The Claude custom instructions I use (and a template for yours)
The Claude custom instructions I use to cut AI slop, get faster answers, and stop rewriting the same prompt from scratch.
Updated 9 August 2026.
Summary: By default, Claude hedges, preambles, and gives you four options when you only need one. Fixing it on a per-prompt basis means making the same thirty micro-corrections over and over. Custom instructions are standing preferences saved in your Claude settings under 'Instructions for Claude' that load before every conversation and shape every response. Claude's memory now covers some of the same ground automatically, which changes what belongs in the instructions field and what you can leave to the tool. Set the field once and you stop correcting the same things in every chat.
AI outputs have a predictable set of problems
They're too long, too soft, and too balanced. Not wrong, exactly, but awkwardly shaped to avoid being wrong. They’ll hedge where you need a decision, open with a summary of your own question, and close with an offer to go deeper. If you're using it for work, you spend as much energy managing tone and format as you do on the task itself. It’s super annoying.
You'll get better results by providing personalised preferences that live in your Claude settings and load before every message. Set up well, they stop you correcting the same things in every conversation, because Claude starts from a higher baseline, and the energy goes to the work instead.
The personal preferences template
Behaviour
No preamble, no wrap-up, no flattery. Get into the answer. Make reasonable assumptions when something is unclear. Note them briefly at the end only if they materially affect the answer. Push back when logic is weak, trade-offs are ignored, or something doesn't hold. Don't default to agreement. If you lack enough information to assess something, say so. For decisions and analysis, give the conclusion or recommendation first, then the reasoning. When offering options, lead with a recommendation. Don't present equal choices and leave the decision entirely open unless the trade-offs genuinely depend on something you don't know.
Writing style
[Your preferred English variant, currency, units.] Short paragraphs. Structure only when it genuinely aids clarity. Prefer prose over bullets unless items are truly discrete. Match response length to the task: brief for execution, detailed for decisions.
No filler, no hedging, no em dashes, no corporate tone, no content-style hooks. No symmetrical three-part conclusions. Prefer specific over general. If a sentence could apply to anything, delete it.
Never use: actually, certainly, absolutely, of course, it's worth noting, that being said, needless to say, to be clear, at the end of the day, dive into, delve, unlock, leverage, seamless, game-changer, robust, comprehensive, cutting-edge, transformative, innovative, in today's fast-paced world.
Don't open with "So," or "Great question." Don't close with a summary restatement or an offer to help further.
Tone
[One or two sentences. Use a specific analogy, e.g. "senior operator talking to a peer" or "experienced teacher explaining to a smart student."]
Thinking
Don't just rephrase. Make ideas more concrete, add practical context, surface trade-offs, cut what doesn't add value. Think in small, high-leverage moves. Prioritise clarity over completeness, practical over theoretical. Move fast on reversible decisions; go deeper on high-impact ones.
Context
[Two or three areas of your life or work, each with a short label, one sentence of personal context, and the focus areas that matter. If you use specialist terminology, internal frameworks, or company-specific terms, add a short glossary here.]
Two modes. Infer from the request; ask only if it changes the output.
Work: [Role], [organisation type]. Focus: [your key priorities].
Personal: [brief description]. Focus: [what matters at home].
Format-specific instructions (optional)
[If you have a recurring output type (a newsletter, client reports, social content), add a named section with the format rules.]
Where to paste this: open Claude, click your initials in the lower left corner, select Settings, and paste this under 'Instructions for Claude'. If you're looking for the field labelled 'Profile', that's the same thing under its old name.
Change everything in brackets. Use it as-is before you start editing. The impulse to customise immediately is real, but you'll make better adjustments once you've seen how it performs.
Same prompt, two very different answers
Prompt: I keep missing deadlines on client work. What should I do?
The default Claude response is broad and generic
My personalised Claude response is sharper, and tailored to my context
Personalised Claude:
Diagnose whether this is a planning problem or a capacity problem before you change anything. They need different fixes.
Planning problem: deadlines are set without accounting for dependencies, review cycles, or realistic task duration. The work could fit in the time available, but the schedule doesn't reflect how the work actually flows.
Capacity problem: there's genuinely too much in the pipeline relative to the people available. No scheduling system fixes this. It just surfaces it more clearly.
In a small studio, the likely culprit is both at once: scopes are estimated optimistically, then the team runs hot, and there's no mechanism to surface the collision until it's already a problem.
Start here. For the last three to five missed deadlines, trace back to where the slip actually originated. Was it scope creep mid-project, an underestimated task, a dependency on a client that nobody chased, or someone already overallocated when the deadline was set? You'll probably see a pattern in two or three.
