MangaAssist Interview Pack - Medium

Level: Medium
What this tests: Request flow reasoning, component responsibilities, tradeoff awareness, and correct use of project-specific details.

Flow Map

graph LR
    A[User Message] --> B[Intent Classifier]
    B -->|chitchat| C[Template Path]
    B -->|order tracking| D[Order API]
    B -->|product question| E[Catalog Lookup]
    B -->|recommendation| F[Reco Engine + Catalog]
    B -->|faq / policy| G[RAG Pipeline]
    B -->|ambiguous| H[Full LLM Path]
    C --> I[Guardrails]
    D --> I
    E --> I
    F --> I
    G --> I
    H --> I
    I --> J[Response]

Interview Questions

Product Manager

1. If a user says, “I liked Demon Slayer, what should I read next?”, what signals from this project would you use before generating the response?
2. How would you explain the difference between product discovery, recommendation, and product Q&A in user-facing terms?

Senior Engineer

1. Describe the full flow of a recommendation request from the moment the user sends it to the moment the UI displays the answer.
2. Why does MangaAssist use a two-stage intent classification path instead of a single model for every message?
3. What is stored in conversation memory, and why is TTL important here?
4. Why are prices treated differently from product details, promotions, and reviews in the caching strategy?

ML Engineer

1. What is the point of reranking in the RAG pipeline, and why is vector similarity alone not enough?
2. How does the design try to reduce hallucinations when the LLM talks about products, prices, or policies?

SRE

1. What parts of this architecture are critical versus nice-to-have during a partial outage?

Analytics Lead

1. How would you connect operational metrics like latency and guardrail block rate to business metrics like conversion and support deflection?

Sequence Recall

sequenceDiagram
    participant User
    participant Orch as Orchestrator
    participant Memory as DynamoDB Memory
    participant Intent as Intent Classifier
    participant Reco as Recommendation Engine
    participant Catalog as Product Catalog
    participant LLM as Bedrock LLM
    participant Guard as Guardrails

    User->>Orch: Recommend manga like Vinland Saga
    Orch->>Memory: Load session context
    Orch->>Intent: Classify intent
    Intent-->>Orch: recommendation
    par Data fan-out
        Orch->>Reco: Get ranked titles
        Orch->>Catalog: Get product metadata
    end
    Reco-->>Orch: Ranked ASINs
    Catalog-->>Orch: Product details
    Orch->>LLM: Prompt with structured context
    LLM-->>Orch: Draft answer
    Orch->>Guard: Validate output
    Guard-->>User: Final response