Explore our AI courses, practical training for non-technical teamsExplore courses →Explore AI courses →
ContextPromptingAI at Work

Level Up Your AI With Context: What to Tell It Before You Ask

Most generic answers come from a request with no situation around it. Brief AI like a capable new colleague, keep only what changes the answer, and save the rest.

TLDR: Context is everything you give AI before the ask: who you are, the audience, the goal, constraints, an example, source material and standing preferences. Keep only what would change the answer, keep private detail out, and save the stable part as a reusable block you audit once a month. Vendor features checked October 21, 2026.
7kinds of context in the reusable block.
4questions in the keep-or-cut test.
Oct 21, 2026the date the vendor help pages were read.

Share this article

The Short Version

Give AI the situation a new colleague would need, then the task. Run every line through one question: would the answer change without it? Describe situations rather than people, so nothing confidential goes in. Save the stable half of your context once, in a personal setting, a project or a file you control, and audit it monthly so it doesn’t steer answers with last quarter’s facts.

A generic answer usually means a missing situation

Most generic AI answers come from a request that described the task and left out the situation. “Write a summary of this report” tells the model what to do. It says nothing about who will read the summary, what they already know, what decision it feeds, or what went wrong the last time someone sent them one. So the model fills those gaps with the most average reader it can manage, and the answer comes back polished, accurate and aimed at nobody in particular.

That’s the gap context fixes. When I talk about context for AI, I mean everything you give it before the ask: who you are, who the output is for, what it needs to achieve, the limits it has to respect, an example of what good looks like, the material it should work from, and the preferences you’d otherwise repeat every time. The prompt is the instruction. The context is the briefing that lets the instruction land.

Anthropic’s own documentation puts this in workplace terms. It tells people to think of Claude as “a brilliant but new employee who lacks context on your norms and workflows.”[1] I find that the most useful frame for non-technical teams, because everyone already knows how to brief a new colleague. You wouldn’t hand a new starter a one-line task on their first morning and expect the version your manager likes. You’d tell them who it’s for and what tripped people up last time.

The Context Rule

Brief AI the way you’d brief a capable new colleague: the situation first, then the task.

This guide covers that briefing and where to keep it. For the wording of the request itself, see our pieces on why prompting matters and reading an answer before you rewrite the prompt.

Seven kinds of context for AI worth giving before the ask

Context sorts into seven kinds. You won’t need all seven every time; the keep-or-cut test later helps you choose. The kinds people tend to skip are the ones that move the answer most. “Who I am” gets written in almost every time. “Who it’s for” and “what it must not do” get left blank.

The seven kinds of context, filled in for one request

KindWhat it tells AIExample line (an HR business partner writing a policy update)
1. Who you areYour role, what you own and what you don’tI’m an HR business partner for an operations division. I own how policy is communicated, not the policy itself.
2. The audienceWho reads the output and how they read itShift supervisors who read on their phones between tasks and skim anything longer than a screen.
3. The goalWhat should be different after they’ve read itSupervisors know what changes next month and the one thing they need to do before then.
4. ConstraintsLimits, and things only you knowUnder 200 words. No legal language. Don’t mention the pay review, which hasn’t been announced.
5. An exampleWhat good looked like last timeHere’s last quarter’s update, which landed well. Match its length and tone.
6. Source materialWhat to work from, and only fromThe approved policy text is pasted below. Work only from it.
7. Standing preferencesHow you like every answer, every timeUK spelling. Plain sentences. Bullet the actions, not the explanation.

A Future Factors working list, not a research-validated model. The right-hand column shows one request filled in so you can see the standard.

Two of these do more work than they look. Constraints carry what only you know, like the announcement that hasn’t happened yet. And an example of past work tells the model more about tone and length than any adjective. Anthropic’s guide calls examples “one of the most reliable ways to steer Claude’s output format, tone, and structure.”[1] That fits how it usually goes in practice: “make it friendly” gets you the model’s idea of friendly, and a pasted example gets you yours.

One ordinary request, with and without context

A finance analyst has to explain a budget overspend to a department head who isn’t a finance person. The quick version of the request goes in first, and what comes back is correct and unusable: an explanation of what a variance is, a list of common causes, and a suggestion to review spend regularly. Nothing in it is wrong. It just isn’t about this department, this number or this reader.

One ordinary request, before and after context

Without contextWith context
The requestExplain why the marketing budget is over this quarter.I’m a finance analyst writing to the head of marketing, who is sharp but not a finance person and wants to know whether she needs to act. Goal: she understands the overspend in two minutes and knows the one decision in front of her. Constraints: under 150 words, no jargon, don’t assign blame, and don’t speculate beyond the figures below. Source: the variance table pasted below, which shows events spend running ahead of plan because a conference deposit was paid early, while digital spend is on plan. Style: answer first, then the reason, then the decision. Task: explain why the marketing budget is over this quarter.
What it tends to produceA general explainer on budget variances that could go to any department.A short note that says the overspend is mostly timing, names the deposit, and asks one question: pull planned spend forward or hold it.