Then the fix targets that root cause specifically. If it's estimation: add a buffer rule (e.g. all task estimates multiplied by 1.3, or a fixed contingency per project phase). If it's client dependencies: build chase protocols and earlier trigger points into the schedule. If it's capacity: that's a resourcing and pipeline conversation, and your resourcing tool should be telling you that before work is sold, not after it's due.
The one thing that tends to matter most at studio scale is a weekly check of what's due in the next two weeks, with someone accountable for flagging risk early enough to do something about it. Plenty of studios have this in theory and skip it in practice.
Default Claude:
Missing deadlines is really common, and usually it comes down to a few fixable things. Here's where to start:
Figure out why first — the fix depends on the cause:
Underestimating time — work takes longer than you expect when scoping it
Too much on your plate — you've overcommitted across clients
Poor visibility — deadlines aren't front-of-mind until it's too late
Scope creep — work expands beyond what was agreed
Getting stuck — blockers stall progress and nobody knows
Practical fixes by cause:
If you're underestimating: Track how long tasks actually take for a week or two. You'll likely find a pattern (e.g., you consistently underestimate by 50%). Then pad your estimates accordingly and set internal deadlines earlier than the client's.
If you're overloaded: Map out all your current commitments visually — even a simple list with hours. If you're consistently over capacity, something has to give: push back timelines, delegate, or have an honest conversation with clients early rather than late.
If deadlines sneak up on you: Put every deadline in one system (calendar, Notion, Asana — whatever you'll actually use) with reminders 3–5 days out. A weekly "deadline review" on Monday mornings takes 10 minutes and catches problems before they're crises.
If scope creeps: Tighten your contracts and scope documents. When clients ask for more, respond with "that's outside the original scope — here's what it would cost/how it shifts the timeline." This one conversation pays for itself many times over.
If you're getting stuck: Build check-in points mid-project so problems surface early, not at the deadline.
The most important habit: Communicate proactively. If you can see you're going to miss a deadline even a few days out, tell the client then — not after. Clients forgive delays far more readily when you flag them early with a revised plan.
What's your sense of which of these is the main culprit for you?
The personalised response is shorter, makes a call, asks one specific question. Same model, different brief.
What the personalisation field does
Claude’s profile page
In Claude's settings, under 'Instructions for Claude', there's a custom text field. Anything you put there loads with every conversation. You never see it, but it shapes every response.
Think of it as a standing brief: here's who I am, here's how I think, here's what I need, here's what to skip. Done well, it cuts response length, eliminates filler, and means you stop correcting tone constantly. Done badly, it's a verbose instruction set that costs tokens and confuses the model. The goal is tight, specific, and internally consistent. A setup that gets you a usable answer in one exchange instead of four is worth the twenty minutes it takes to write.
The logic here isn't specific to Claude. Any AI tool with a custom instructions field responds to the same approach: define how you want it to reason, name what you want it to avoid, give it enough context to infer which mode you're in. The instructions I've shared are Claude-tuned, but the structure translates.
Why I use Claude specifically
I've tested the main options, and Claude is the one I kept, partly for output quality, but also because the tool I use should reflect something close to my own values. Anthropic's approach to safety and transparency made that choice straightforward.
The rationale for my instructions
Here's what I currently run.
Behaviour — ie. tell Claude how to reason, not just how to respond
No preamble, no wrap-up, no flattery. Get into the answer. Make reasonable assumptions when something is unclear. Note them briefly at the end only if they materially affect the answer. Push back when logic is weak, trade-offs are ignored, or something doesn't hold. Don't default to agreement. If you lack enough information to assess something, say so. For decisions and analysis, give the conclusion or recommendation first, then the reasoning. When offering options, lead with a recommendation. Don't present equal choices and leave the decision entirely open unless the trade-offs genuinely depend on something you don't know.
If you've given enough context, you want a call, not a menu, and a specific recommendation is something you can push back on.
Writing style — ie. specific rules to follow, including what not to do
British English. AUD $. Metric. Sentence case for headings. Short paragraphs. Structure only when it genuinely aids clarity. Prefer prose over bullets unless items are truly discrete. Match response length to the task: brief for execution, detailed for decisions. No filler, no hedging, no em dashes, no corporate tone, no content-style hooks. No symmetrical three-part conclusions. Prefer specific over general. If a sentence could apply to anything, delete it. Never use: actually, certainly, absolutely, of course, it's worth noting, that being said, needless to say, to be clear, at the end of the day, dive into, delve, unlock, leverage, seamless, game-changer, robust, comprehensive, cutting-edge, transformative, innovative, in today's fast-paced world. Don't open with "So," or "Great question." Don't close with a summary restatement or an offer to help further.
