system-design-game/data/levels.json

[
    {
        "id": "url-shortener",
        "name": "URL Shortener",
        "description": "Scale your URL shortener to handle traffic spikes and ensure high availability.",
        "targetRps": 1000,
        "durationSec": 180,
        "maxP95LatencyMs": 150,
        "requiredAvailabilityPct": 99.9,
        "mustInclude": ["database", "loadBalancer"],
        "encouragedComponents": ["cache"],
        "hints": ["Consider caching and horizontal scaling."],
        "interviewerRequirements": [
            "The service should handle traffic spikes gracefully.",
            "Shortened links should resolve quickly under moderate load.",
            "Ensure no single point of failure in the redirect path."
        ],
        "functionalRequirements": [
            "Must include a database and a load balancer",
            "Encouraged to add a cache in front of the database"
        ],
        "nonFunctionalRequirements": [
            "Target RPS: 1000",
            "Max P95 latency: 150ms",
            "Required availability: 99.9%",
            "Simulation duration: 180 seconds"
        ]
    },
    {
        "id": "chat-app",
        "name": "Chat App",
        "description": "Support real-time chat across mobile and web, with message persistence.",
        "targetRps": 500,
        "durationSec": 300,
        "maxP95LatencyMs": 200,
        "requiredAvailabilityPct": 99.9,
        "mustInclude": ["webserver", "database", "messageQueue"],
        "encouragedComponents": ["cache"],
        "hints": ["Ensure you decouple frontend from persistence."],
        "interviewerRequirements": [
            "Messages must be delivered in order and reliably across multiple clients.",
            "Frontend and backend should be decoupled via an asynchronous system.",
            "Messages should be persisted with low latency under load."
        ],
        "functionalRequirements": [
            "Must include a webserver, message queue, and database",
            "Encouraged to use a cache to reduce database read pressure"
        ],
        "nonFunctionalRequirements": [
            "Target RPS: 500",
            "Max P95 latency: 200ms",
            "Required availability: 99.9%",
            "Simulation duration: 300 seconds"
        ]
    },
    {
        "id": "netflix-clone",
        "name": "Netflix Clone",
        "description": "Add video transcoding, caching, and recommendations.",
        "targetRps": 1000,
        "durationSec": 600,
        "maxP95LatencyMs": 300,
        "requiredAvailabilityPct": 99.9,
        "mustInclude": ["cdn", "data pipeline", "cache"],
        "encouragedComponents": ["monitoring/alerting"],
        "hints": ["Think about asynchronous jobs and caching strategy."],
        "interviewerRequirements": [
            "Videos should be transcoded into multiple bitrates for adaptive playback.",
            "Popular content should be cached to improve performance.",
            "Users should receive basic recommendations based on view history."
        ],
        "functionalRequirements": [
            "Must include a CDN, cache, and data pipeline (e.g. for processing viewing logs)",
            "Encouraged to include monitoring/alerting for system health"
        ],
        "nonFunctionalRequirements": [
            "Target RPS: 1000",
            "Max P95 latency: 300ms",
            "Required availability: 99.9%",
            "Simulation duration: 600 seconds"
        ]
    },
    {
        "id": "rate-limiter",
        "name": "Rate Limiter",
        "description": "Design a rate limiter that works across multiple instances and enforces global quotas.",
        "targetRps": 1000,
        "durationSec": 180,
        "maxP95LatencyMs": 50,
        "requiredAvailabilityPct": 99.9,
        "mustInclude": ["webserver", "cache"],
        "encouragedComponents": ["messageQueue"],
        "hints": ["Consider Redis or distributed token buckets. Account for clock drift."],
        "interviewerRequirements": [
            "Rate limits must be enforced across multiple service instances.",
            "State should be centralized or synchronized (e.g., using Redis).",
            "System should recover cleanly from cache failures."
        ],
        "functionalRequirements": [
            "Must include a shared cache (e.g., Redis) for rate limiting state",
            "Must include a webserver that respects global rate limits",
            "Encouraged to queue burst traffic using message queues"
        ],
        "nonFunctionalRequirements": [
            "Target RPS: 1000",
            "Max P95 latency: 50ms",
            "Required availability: 99.9%",
            "Simulation duration: 180 seconds"
        ]
    },
    {
        "id": "metrics-system",
        "name": "Metrics System",
        "description": "Design a pull-based metrics system like Prometheus that scrapes multiple services.",
        "targetRps": 1000,
        "durationSec": 300,
        "maxP95LatencyMs": 100,
        "requiredAvailabilityPct": 99.9,
        "mustInclude": ["data pipeline", "monitoring/alerting"],
        "encouragedComponents": ["cache"],
        "hints": ["Consider time-series indexing and label-based queries."],
        "interviewerRequirements": [
            "The system should pull metrics from external sources at regular intervals.",
            "Collected metrics should be queryable using labels and timestamps.",
            "Alert on metric thresholds (e.g., error rates > 5%)."
        ],
        "functionalRequirements": [
            "Must include a data pipeline for ingesting scraped metrics",
            "Must include a monitoring/alerting component that triggers alerts based on thresholds",
            "Encouraged to cache recently queried results for performance"
        ],
        "nonFunctionalRequirements": [
            "Target RPS: 1000",
            "Max P95 latency: 100ms",
            "Required availability: 99.9%",
            "Simulation duration: 300 seconds"
        ]
    }
]