The task line is nearly identical in both versions. Everything that changed the answer sits in the situation around it.

Notice what the second version didn’t need: a cleverer instruction. The gain comes from a few sentences of situation, and three of them (the reader, the goal and the line about blame) are things the model could never have inferred from a spreadsheet. If you want to see how one request like this can be shaped further across a few turns, our guide to prompting AI like a conversation picks up where this leaves off. “Could the model have guessed this?” is also the first question to ask about any line of context, and it’s where the next section starts.

What to leave out, because more context can make it worse

Once people discover context, the next move is predictable: they paste everything. The whole policy manual, three old email threads, a long biography and a note saying “use whatever’s relevant.” It feels thorough, and it usually makes the answer worse, for two reasons.

The first is that irrelevant material competes with the material that matters. A 2023 study of how language models use long inputs found performance “is often highest when relevant information occurs at the beginning or end” and degrades when the model has to find it in the middle.[2] Models have moved on since then, so I’d hold the details loosely. Anthropic’s current advice to its own developers points the same way, though: find “the smallest possible set of high-signal tokens” for the job.[3]

The second reason is staleness. Old context reads as current. If last year’s org chart or a superseded price list is sitting in a project, the model will usually treat it as confidently as everything else, and nothing in the tone of the answer warns you. Long conversations have their own version of this, which we cover in what is context rot. Here the problem sits one step earlier, in what you choose to include before the conversation starts.

The keep-or-cut test for any piece of context

QuestionIf yesIf no
1. Would the answer change if I left this out?Keep itCut it
2. Is it still true today?Keep itUpdate it or cut it. Out-of-date context usually does more harm than a gap
3. Does the model need all of it?Paste the whole thingPaste the part that applies, or summarise it in two lines
4. Is it safe to share under my organisation’s AI policy?Keep itRemove it, or describe it without the identifying detail

A Future Factors working test. Run it on a context block before you save it, and again whenever answers start drifting.

The Relevance Rule

If it wouldn’t change the answer, it doesn’t belong in the context.

What stays out of the context, whatever the plan

Privacy needs its own rule, because context is exactly where sensitive material slips in. A request feels like a request. A context block feels like background, and background is where people paste the client’s name, the salary band, the board paper or a colleague’s performance notes “just so it understands.”

Where that material ends up depends on the tool and the account. OpenAI, for example, says it may use content from its services for individuals to train its models unless you turn off “Improve the model for everyone” in Data controls, and that by default it doesn’t use inputs or outputs from ChatGPT Business, Enterprise, Edu or its API to improve models.[4] Other vendors set their own terms. So the first check is your organisation’s AI policy and which account you’re signed into, before any setting inside the tool.

My own line is stricter than most settings pages. Unless your organisation has approved that specific use in writing, these stay out of the context whatever the plan:

  • Personal data about identifiable people, especially anything about performance, health, pay or discipline.
  • Client or customer information covered by a contract or a confidentiality agreement.
  • Credentials of any kind: passwords, API keys, private access links.
  • Unannounced results, deals, restructures or anything market-sensitive.
  • Anything you’d be uncomfortable seeing surface again in a different chat, which is a real possibility once memory is switched on.

Most context doesn’t need the sensitive detail anyway. “A senior engineer whose last two projects ran late” gives the model the situation. The name adds nothing to the answer and a great deal to the risk. Describe the shape of the situation and keep the identifying details on your side of the screen. For the settings in each tool, see our guide to using AI at work without leaking company data.

The Privacy Rule

Describe the situation, not the person: if a detail identifies someone or something confidential, leave it out or replace it with a description.

Write it once: a reusable context block

Retyping the same background into every chat is how good context habits fade by week two. Write the stable parts once and keep them where you can paste or attach them in seconds. The stable parts are who you are, the audiences you write for most, your standing preferences and your always-and-never lines. The changing parts, the goal and the source material, still go in fresh each time.

A reusable context block, filled in

ABOUT ME: I’m an operations manager at a mid-sized logistics company. I own the weekly performance report and supplier communications. I don’t approve spend beyond my budget line; finance does.

WHO I USUALLY WRITE FOR: (1) The leadership team: short, numbers first, they want the decision. (2) Site supervisors: practical, reading on phones, actions in bullets. (3) Suppliers: polite, firm, no internal detail.

