design document (for example Client -> DNS -> Load Balancer -> Application Service -> Database, plus a call to a third-party API) that contains omissions and unsafe assumptions. Review…

1 report·last seen Apr 2026·also asked at 2 other companies
13

Design guardrails and fallback for LLM reliability

HLDIntermediateAI / MLSecurityDistributed Systems

Design the safety and reliability layer around an LLM-powered production system. Include input validation and prompt-injection detection, output validation (schema checks, toxicity and PII filters), policy enforcement, fallback…

1 report·last seen Feb 2026
14

Design a distributed web crawler

HLDAdvancedDistributed SystemsStorageSearch

Design a distributed web crawler that starts from seed URLs and crawls about 10 billion pages (or all images reachable from given root URLs), with periodic recrawls. It must avoid fetching the same URL twice, obey robots.txt and…

1 report·last seen Jan 2026·also asked at 5 other companies
15

Optimize HTTP requests for speed and limits

HLDIntermediateConcurrencyAPI DesignRate Limiting

You need to make a very large number of HTTP requests to an external API as fast as possible while respecting its rate limits. Design the client: concurrency (async I/O, connection pooling), client-side rate limiting (token…

1 report·last seen Dec 2025

Duplicate reports of the same problem are merged and counted.

Practice with a Mock Interview

Apply these questions in a live system design mock interview with InterviewSkool's AI interviewer.

Start System Design Interview →

Frequently Asked Questions

What system design questions does Anthropic ask?

Candidates reported 15 distinct system design problems at Anthropic between September 2025 and September 2026, including Design a Resilient Chat System, Design Large Model-Weight Distribution to GPU Workers, Design a Dynamically Batched Inference API.

How to prepare for Anthropic system design interview?

Start with the Anthropic problems reported most often, work through each full solution, then practice explaining a design end to end under time pressure in a mock interview.

What is the difference between HLD and LLD at Anthropic?

HLD (High-Level Design) focuses on system architecture, scalability, and component interactions. LLD (Low-Level Design) dives into class diagrams, API contracts, and database schemas. Anthropic tests both.