•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
Design a Resilient Chat System
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…
Also worded as: Design a One-on-One Chat Service · Design a One-to-One Chat System +2
Design Large Model-Weight Distribution to GPU Workers
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…
Also worded as: Design Peer-to-Peer Model Distribution Under a Shared Link Cap · Deploy a Large Model to GPU Workers +1
Design a Dynamically Batched Inference API
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…
Also worded as: Design an LLM Request Batching System
Design a Prompt Sharing Product
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,…
Also worded as: Design a prompt-sharing platform
Design a Concurrent Image Processing Service
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…
Also worded as: How would you scale batch image pipelines?
Design a prompt playground
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…
Also worded as: Design An AI Playground For Very Large Prompts
Design Telemetry Ingestion and Reconcile Metric Names
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…
Find a Distributed Mode Efficiently
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…
Design a Distributed Rate Limiter
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…
Design Instagram (Feed, Photos, and Friend Recommendations)
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…
Scale Duplicate File Detection
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,…
Review and Improve a Flawed Design Document
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…
Design guardrails and fallback for LLM reliability
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…
Design a distributed web crawler
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…
Optimize HTTP requests for speed and limits
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…
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.