A prompting technique that asks Claude to explain its reasoning step by step before giving a conclusion. For tasks requiring multi-step judgment, this produces more accurate results than jumping straight to an answer — and makes it easier for you to spot where the reasoning went wrong.

Constraint stacking refers to giving Claude several positive constraints at once in the same prompt — length, tone, format, target audience. When these constraints pile up without a stated priority, they can conflict with each other, leaving Claude to decide on its own which one to satisfy first.

Context Handoff refers to the deliberate technique of transferring work context between different Claude conversations. Because Claude has no cross-conversation memory by default, Context Handoff lets you quickly 'wake up' the needed background when starting a new conversation, avoiding the need to re-explain everything from scratch.

The total amount of information Claude can 'see' in a single conversation — including your messages, uploaded files, and all prior conversation turns. Once exceeded, the earliest content gets cut off.

Custom Instructions are fixed background descriptions you configure in <a href="/en/glossary/claude-tools/claude-projects/" target="_blank">Claude Projects</a>, so Claude automatically knows your role, work context, preferences, and constraints at the start of every conversation in that Project — without you needing to re-explain each time.

Example ordering means that in few-shot prompting, arranging the same set of examples in a different sequence changes how Claude picks up on the underlying pattern. Placing the example that best represents the core rule last, closest to the actual task, usually makes it easier for Claude to grasp the pattern you want than a random order would.

<a href="/en/glossary/core-concepts/extended-thinking/" target="_blank">Extended Thinking</a> is a separate reasoning phase Claude goes through before giving its final answer, where it breaks down the problem, works through it step by step, and double-checks its own logic. This reasoning is typically shown to you, so you can see how Claude arrived at the answer instead of just seeing the conclusion.

Few-Shot Prompting involves providing 1-3 concrete input-to-output examples in the prompt, letting Claude generate output matching your expectations by imitating the format and style of these examples. When Zero-Shot (no examples) is not precise enough, adding examples is typically the most effective improvement.

Follow-up question design refers to Claude proactively asking a clarifying question when an instruction isn't specific enough, aiming to confirm direction before actually doing the work, rather than guessing and producing a result that might not match what's needed. Asking isn't a sign of insufficient capability — it's a reasonable response to an ambiguous instruction.

Claude outputs incorrect, fabricated, or unverifiable information with high apparent confidence — like a very confident colleague giving you a wrong answer that feels completely reliable. In workplace contexts, the most dangerous aspect isn't Claude making obvious errors, but making errors confidently.

<a href="/en/glossary/core-concepts/hallucination/" target="_blank">Hallucination</a> refers to an AI model generating inaccurate, nonexistent, or unverifiable information in a confident tone. Claude may give an answer that sounds plausible but is actually wrong when uncertain. This is a limitation shared by all large language models — workplace users need to understand when it's most likely to occur.

Iterative Prompting means providing feedback or adjustment requests within the same conversation based on Claude's previous output, progressively moving the output toward what you truly need. Rather than asking once and finishing, it transforms 'Q&A' into 'conversational work' — through several back-and-forth rounds making Claude's output progressively more precise.

"Context" is what Claude can see within a single conversation — it disappears when that conversation ends. "Memory" is information that persists across conversations and is still there next time you open a new chat. Confusing the two leads to broken workflow assumptions.

Model selection trade-off means weighing speed, cost, and capability against each other to pick the Claude model tier that fits the task at hand, rather than always defaulting to the most powerful model or always defaulting to the cheapest.

Negative prompting means explicitly telling Claude what not to do, rather than only describing what to do. For example, beyond saying 'write me an apology email,' adding 'don't use stiff corporate language, keep it under 150 words' — those last two instructions are negative prompting.

Output Format refers to explicitly telling Claude in your prompt what the output you want should look like — length, structure, tone, format (bullet points/paragraphs/tables), etc. Explicitly specifying output format is one of the single most effective changes to take Claude's output from 'roughly meets requirements' to 'ready to use directly.'

Prompt Chaining breaks a complex task into multiple steps, sending a separate prompt to Claude for each step and using the previous step's output as input for the next, connecting the entire task like links in a chain.

<a href="https://claude-me.com/en/glossary/prompt-techniques/prompt-injection/" target="_blank">Prompt Injection</a> is when an external document, email, or webpage contains text disguised as an instruction, attempting to trick Claude into executing it as a command from you rather than treating it as plain data to be processed. This matters especially in workplace settings, since you often ask Claude to read documents or emails received from outside sources.

Prompt length calibration means finding the length where a prompt is 'just enough' — too short leaves Claude without enough context to guess what you actually want, too long buries the instructions that actually matter under excess detail. Both ends degrade output quality.

A pre-structured prompt framework with placeholder variables, enabling consistent high-quality outputs by simply swapping in new content each time.

Response regeneration means, when you're not satisfied with one of Claude's answers, asking for another answer to the same question without changing the prompt. Since each generation has some randomness, regenerating often produces a version with a different style or angle — but if the underlying issue is that the prompt itself wasn't clear enough, regeneration usually won't fix the root problem.

Role persona depth refers to how much detail is given when setting up a role in <a href="/en/glossary/prompt-techniques/role-prompting/" target="_blank">Role Prompting</a> — giving just a title ('you are a marketing consultant') is a shallow persona, while adding background experience, judgment style, and characteristic tone builds a deep one. Deeper isn't always better; depth needs to match the task's complexity to genuinely improve output quality.

<a href="/en/glossary/prompt-techniques/role-prompting/" target="_blank">Role Prompting</a> is the technique of specifying a particular role or identity for Claude at the start of a prompt — such as 'you are a marketing consultant with 10 years of experience' or 'you are a strict legal editor.' This lets Claude respond from a specific professional perspective, with output that better matches that domain's tone, terminology, and thinking framework.

Session continuity refers to how different actions within a conversation affect whether Claude still remembers prior context — regenerating a different version of the same message keeps all the conversation before it intact, but opening a brand-new conversation means none of what was previously discussed carries over automatically, unless manually copied over or saved into a Claude Project.

A <a href="/en/glossary/prompt-techniques/system-prompt/" target="_blank">System Prompt</a> is an instruction pre-configured at the system level before formal conversation begins, defining Claude's role, behavioral guidelines, and response style. What workplace users configure through <a href="/en/glossary/claude-tools/claude-projects/" target="_blank">Claude Projects</a>' Custom Instructions is essentially a form of System Prompt.

A task handoff template is a fixed-format document that organizes a task's current progress, key decisions made, and unresolved questions, so the next conversation, another person, or your future self can pick up right where it left off without having to review the entire process from scratch.

<a href="/en/glossary/core-concepts/temperature/" target="_blank">Temperature</a> is a parameter controlling the 'randomness' of AI output, ranging from 0 to 1 (or higher). Lower values produce more stable, predictable output; higher values produce more creative but less consistent output. Workplace users typically encounter this parameter only when using the API.

The maximum amount of text Claude can process in a single conversation. Once exceeded, earlier content is forgotten, causing Claude to 'lose memory' or stop responding coherently.

XML tag structuring means wrapping different types of content in a prompt with tags like <instructions></instructions>, so Claude can clearly tell which part is background material, which part is a rule to follow, and which part is the actual task — instead of leaving everything mixed together in one block of text for Claude to guess at.

<a href="/en/glossary/prompt-techniques/zero-shot-prompting/" target="_blank">Zero-Shot Prompting</a> means giving Claude a task instruction without any examples, letting it complete the task based on its own training knowledge. Most everyday Claude use is Zero-Shot — you ask a question or give an instruction directly, without needing to provide examples first.