MangaAssist Interview Pack - Very Hard

Level: Very Hard
What this tests: Cross-component failure reasoning, safety under pressure, cost and scaling judgment, and clear thinking in ambiguous scenarios.

Incident Map

graph TD
    A[Traffic Spike] --> B[More requests]
    B --> C[Higher downstream fan-out]
    C --> D[Higher LLM load]
    D --> E[Latency increase]
    E --> F[Timeouts]
    F --> G[More retries]
    G --> H[Dependency stress]
    H --> I[Circuit breakers open]
    I --> J[Fallback paths]
    J --> K[Lower experience quality]
    K --> L[Escalation rate rises]

Interview Questions

Principal Engineer

1. Imagine recommendation, promotions, and reviews are all degraded at the same time during a major manga release. How should the orchestrator degrade the customer experience without making the system feel broken?
2. How would you explain the difference between a graceful fallback and a misleading fallback in this project?
3. If guardrail block rate suddenly doubles after a prompt change, how would you isolate whether the issue is prompt quality, policy strictness, or data quality?

Applied Scientist

1. How would you build a feedback loop that improves intent routing, retrieval quality, and recommendation explanation quality without retraining blindly on noisy user feedback?
2. What evaluation set would you create for this chatbot so that you can detect regressions in RAG relevance, hallucination control, and user resolution?

Security Engineer

1. How would you respond if an audit found that raw prompts containing sensitive user text were retained longer than the policy intended?
2. What are the most realistic abuse patterns for a shopping chatbot like this, and which ones are more dangerous than they first appear?

SRE

1. Design a canary release strategy for a new LLM or prompt version so that quality regressions are caught before they affect most users.
2. What dashboards and alerts would you put in front of the on-call engineer so they can distinguish between model issues, dependency issues, and traffic issues quickly?

Distinguished Engineer

1. Which single architectural assumption in MangaAssist would you challenge first if this system had to expand from one niche storefront to many retail domains?

Recovery Sequence

sequenceDiagram
    participant User
    participant Edge as Gateway
    participant Orch as Orchestrator
    participant Dep as Downstream Services
    participant Safe as Guardrails/Fallback
    participant Agent as Human Queue

    User->>Edge: Send message
    Edge->>Orch: Request
    Orch->>Dep: Parallel lookups
    Dep-->>Orch: Partial failures
    Orch->>Safe: Check fallback policy
    alt recoverable
        Safe-->>User: Reduced but safe answer
    else not recoverable
        Safe->>Agent: Escalate with context
        Agent-->>User: Handoff path
    end