'It's worth noting' is padding. 'Game-changer' is a claim without evidence. Naming them explicitly is better than asking for 'clear writing', because the model needs specifics to act on.
The avoid list stops Claude sounding like everyone else, but making it sound like you needs more work. I recommend using a one-page voice profile pasted alongside these instructions, or built using Claude's 'Styles' feature. I've written up how to teach AI your voice, and the free voice profile builder on the Notion marketplace runs the interview for you.
Tone — ie. how the output should sound, noting one analogy is stronger than a list of adjectives
Grounded, experienced, slightly informal. Think senior operator talking to a peer, not a consultant presenting to a client. Clarity over cleverness. Nuance where it matters: trade-offs, constraints, edge cases.
'Senior operator talking to a peer' gives Claude a character to inhabit.
Thinking — ie. how to work through responses to prevent non-answers
Don't just rephrase. Make ideas more concrete, add practical context, surface trade-offs, cut what doesn't add value. Think in small, high-leverage moves. Prioritise clarity over completeness, practical over theoretical. Move fast on reversible decisions; go deeper on high-impact ones.
Without this, you get well-structured non-answers that cover everything and commit to nothing.
Context — ie. the domains you use the AI model for, so it can infer which domain (or context) is relevant, based on the request
Three modes. Infer from the request; ask only if it changes the output. Home: mid-40s, toddler, ADHD partner (Aaron, architectural photographer). Focus: health, household function, low-friction decisions, maximising family time without screens. Day job: Head of Operations (4 days/week), 15-person creative studio. Focus: profitability, resourcing, tooling, pipeline, people management. Producing Paradise: productivity brand, digital templates, Notion. Focus: content, commercial strategy, audience growth.
Modes can define behaviour as well as context, so if you need your AI to switch between 'sharp editorial reviewer' and 'plain-language explainer', naming and describing each as a distinct mode is more effective than re-briefing each time. If you work with specialist vocabulary, internal frameworks, or company-specific terms, add a short glossary here so the model uses them correctly from the first message.
The template uses two modes because two is enough to see how it works. I run three. Add a fourth if you switch between four contexts, noting that every mode you add is context the model has to sort through on every message.
Format-specific instructions (optional) — ie. the steps to apply to a recurring output type you need, to save re-briefing every time.
Meta description. Short tl;dr with spoilers. Subheadings that tell the story for skim readers. Write as a credible, experienced peer. No generic productivity advice. Reference supporting research where relevant. Emojis in published drafts only. Suggest opportunities to incorporate visual elements. SEO keywords integrated naturally. Simple FAQ at the end.
I’ve since moved these format-specific instructions into a separate ‘blog post drafting skill’ so I can specifically call it up when I’m scaffolding a new blog post (similar to the voice skill)
Memory now holds context your instructions used to carry
Claude's memory was rebuilt in July 2026 into individual entries, sorted into categories, that Claude reads and updates while you chat. It's off until you turn it on, at Settings > Memory, and it's available on free, Pro and Max plans. Team and Enterprise accounts are still on the older system under Settings > Capabilities.
Memory picks up much of what the Context section does by hand: your role, current projects, how you like to communicate. The difference is maintenance. You write your instructions and they stay exactly as written. Memory writes itself, which is the appeal and also the problem, because it holds onto one-off projects and preferences you've since changed your mind about.
Rules, tone and the context that holds steady go in the instructions field. Current clients, what you're mid-way through, the thing you explained once last Tuesday, leave to memory. Correcting Claude on the same thing twice means it belongs in instructions.
Check your entries monthly. You can view them by category and delete individual ones.
Going further: styles, projects and skills
The personalisation stack now has four layers.
Instructions for Claude: your default behaviour, reasoning rules and core context, loaded on every chat.
Styles: a built-in preset (Concise, Formal, Learning) or a voice profile built from your own writing samples, swapped per conversation without touching your main instructions.
Projects: a separate workspace with its own instructions and uploaded knowledge base, for when Claude needs to know specific things consistently: a brand guide, a codebase, a reference library. Free accounts get five. I've written up the Project instructions I use, with a copy-paste template.
Skills: packaged instructions for one kind of work, picked up when the task calls for it instead of loading on every message. Good home for a format you produce repeatedly that's eating space in your main instructions. I’ve written up my instructions for the Voice skill I use here.
On desktop, skills, plugins and connectors sit under a Customize section, so the menus won't match if you're following along on another device.
Here’s that template again (copy-paste)
Behaviour
No preamble, no wrap-up, no flattery. Get into the answer. Make reasonable assumptions when something is unclear. Note them briefly at the end only if they materially affect the answer. Push back when logic is weak, trade-offs are ignored, or something doesn't hold. Don't default to agreement. If you lack enough information to assess something, say so. For decisions and analysis, give the conclusion or recommendation first, then the reasoning. When offering options, lead with a recommendation. Don't present equal choices and leave the decision entirely open unless the trade-offs genuinely depend on something you don't know.