HOW I LIKE ANSWERS: UK spelling. Plain language. Lead with the answer. Flag anything you’re unsure of instead of guessing. If my request is ambiguous, ask me one question before you start.

ALWAYS: When I give you a source, work only from it. Tell me if anything I’ve given you looks out of date or contradicts itself.

NEVER: Invent figures. Name a supplier or a member of staff unless I’ve named them in this chat.

THIS TIME (fill in per request): Goal: ___. Audience: ___. Constraints: ___. Source: ___. Example of good: ___.

Replace each line with your own. Everything above THIS TIME is stable and worth saving. The last line changes with every request, which is why it’s the only one left blank.

The block shifts by role more than people expect, even though the seven kinds stay the same:

  • An HR business partner usually has the longest never list, mostly about people data.
  • A finance analyst leans on the always line: which system is the source of truth.
  • A marketing manager gets most from the example of past work, because tone is what gets judged.
  • A team lead needs the audience section most, one line per group.

Where to keep it so you stop retyping it

Every major assistant now has somewhere to keep context, and they behave differently enough that it’s worth choosing on purpose. The decision rule I’d use: put what applies to almost everything you do in a personal setting, put what applies to one piece of work in a project, and treat memory as a convenience you check, never as a filing system you rely on.

Where each kind of context lives best (vendor pages checked October 21, 2026)

ContainerBest forWhat the vendor saysWatch out for
Personal or custom instructionsWho you are and standing preferencesAccount-wide settings that apply across your chatsKeep them short and general. Project settings can override them
ChatGPT project instructions and filesOne client, one report, one recurring piece of workProject instructions “apply only within that project and override your global custom instructions”[5]Your global preferences won’t carry into the project unless you repeat them there
Claude project instructions and knowledgeThe same, for Claude usersAnything uploaded “will be used across all of your chats within that project”; free accounts are limited to five projects[6]Upload the current version only. An old draft in project knowledge is stale context
Gemini GemsA repeat task with its own instructions and filesGems take instructions and knowledge files; Google says that starting in November 2026, Gems “will go away on personal Google accounts” and move to skills[7]On a personal account, keep a copy of your instructions somewhere you control
MemorySmall personal facts and preferencesSaved memories are “details that you explicitly ask ChatGPT to remember”; temporary chats don’t create or update them[8]You don’t always see what it draws on. Review the list and keep sensitive detail out
A saved context fileAnything you use across more than one toolWorks anywhere you can paste or attach textOnly as current as the last time you edited it

A Future Factors decision table built from each vendor’s help pages. Features change often, so check before you rely on one.

For setup, see our walkthroughs of ChatGPT custom instructions, ChatGPT Projects, Claude Projects, Gems in Gemini and how AI memory works.

Storing context changes who does what. The model applies the briefing; you decide what’s in it and own what leaves your desk.

What the stored context does, what you still own, how it gets checked

What AI does with itWhat you still ownHow it gets checked
Uses your context block to pitch tone, length and audience on every draftWhat goes into the block and what stays outThe monthly audit below, ten minutes
Drafts from the files in a projectWhich version of each file is currentRemove a superseded file the day its replacement goes in
Recalls preferences you’ve asked it to keepWhat it’s allowed to rememberOpen the memory list once a month and delete anything stale or sensitive
Produces a draft pitched to the situationEvery figure, name and claim that leaves your deskCheck them against the source before you send

A Future Factors working split for any assistant that stores context.

Keep it current with a monthly context audit

Context goes stale quietly. A team changes, a priority shifts, the audience you described as “skims on a phone” gets replaced by a board that reads every word, and the block keeps steering the model toward last quarter’s situation. Nothing announces it. The answers drift slightly off, and it takes a while to notice that the cause is the briefing rather than the model.

The monthly context audit

CheckPasses ifIf it fails
1. Role and remitIt still describes your current job and what you ownRewrite the line
2. AudiencesThey’re still the people you write for most this monthAdd or remove one
3. PreferencesYou’d still ask for each one if you were starting freshDelete the ones you’ve stopped caring about
4. Project filesOnly current versions, nothing supersededRemove old drafts and old price lists
5. MemoryNothing sensitive and nothing out of dateDelete the entry
6. PrivacyNothing fails the Privacy RuleReplace the detail with a description
7. ReworkRecent answers needed less correcting than beforeFind the line that’s steering it wrong

Scoring: all seven pass, leave it alone. One or two fail, fix them today. Three or more fail, rewrite the block from the template above.

You can also get the model to do the first pass of the audit, as long as you make the decisions. This prompt asks it to find problems without rewriting anything yet:

Prompt: audit my context block

Here is the context block I use with you. Don’t rewrite it yet. First, list anything that looks vague, out of date, contradictory, or more detailed than an ordinary request would need. Second, list anything that looks like personal or confidential detail I should remove or describe more generally. Third, ask me up to three questions about my work whose answers would make this block more useful. [paste your block]

Paste your block where the brackets are. You decide what changes; the model only points.

