Prompt decomposition — breaking a complex task into smaller sub-prompts that are easier for the model to handle reliably.
Map-reduce prompt pattern — processing chunks of data in parallel (map), then synthesising the results in a final prompt (reduce).
0 / 10 completed
1 / 10
A pipeline feeds the summary from step 1 into step 2's prompt. This is an example of:
Prompt chaining connects LLM calls so that the output of one becomes the input of the next. This is fundamental to building reliable LLM pipelines: rather than asking a model to do everything in one prompt (which increases failure risk), you break the work into steps and pass structured information between them.
2 / 10
Your team processes a 200-page document by splitting it into 20 chunks, summarising each with a separate LLM call, then combining the summaries. This is the:
The map-reduce prompt pattern mirrors the classic MapReduce algorithm. In the map phase, each chunk is processed independently (and in parallel) with the same prompt. In the reduce phase, the partial outputs are synthesised by a final prompt. This is essential for handling documents longer than the model's context window.
3 / 10
A prompt DAG represents a prompt pipeline as a directed acyclic graph. What does this structure enable?
A prompt DAG (directed acyclic graph) models the prompt pipeline as nodes (LLM calls or tool calls) connected by directed edges (data flow). Because it's acyclic, it has no infinite loops. The DAG structure allows orchestrators like LangGraph or Prefect to execute independent branches in parallel and merge results at join nodes, making complex pipelines both efficient and predictable.
4 / 10
In a prompt chain, what is a handoff?
A handoff is the transfer of control and state between steps in a prompt chain or between agents in a multi-agent system. A well-designed handoff includes: the output of the previous step, any relevant context, and clear instructions for what the next step should do. Poor handoffs (e.g., passing unstructured text) are a common source of pipeline failures.
5 / 10
Why is prompt decomposition recommended for complex tasks?
Prompt decomposition improves reliability because LLMs perform better on narrow, well-defined tasks than on vague, multi-faceted ones. A single prompt asking a model to "analyse, summarise, classify, and translate" in one go concentrates many potential failure points. Breaking this into four sequential prompts, each doing one thing well, dramatically reduces error rates and makes debugging easier.
6 / 10
Alice: 'I'm struggling with the new prompt chain. The LLM keeps generating irrelevant code snippets! I've tried tweaking the initial prompt, but nothing seems to stick.' What does Alice likely need to do to improve the situation?
Alice's issue suggests the LLM is generating off-topic content. A negative constraint – telling the model *what not* to produce – is a powerful technique for guiding its output. Increasing temperature can make it *more* random, and larger datasets don't address the problem of poorly defined initial prompts; increasing token limits may also introduce issues related to context window size.
7 / 10
During a code review, Ben comments on a PR: 'This prompt chain seems overly complex. Splitting the task into smaller prompts and chaining them together could improve maintainability and reduce the risk of errors.' Ben is advocating for which strategy regarding prompt chains?
Ben's comment highlights the benefits of prompt decomposition. Complex tasks are often easier to manage when broken down into smaller, more manageable steps. Vertical integration and centralized prompting can lead to monolithic prompts that are harder to debug and maintain; sequential execution doesn't address the complexity inherent in a multi-stage process.
8 / 10
You're designing an API endpoint that accepts a JSON payload containing instructions for a prompt chain. The endpoint's response includes the generated output from the final prompt in the chain. What is the primary purpose of including this output within the API response?
The core purpose of including the final prompt's output in an API response is to enable external applications to *use* the result generated by the prompt chain. While logging is useful, it doesn't provide a way for other systems to leverage the processed information; manipulating the running chain directly is generally not advisable and would introduce significant complexity.
9 / 10
Chloe writes in a Slack channel: 'I'm using prompt chaining to summarize customer feedback. The first prompt extracts key themes, the second summarizes those themes into concise bullet points, and the third generates a short report. I've noticed that the summaries from the second prompt are sometimes inconsistent – they change significantly even with identical input data!'. What is the most likely cause of this inconsistency?
Chloe's observation points to a fundamental issue: unclear prompting. If the initial prompt doesn't precisely define the expected output format (e.g., specific keywords, sentence structure), the LLM will struggle to consistently produce the desired result. While temperature and API integration *could* contribute, they are less likely than a poorly defined initial prompt.
10 / 10
You're building a system that uses a prompt chain to generate marketing copy. The chain consists of three prompts: one for idea generation, one for draft creation, and one for refinement. In a standup update, you explain this process. Which statement best describes the concept of 'handoff' within this context?
'Handoff' refers to the transfer of data or control between consecutive steps within a prompt chain. It's how one prompt passes its output and potentially its context to the next, allowing them to build upon it. The other options represent different aspects of LLM operation or debugging – they don't capture the core concept of sequential processing within a chain.
What will I practice in "Prompt Chaining Vocabulary | Coders Lingo"?
This is a Prompt Engineering Language exercise set. It walks through 10 scenario-based multiple-choice questions built around real usage of prompt engineering language terminology that IT professionals encounter on the job.
Is this exercise free to use?
Yes. Every exercise on CoderSlingo, including this one, is free to complete with no account, sign-up, or paywall.
How many questions are in this exercise?
This set contains 10 questions. Each one shows immediate feedback and a detailed explanation after you answer, so you learn the correct usage right away rather than waiting for a final score.
Do I need prior experience to complete this exercise?
No prior experience is required. Each question includes a full explanation covering the reasoning behind the correct answer, so the exercise itself teaches the prompt engineering language vocabulary as you go.
Can I retry the exercise if I get questions wrong?
Yes — use the "Try again" button on the results screen to reset your answers and go through all the questions again. There is no limit on attempts.
Is my progress saved?
Your answers and score for the current session are tracked in the browser as you go. No account or login is needed, and there is nothing to install.
What if I don't understand a term used in a question?
Read the explanation shown after you answer each question — it breaks down the correct term in plain English with a real-world example. You can also check the site Glossary for quick definitions.
How is this different from reading a blog article on the topic?
Exercises like this one are interactive drills that test and reinforce specific vocabulary through multiple-choice questions, while blog articles explain concepts in prose. Practising here after reading builds active recall, not just passive recognition.
Where can I find more Prompt Engineering Language exercises?
See the Prompt Engineering Language exercises hub for the full set of related pages, or browse all exercise categories from the main Exercises index.
Can I use this exercise to prepare for a technical interview?
Yes — prompt engineering language vocabulary comes up often in technical discussions and interviews. Pair this exercise with our dedicated Interview Preparation section for role-specific practice.