Mock system design interview at Anthropic

A live 45-minute round on a question reported in Anthropic interviews, run by an AI interviewer that asks one thing at a time, probes what you say, looks at your whiteboard, and weighs what that round is reported to weigh. It ends with a debrief: a score, what was strong, what was missing.

your question

Design Slack

Real-time team messaging: channels, DMs, presence, history and search for millions of concurrent users.

You will not see the requirements, the numbers or the design before you start. That is the point.

Walk through it first

What the Anthropic round is reported to look like

A 50–55 minute round, often on infrastructure behind an AI product rather than a consumer app. Two shapes are reported: design from scratch, and reviewing a design document and improving it.

What it weighs

Decomposition: breaking an open problem into parts that can be reasoned about separately
Scale reasoning under real constraints, especially scarce and expensive capacity
Failure modes, overload behaviour and what degrades first
Driving the conversation yourself at staff level, rather than waiting to be prompted

The common mistake

Most of the questions reduce to ordinary distributed systems: queueing, batching, backpressure. Candidates who reach for model internals instead of the infrastructure answer tend to drift.

From public interview guides and candidate reports, and Anthropic’s own interview guidance where it publishes any. Not endorsed by Anthropic. The interviewer is an AI running in that style; it is practice, not a prediction.

Start the round

Timed · 45 minutesInterview conditions. The AI interviewer owns the clock; the AI Mentor is off.With the AI Mentor · untimedNo clock, and an AI Mentor beside you to ask when you are stuck.

The interviewer’s opening question is free. Answering it is part of Pro. See an example round and its debrief →

The 11 questions this round draws from

Each is reported in Anthropic interviews. Pick one to sit, or read its reference design and walk through a strong answer first.

Design SlackReal-time team messaging: channels, DMs, presence, history and search for millions of concurrent users.
drawn
Design a News FeedThe home timeline of Twitter, Instagram or Facebook: posts from people you follow, ranked, fresh, and fast for hundreds of millions of users.
Design an LLM Inference ServiceServe a large language model behind an API: queue the requests, batch them onto scarce GPUs, stream tokens back, and keep every accelerator busy without blowing the latency budget.
Design ChatGPTAn AI chat assistant for 100 M weekly users whose streamed answers survive dropped connections, call tools mid-answer, and share scarce GPUs across tiers.
Design a Distributed CacheA Redis-like cache as a service: hundreds of nodes, terabytes of memory, sub-millisecond gets, and a cluster that survives losing a machine mid-request.
Design a Web CrawlerFetch billions of pages a month politely, discover new links, skip duplicates, and keep the copy fresh without getting the crawler banned.
Design a Rate LimiterA distributed service that decides, in under a millisecond, whether a request from a client is allowed under its quota.
Design a Large File Distribution SystemGet a 200 GB checkpoint from one origin onto 10,000 machines in five data centres within minutes, under capped links, verifying every byte.
Design a RAG SystemAn assistant that answers employees’ questions from their company’s documents, with citations, only from what each user may open, minutes after edits.
Design GitHub CopilotInline AI code suggestions for 10 M developers, shown within 300 ms of a pause in typing, when most requests are never used.
Design a Vector DatabaseA managed vector database: 10,000 tenants, 20 B vectors, filtered top-k in under 50 ms at 0.95 recall, and writes searchable in seconds.

Other companies: Google · Meta · Amazon · OpenAI · Microsoft · Uber · DoorDash · Netflix