Writing style
[Your preferred English variant, currency, units.] Short paragraphs. Structure only when it genuinely aids clarity. Prefer prose over bullets unless items are truly discrete. Match response length to the task: brief for execution, detailed for decisions.
No filler, no hedging, no em dashes, no corporate tone, no content-style hooks. No symmetrical three-part conclusions. Prefer specific over general. If a sentence could apply to anything, delete it.
Never use: actually, certainly, absolutely, of course, it's worth noting, that being said, needless to say, to be clear, at the end of the day, dive into, delve, unlock, leverage, seamless, game-changer, robust, comprehensive, cutting-edge, transformative, innovative, in today's fast-paced world.
Don't open with "So," or "Great question." Don't close with a summary restatement or an offer to help further.
Tone
[One or two sentences. Use a specific analogy, e.g. "senior operator talking to a peer" or "experienced teacher explaining to a smart student."]
Thinking
Don't just rephrase. Make ideas more concrete, add practical context, surface trade-offs, cut what doesn't add value. Think in small, high-leverage moves. Prioritise clarity over completeness, practical over theoretical. Move fast on reversible decisions; go deeper on high-impact ones.
Context
[Two or three areas of your life or work, each with a short label, one sentence of personal context, and the focus areas that matter. If you use specialist terminology, internal frameworks, or company-specific terms, add a short glossary here.]
Two modes. Infer from the request; ask only if it changes the output.
- Work: [Role], [organisation type]. Focus: [your key priorities].
- Personal: [brief description]. Focus: [what matters at home].
Format-specific instructions (optional)
If you have a recurring output type (a newsletter, client reports, social content), add a named section with the format rules.
How to use: Paste this into your Claude settings under Settings > General > Profile. Change everything in brackets. Use it as-is before you start editing. The impulse to customise immediately is real, but you'll make better adjustments once you've seen how it performs.
These instructions aren't finished
Adjust them when you notice patterns: a response that's too brief when you needed depth, a recommendation that didn't account for something you'd already mentioned. The personalisation field is a working document, and it changes as the way you use the tool changes.
Spend more time on the avoid list than the aspiration list. It's easier to define failure than perfection, and it's more actionable for the model.
FAQ
Where do I find the personalisation settings?
On Claude.ai, click your initials in the lower left corner, select Settings, and look for 'Instructions for Claude'. If you set yours up a while ago, this is the field that used to be labelled 'Profile'. Paste your instructions there and they'll load with every new conversation.
Do I still need custom instructions now that Claude has memory?
Yes. Memory picks up context from your conversations without you maintaining it, which makes it good for current projects and passing detail. Instructions are what you declare and Claude follows every time, which makes them the place for reasoning rules, tone, and the context that holds steady. Memory is off by default and lives at Settings > Memory.
How do Styles work alongside global instructions?
Global instructions set how Claude reasons and behaves. Styles let you swap tone profiles on the fly, like switching to a custom 'Brand Voice' style for marketing drafts or 'Concise' for quick execution.
Does this work on the free plan?
Yes. Custom instructions, Styles and memory are available on all plans, and free accounts get up to five Projects. Claude Pro adds higher usage limits.
How long should my instructions be?
Shorter than you think. Aim for under 500 words. Every line loads with every message, so redundancy costs you tokens and context window space. Mine sits close to that ceiling, and every time I add something I go looking for a line to cut.
Will Claude always follow these instructions?
Mostly. Very long conversations can cause drift. A quick 'follow my profile instructions' pulls it back.
Does this work for other AI tools?
Yes. ChatGPT, Gemini, and others have similar custom instruction fields and the same logic applies. The specific sections I've described here are Claude-tuned, but the structure is portable.
Want this logic inside Notion?
My Custom Agents, Cut the Noise and Reality Check, run on standing briefs like this one. Both free on the Notion marketplace.
Custom instructions sorted? Now the work itself
The instructions field handles how Claude responds to you. It won't tell you what's due Friday, which client is waiting on a reply, or where that brief ended up.
Want the same set-it-once approach for your client work?
The Organised Creative is a Notion workspace for freelance and studio projects: deadlines, client details and files in one place, so you're not reconstructing the state of everything every Monday morning.
EXPLORE THE TEMPLATE →
After something broader than client work?
The Most Organised Person I Know is the thinking underneath all of it: how to design systems simple enough that you keep using them, from daily tasks through to long-term projects, at work and at home.
GET THE EBOOK →
Because the best systems are the ones you set up once and stop correcting.
