Sector file // ai-engineering
AI ENGINEERINGDECODED.
Prompts, RAG, agents & evals
Easy
7 questionsWhat is a Large Language Model and how does it generate text?
AI Engineering · 1.1k views · llm, transformer, fundamentals
What are embeddings and what are they used for?
AI Engineering · 974 views · embeddings, vectors, semantic-search
Context windows in 2025-26: how do you use 128k-1M tokens without drowning?
System Design · 604 views · context-window, long-context
What are tokens and why do they matter for cost and limits?
AI Engineering · 540 views · tokens, tokenization, pricing
AI observability: how do you trace and log LLM calls in prod?
Frontend · 219 views · observability, tracing
What is a context window and what happens when you exceed it?
AI Engineering · 172 views · context-window, limits, fundamentals
When should you use batch APIs instead of real-time LLM calls?
AI Engineering · 107 views · batch-api, cost, async
Medium
23 questionsHow do you build resilient LLM calls with rate limits, retries and fallbacks?
AI Engineering · 1.2k views · rate-limits, retries, fallbacks
What is the difference between a base model, an instruction-tuned model and a chat model?
AI Engineering · 1.1k views · base-model, instruction-tuning, rlhf
What are reasoning models and when should you use them?
AI Engineering · 912 views · reasoning, models
How do multimodal models handle images, audio and other non-text inputs?
AI Engineering · 872 views · multimodal, vision, audio
How do you estimate and control LLM costs in production?
AI Engineering · 831 views · cost, tokens, optimization
Cost optimization for LLM apps: how do you keep the bill predictable?
System Design · 804 views · cost, optimization
How do temperature, top-p and other sampling parameters affect output?
AI Engineering · 722 views · temperature, top-p, sampling
What chunking strategies exist and how does chunk size affect RAG quality?
AI Engineering · 615 views · chunking, rag, indexing
Hard
12 questionsHow do you sandbox an agent and enforce least-privilege tool access?
AI Engineering · 1.2k views · sandboxing, least-privilege, security
How do you evaluate a RAG pipeline end to end?
AI Engineering · 1.0k views · rag-evaluation, recall, faithfulness
When should you split work across multiple agents instead of one?
AI Engineering · 947 views · multi-agent, orchestration, subagents
How would you design a production RAG pipeline end-to-end in 2025-26?
System Design · 859 views · rag, architecture, retrieval
MCP authoring: how do you build a Model Context Protocol server in 2025-26?
System Design · 777 views · mcp, tooling
What is prompt injection and how do you defend against it?
AI Engineering · 560 views · prompt-injection, security, guardrails
Guardrails for AI agents: rate limits, budget caps, and HITL?
System Design · 559 views · agents, cost
How do you validate and repair structured LLM output at runtime?
AI Engineering · 480 views · validation, structured-output, repair-loop
Seen a AI Engineering question that is not here? Add it and help the next candidate.
Share a question