Mock system design interview at OpenAI

A live 45-minute round on a question reported in OpenAI 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 OpenAI round is reported to look like

45–60 minutes, frequently on the infrastructure behind model serving, data pipelines or developer-facing APIs.

What it weighs

Latency and cost tradeoffs under expensive, constrained compute
Streaming, batching and backpressure on the request path
Safety, abuse and quota mechanics as part of the design, not an afterthought
Pragmatism: what you would actually ship first

The common mistake

Treating an AI product as a standard CRUD app. The interesting constraints are capacity, streaming and cost per request.

From public interview guides and candidate reports, and OpenAI’s own interview guidance where it publishes any. Not endorsed by OpenAI. 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 8 questions this round draws from

Each is reported in OpenAI 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 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 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 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: Anthropic · Google · Meta · Amazon · Microsoft · Uber · DoorDash · Netflix