If you’re starting from nothing, this is the order I’d go in this week:

  1. Write the stable half of the block today, using the template above. Twenty minutes is enough for a first version.
  2. Run the keep-or-cut test on it and remove anything that fails.
  3. Save it where you’ll actually use it: personal instructions, a project or a document you paste.
  4. Use it on a few ordinary requests and note each time you still had to correct the answer.
  5. Add one line to the block for any correction that came up twice.

You can start all of this on your own. Where a whole team wants shared context blocks, building them together with someone who has seen how they go wrong shortens the learning curve, and that’s the kind of work our corporate workshops are built around.

Start with the request you make most often. Write down who it’s for and what they need from it, put that above the ask, and see what changes.

Sana Mian
Sana Mian, Co-Founder of Future Factors AI

Sana is an AI educator and learning designer specialising in making complex ideas stick for non-technical professionals. She has trained 2,000+ learners across corporate teams, bootcamps, and keynote stages. Future Factors offers AI Bootcamps, Corporate Workshops, and Speaking & Consulting for businesses ready to adopt AI without the overwhelm.

More about Sana →

Frequently Asked Questions

Is context the same as a prompt?

They overlap. I’d treat the prompt as the instruction for this request and context as the situation it sits in: who, for whom, why and within what limits. The practical difference is reuse: the instruction changes every time, while most of the situation stays put.

How long should a context block be?

Long enough to change the answer and short enough to read in a minute. Past a page, it’s usually holding detail that belongs in a project file, or nowhere. The keep-or-cut test will tell you which.

Should I just turn memory on and let it learn?

It’s handy for small, stable preferences, and a weak place for anything you need to control, because you don’t always see what it’s drawing on. One detail from OpenAI’s Memory FAQ is worth knowing: deleting a chat doesn’t necessarily delete a saved memory created from it, so review the memory list itself.

Can I use the same context block in ChatGPT, Claude, Gemini and Copilot?

Yes, if you keep it as plain text in a document you control and paste or attach it where you need it. Each tool stores context differently and those features change, so the copy in your own file is the one that survives a tool switch or a product change.

What if my organisation hasn't approved an AI tool for work data?

A context block is still useful, as long as it holds only non-sensitive detail: your role, your audiences described in general terms and your style preferences. Keep client, people and financial specifics out until there’s an approved tool and a policy that covers them.

About This Article

I read these pages on October 21, 2026: Anthropic’s Prompting best practices guide and its Effective context engineering for AI agents post, OpenAI’s help pages on Projects, Memory and how data is used to improve models, the Claude Help Center page on creating and managing projects, and Google’s Use Gems in Gemini Apps page. I also read the abstract of the 2023 Lost in the Middle paper and use it only for the direction of its finding. I left out context-window sizes, prices and plan-by-plan limits, which change often. I did not test these features hands-on for this article. The seven kinds of context, the keep-or-cut test and the monthly audit are Future Factors working methods, not research-validated models, and the scenes are illustrations, not client stories.

Sources

  1. Anthropic, Claude Platform Docs: Prompting best practices (sections Be clear and direct, and Use examples effectively). Read October 21, 2026. https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices
  2. Liu et al., Lost in the Middle: How Language Models Use Long Contexts (arXiv 2307.03172, 2023). Read October 21, 2026. https://arxiv.org/abs/2307.03172v3
  3. Anthropic, Effective context engineering for AI agents (September 29, 2025). Read October 21, 2026. https://www.anthropic.com/research/effective-context-engineering-for-ai-agents
  4. OpenAI Help Center, How your data is used to improve model performance. Read October 21, 2026. https://help.openai.com/en/articles/5722486
  5. OpenAI Help Center, Using ChatGPT Projects. Read October 21, 2026. https://help.openai.com/en/articles/10169521-using-chatgpt-projects
  6. Claude Help Center, How can I create and manage projects? Source for project knowledge, project instructions and availability on free accounts (limited to five projects). Read October 21, 2026. https://support.claude.com/en/articles/9519177
  7. Gemini Apps Help, Use Gems in Gemini Apps. Read October 21, 2026. https://support.google.com/gemini/answer/15146780?hl=en
  8. OpenAI Help Center, Memory FAQ. Read October 21, 2026. https://help.openai.com/en/articles/8590148-memory-faq

Psst, Hey You!

(Yeah, You!)

Want helpful AI tips flying Into your inbox?

Weekly tips. Real examples. Practical help for busy professionals.

We care about your data, check out our privacy policy.