Prompt Engineer or Prompt… · 7Q AI Trivia · Play Free

Prompt Engineer or Prompt… · 7Q AI Trivia · Play Free

About “Prompt Engineer or Prompt Tourist?”

~3 min
·
7 questions
·
medium
·
fun
·
English
·
Smart Host

Hosted byCalmLunaCalm and thoughtfulWarm, unhurried English with clear articulation

This pack is a shareable medium-level check on A technical but fun AI builder challenge about prompt engineering myths, evals, retrieval augmented generation, agents, context windows, tool use, structured outputs, and disciplined AI product workflows.. Built for educators, L&D teams, and anyone running a review session who doesn't want a dry slide deck or a paper quiz.

Each question runs on a 20-second timer, with answer reveals voiced by Luna. Luna brings calm, poetic energy to every question — warm, measured, thoughtful. Total run time is about 3 minutes for 7 questions.

The pack covers Prompt Engineering Fundamentals, Context Window Management, Retrieval Augmented Generation, AI Agent Workflows, Model Performance Optimization, and Prompt and Context Distinctions. Actual question text is kept off the lander so the first run doubles as a genuine pre-/post-test, not a review of the questions you already saw.

No accounts, no installs — participants open the link on any device and play. The results screen shows each player's score and streak, which is enough for a quick debrief without exporting data. All in English.

What you’ll be tested on

Prompt Engineering Fundamentals
Context Window Management
Retrieval Augmented Generation
AI Agent Workflows
Model Performance Optimization
Prompt and Context Distinctions
Tool Orchestration in AI
Token Budget Allocation

Categories

Questions about this game

FAQ

Expect roughly 3 minutes for a full playthrough. "Prompt Engineer or Prompt Tourist?" has 7 questions on a 20-second-per-question clock, with voice-hosted reveals in between.

About this game

Prompt Engineer or Prompt Tourist? is a 7-question AI-hosted trivia round about A technical but fun AI builder challenge about prompt engineering myths, evals, retrieval augmented generation, agents, context windows, tool use, structured outputs, and disciplined AI product workflows.. The round is balanced for mixed audiences — challenging enough to keep regulars engaged without losing newcomers, and the host carries it with a tone that is fun and upbeat — the round keeps the energy light while still rewarding real topic knowledge. Most players finish in about 3 minutes on phone or laptop — no signup, no app install, just a shareable link that opens straight into the game.

Every question is generated by AI and checked before publication. The pack passed Trivana's quality and fact-checking pipeline before publication. The host voice (delivered by Luna) reads each question aloud with timing, reacts to your answer in real time, and produces a shareable scorecard when the round ends. Trivana is built for the moment when a static quiz form falls short of the gameshow energy the topic deserves.

What we verified before publishing

Fact-check status: passed

The following claims were verified through Perplexity Sonar before the questions were finalised. The host can reference any of them during play:

Prompt engineering is the practice of designing and refining instructions given to a large language model to improve output quality, accuracy, and relevance.
Prompt engineering commonly includes few-shot examples, chain-of-thought reasoning, role assignment, and output constraints.
Context engineering is described as managing what information persists, gets summarized, or gets dropped so an AI agent's context window stays focused and signal-dense.
Retrieval-augmented generation (RAG) is a technique within context engineering that pulls relevant documents or data into the model's context window before inference.
Context engineering also covers memory management, tool orchestration, token budget allocation, context compression, and state persistence across multi-turn interactions.

Show all 7 questions, answers, and explanations — full spoilers, only expand after playing

Heads up: opening this section reveals every question, every option, and the correct answer for this round. If you came here to play, scroll up and hit Play first.

Question 1: What is the primary goal of prompt engineering?

To create graphical user interfaces for AI applications.
To manage server infrastructure for AI deployments.
To design and refine instructions for large language models. ✓ correct
To develop new AI models from scratch.

Explanation: Prompt engineering focuses on crafting and refining instructions given to a large language model to improve the quality, accuracy, and relevance of its output, making it a crucial skill for AI builders.

Question 2: Which of these is NOT a common technique used in prompt engineering?

Hardware optimization. ✓ correct
Role assignment.
Chain-of-thought reasoning.
Few-shot examples.

Explanation: Prompt engineering commonly includes techniques like few-shot examples, chain-of-thought reasoning, role assignment, and output constraints. Hardware optimization is related to system performance, not prompt design.

Question 3: What is the main purpose of context engineering in AI agents?

To manage an AI agent's context window for focus and signal density. ✓ correct
To design the physical hardware for AI agents.
To create marketing materials for AI products.
To write the initial training data for AI models.

Explanation: Context engineering is described as managing what information persists, gets summarized, or gets dropped so an AI agent's context window stays focused and signal-dense, optimizing its operational efficiency.

Question 4: What technique involves pulling relevant documents into a model's context window before inference?

Generative adversarial networks (GANs).
Recurrent neural networks (RNNs).
Retrieval-augmented generation (RAG). ✓ correct
Convolutional neural networks (CNNs).

Explanation: Retrieval-augmented generation (RAG) is a key technique within context engineering that pulls relevant documents or data into the model's context window before inference, enhancing the model's knowledge.

Question 5: What can happen if a prompt exceeds a model's maximum token length?

The model requests a shorter prompt from the user.
The model automatically expands its token limit.
The prompt is truncated, leading to lost context. ✓ correct
The model processes the entire prompt without issues.

Explanation: Prompt size matters because prompts that exceed a model's maximum token length can truncate instructions or input data, leading to lost context or incomprehensible output from the model.

Question 6: According to Glean, how is prompt engineering generally framed compared to context engineering?

Prompt engineering is developer-facing; context engineering is user-facing.
Prompt engineering is user-facing; context engineering is developer-facing. ✓ correct
Both are exclusively developer-facing.
Both are exclusively user-facing.

Explanation: Glean frames prompt engineering as user-facing, focusing on the direct instructions given by users, while context engineering is described as developer-facing and system-oriented, managing the underlying AI context.

Question 7: What is a potential issue if the wrong chat template is used with a modern language model?

Unexpected performance drops can occur. ✓ correct
The model will switch to a different language.
The model will automatically correct the template.
The model will refuse to generate any output.

Explanation: Using the wrong chat template, even with small errors such as extra newlines, can cause unexpected performance drops, highlighting the importance of correct template application for optimal model behavior.