Skip to content

Tracks Drills Topics Technologies Tech stacks Skill areas

Tracks Drills Guides

Loading

Aporeon

Technical interview practice, from one developer to another.

Guides About Editorial standards Support Privacy Terms Refund policy

Drills

Pick a focused question that fits your time, stack, and interview goal.

How much time do you have?

Show one-drill sessions you can finish now.

Search

Track

Practice style

Level

More filters1

Topic

Technology

Tech stack

Skill area

21 results across 1 active filter

Page 1 of 1

Debugging scenarioHard~15 min

A RAG system missed the right document. How would you diagnose it?

Traces a missed answer through source ingestion, parsing, chunking, filtering, query construction, retrieval, fusion, and ranking.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Hard

~40 min

Build hybrid RAG retrieval with access control and verified citations

Builds a hybrid retrieval pipeline that enforces tenant scope before ranking, assembles a bounded context, and verifies returned citations.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Comparison questionHard~12 min

Compare a managed RAG service with a custom retrieval pipeline.

Chooses between managed ingestion and retrieval convenience and custom control over indexing, ranking, security, evaluation, and operations.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Comparison questionMedium~10 min

Compare inference, training, fine-tuning, prompting, and RAG.

Separates runtime model use from model training, fine-tuning, prompt design, and retrieval-augmented generation as different engineering levers.

Artificial IntelligenceGenerative AILarge Language Models

Comparison questionMedium~10 min

Compare keyword, vector, and hybrid search for RAG.

Combines exact lexical matching with semantic recall and explains why hybrid retrieval often needs measured fusion and ranking.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Coding problemHard~40 min

Contain and recover from a poisoned RAG index

Handles a poisoned retrieval corpus by freezing ingestion, tracing provenance, switching immutable index versions, rebuilding clean data, and proving recovery.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioHard~20 min

Design a production RAG answering boundary for internal knowledge.

Combines governed ingestion, authorized hybrid retrieval, reranking, grounded generation, citations, evaluation, observability, and fallback.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Coding problemHard~35 min

Diagnose a RAG quality regression from retrieval and generation evidence

Uses versioned traces and evaluation slices to locate whether a RAG regression came from ingestion, retrieval, context assembly, or generation.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioMedium~10 min

How would you build or rewrite a retrieval query for RAG?

Transforms conversational requests into bounded search inputs while preserving user intent, constraints, and traceability.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioMedium~10 min

How would you choose a chunking strategy for a RAG system?

Balances retrieval precision, answer completeness, document structure, overlap, metadata, and model input limits.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioHard~12 min

How would you choose top-k, relevance thresholds, and abstention behavior for RAG?

Tunes evidence quantity and no-answer behavior from measured relevance rather than treating similarity scores as universal confidence.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioMedium~12 min

How would you design an ingestion and indexing pipeline for RAG?

Builds a repeatable path from governed source documents to parsed, chunked, embedded, traceable, and replaceable index records.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioHard~15 min

How would you enforce tenant and document access in a RAG system?

Carries source permissions into ingestion and query-time filtering while failing closed across retrieval, caching, and citations.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioHard~15 min

How would you evaluate retrieval separately from generation in a RAG system?

Builds a query-and-relevance dataset and separates retrieval recall, ranking quality, context quality, and generated-answer quality.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioHard~12 min

How would you ground a RAG answer and produce honest citations?

Connects answer claims to retrieved evidence while preventing decorative citations and preserving source-level traceability.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioHard~12 min

How would you keep a RAG index fresh through updates and deletes?

Coordinates source changes, versions, tombstones, reconciliation, and query-time freshness without treating the index as authoritative.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioHard~15 min

How would you secure RAG ingestion against poisoned content?

Protects knowledge ingestion with source trust, provenance, validation, quarantine, review, versioning, and rollback.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Concept questionEasy~7 min

What does retrieval-augmented generation add to an LLM application?

Explains RAG as a runtime retrieval boundary that supplies relevant, current, and governed evidence without changing model weights.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Architecture scenarioMedium~10 min

What metadata and provenance would you store in a RAG index?

Designs index records that support filtering, authorization, freshness, citations, diagnosis, and safe reprocessing.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Comparison questionMedium~10 min

When would you use RAG instead of a database query or tool call?

Chooses retrieval for ambiguous knowledge search while keeping authoritative structured operations behind deterministic services.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases

Concept questionMedium~7 min

Why preserve document structure and parent-child relationships in RAG?

Uses hierarchy and adjacency to recover context that flat chunks lose while avoiding indiscriminate document expansion.

Artificial IntelligenceGenerative AILarge Language ModelsVector Databases