Custom instructions

On this page 7

Custom instructions are persistent, user-defined directions that an AI assistant applies automatically to every new conversation, so that preferences about tone, format, background and constraints do not need to be repeated in each prompt. In prompting for artificial intelligence systems, they act as a standing layer of context placed before the individual request.

Most chat assistants expose custom instructions as a settings field or profile, sometimes split into what the model should know about the user and how it should respond. Their value lies in consistency across sessions; their main risk is that a forgotten instruction can silently distort later answers.

How custom instructions reach the model

Custom instructions work by injecting stored text into the context window at the start of each conversation, usually inside or alongside the system prompt that the application already sends. The model does not remember the user in a biological sense; it simply reads the same instructions again every time a new chat begins.

Because the text is processed as ordinary input tokens, custom instructions consume part of the context budget and are subject to the same attention dynamics as any other prompt content. Applications typically cap their length at a few thousand characters, and the platform own safety rules and system prompt take precedence over anything the user writes.

The table below shows where custom instructions sit among the layers that shape a typical assistant response.

LayerWho writes itScopePriority
Platform system promptModel provider or applicationAll usersHighest
Organization instructionsWorkspace administratorAll members of a workspaceHigh
Custom instructionsIndividual userAll of that user conversationsMedium
Project or assistant instructionsUser or teamOne project or configured assistantMedium, more specific
Conversation promptUser, per messageCurrent turnMost specific
Layers of instruction in a typical assistant

What custom instructions usually contain

Effective custom instructions describe stable facts and durable preferences, not one-off tasks. They usually fall into two groups: background about the user, such as role, expertise and working language, and response preferences, such as length, structure and level of formality.

CategoryExample instructionEffect on answers
Role and expertiseSenior backend engineer, familiar with GoSkips basics, uses precise terminology
Output formatPrefer tables and numbered stepsMore structured, scannable responses
Length and depthKeep answers under 200 words unless askedShorter default replies
Tone and styleFormal register, American spellingConsistent voice across sessions
ConstraintsNever suggest paid tools without saying soFilters certain recommendations
Common categories of custom instructions

A well-written set reads like a concise briefing for a new colleague: specific, positively phrased and free of contradictions. Vague wishes such as “be helpful” add tokens without changing behavior. Concrete wording, such as naming the preferred date format or the target audience, gives the model a clear signal it can act on.

Custom instructions overlap with several neighboring techniques in prompting, but they differ in who controls them and how long they last. Role prompting and a prompt template, for example, are applied deliberately to a single task, while custom instructions apply by default to everything.

TechniquePersistenceTypical authorBest use
Custom instructionsEvery new conversationEnd userDurable personal preferences
System promptEvery request in an applicationDeveloperProduct behavior and guardrails
Prompt templateEach time it is filled inPrompt authorRepeatable task structure
Role promptingSingle prompt or conversationUserAdopting a specific perspective
Assistant memoryLearned facts across chatsModel and user togetherRecalling details mentioned earlier
Custom instructions and neighboring techniques

The distinction from memory features matters in practice. Custom instructions are explicit text the user fully controls, whereas memory stores facts the assistant inferred or saved, which can be harder to audit. Context engineering treats both as inputs to be curated deliberately.

Writing and maintaining effective instructions

Good custom instructions are short, specific and testable. Each line should describe a behavior that can be observed in an answer, which allows the user to verify whether the model actually follows it.

  • State defaults, not absolutes: “Prefer concise answers” leaves room for detail when a question demands it.
  • Put the most important rules first, because long instruction blocks dilute attention.
  • Avoid conflicts with likely task prompts, such as a strict word limit combined with frequent requests for full reports.
  • Test with representative questions after every change and compare answers with and without the instructions.
  • Review them periodically, since a changed role or project makes old background misleading.

In shared or enterprise deployments, organization-level instructions should cover compliance and house style, leaving personal fields for individual preferences. This separation of concerns prevents users from accidentally overriding policy text.

Limitations, risks and common mistakes

Custom instructions influence behavior but do not guarantee it. Models can drift away from a preference in long conversations, especially when later messages pull in another direction, and instruction-following quality differs between model versions.

SymptomLikely causeFix
Instruction ignored in long chatsDilution by later contextRestate the rule or start a new chat
Odd answers on unrelated topicsOverly broad background detailsRemove details irrelevant to most tasks
Inconsistent formattingContradictory format rulesMerge into one clear preference
Private data appearing in outputsSensitive facts stored in instructionsDelete personal identifiers from the profile
Typical problems and how to fix them

A security point is often overlooked: custom instructions are not a security boundary. Text retrieved from documents or web pages can attempt prompt injection, and a user preference cannot reliably block it; protection belongs in the application design.

In simple terms

Custom instructions are like a note you hand to an assistant before every meeting. Instead of explaining each time who you are and how you like information presented, you write it once, and the AI reads that note at the start of every new chat.

The note shapes the answers but does not lock them. Keep it short, accurate and up to date, because the assistant will keep following old advice until you change it.

A practical example

A compliance analyst at a mid-sized bank uses an AI assistant daily to summarize regulatory updates. At first, every answer arrives as long prose with British and American spelling mixed together, and she spends several minutes reformatting each summary for internal reports.

She adds three custom instructions: her role as a compliance analyst in banking, a request for a five-bullet summary followed by a table of deadlines, and a rule to flag any uncertainty explicitly. Over the next weeks, summaries arrive in a consistent, report-ready format, and her editing time per document drops from roughly ten minutes to two. When she later moves to a risk modeling team, she rewrites the role line so that answers stop emphasizing regulatory deadlines.