All classes Claude from Zero to Expert Syllabus · Episode 35 of 100

Claude from Zero to Expert Class #35: Setting Response Style and Personal Preferences

0 views

Learn to set up Claude to answer the way you need: the difference between profile preferences, response styles, Project instructions, and regular prompts, writing effective personal preferences, choosing a built-in style, creating your own style from writing samples, then testing and maintaining them. Episode 35 of 100, Session 7: Daily Productivity.

Software: Claude
Level: Beginner
Duration: ± 8 min
Series total: 15 h 1 min · 100 videos
Published: October 28, 2026

Episode 35 of 100 · view syllabus

Subscribe ▶ Watch the video lesson0 plays

Checking access...

Want to go deeper?

Join one of our courses or ask us directly on WhatsApp.

View the full 100-episode syllabus View Claude AI Courses Ask on WhatsApp

Recommended classes for you

Picked from the software, topic, and level of “Claude from Zero to Expert Class #35: Setting Response Style and Personal Preferences”.

50 episodesFree preview

Agentic AI · Beginner–Intermediate

Agentic AI Without Coding

50 video lessons with PDF guides, 14 h 29 min in total. Starts with: Chatbots, Automation, and AI Agents: What's the Difference?.

14 h 29 min 66 0

View class

18 episodesFree preview

Python · Beginner–Advanced

Machine Learning Python

18 video lessons with PDF guides, 3 h 41 min in total. Starts with: Introduction to Machine Learning & First Model.

3 h 41 min 61 0

View class

6 episodesFree preview

Python · Intermediate–Advanced

Brain Tumor Segmentation with U-Net

6 video lessons with PDF guides, 1 h 10 min in total. Starts with: Brain MRI Dataset & Tumor Mask: Loading, Visualization & Patient-wise Splitting.

1 h 10 min 28 0

View class

Deep Learning CNN-LSTM Pneumonia Detection

6 episodesFree preview

Python · Intermediate–Advanced

Deep Learning CNN-LSTM Pneumonia Detection

6 video lessons with PDF guides, 57 min in total. Starts with: Chest X-ray Dataset: Loading, Exploration & Data Splitting.

57 min 22 0

View class

Need more than a video?

Other ways we can help with Claude.

Learn with a mentor

Scheduled AI & Machine Learning courses with live guidance and a certificate.

Course

Midjourney Course: Create Stunning AI Images from Text

★ 4.9

Course

DALL-E Course: Creating Professional AI Images from Text

★ 4.9

Course

Stable Diffusion Course: AI Art from Beginner to Professional

★ 4.9

See all in AI & Machine Learning →

Have it built for you

No time to learn Claude? Our team can do the project for you.

Service

AI Image Creation with Stable Diffusion — Unlimited Custom Visual Production

★ 4.9

Service

AI Image & Video Creation with Leonardo AI — All-in-One Visuals for Business

★ 4.9

Service

AI Image Creation with Midjourney — Cinematic AI Art for Business

★ 4.9

See all in AI & Machine Learning →

Get notified about new Claude classes

At most one email a week. Unfollow anytime with one click.

Transcript

The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.

Show transcript

Introduction

Hi, and welcome to the last episode of the Daily Productivity session. So far we've often typed the same requests: keep it short, use plain English, don't be too formal. In this episode we set Claude up just once, through personal preferences and response styles, so it answers the way we like in every conversation.

Step 1: Four layers of settings

When do we need to set preferences? The first sign: you repeat the same request every day, such as keep it short, use plain English, and no emoji. The second sign: Claude's answers are often too long or too short, so you have to trim them or ask again. The third sign: the tone doesn't fit. Too stiff for replying to customers, or too casual for a report to your boss. All three problems can be set up just once. Take Laras, for example. Every morning she retypes the same sentence: I own Sunset Coffee, answer in a casual tone. Fifteen seconds isn't long, but done dozens of times a day, it adds up. Before setting anything up, get to know the four layers of settings. The first layer is personal preferences. They apply to every conversation, for example who you are and the language you use. The second layer is the response style. A style controls how Claude writes, for example concise or full of explanation, and you can switch it at any time. The third layer is Project instructions, which we learned in the Projects session. Those rules apply only inside one Project, such as Sunset Coffee's customer reply rules. The fourth layer is a regular prompt in the chat. It applies only to that conversation, for one-off tasks. The rule is simple: what's always true about you goes into preferences, how to write goes into a style, rules for one job go into a Project, and a one-time request just goes in the chat.

Step 2: Writing personal preferences

Step two is writing personal preferences. Here's Dewi's example, in four parts. First, her role: an operations manager who often writes emails, reports, and meeting minutes. Second, the format: plain English, start with the main point, then details if needed, and use tables for data. Third, the constraints: no emoji in office documents, and if information is missing, Claude must ask first instead of guessing. Fourth, the goal: results she can send right away after reading them through once. A goal like this helps Claude judge how polished the answer needs to be. These preferences go into the settings menu, in the profile section. The screen in this video is a simulation, and menu names may differ slightly because Claude is updated often. First, Dewi fills in what Claude should call her. Then her work: operations manager at an office stationery distributor. In the preferences box, Dewi pastes a summary of those rules. Once saved, these rules carry over into every new conversation without being retyped. One important warning: don't write sensitive data here, such as bank account numbers, your home address, or passwords. Preferences only need to describe how you work. After saving, Dewi opens a new conversation to test it. She writes just one short sentence: write an email to the paper supplier about a late delivery. No extra rules. Claude doesn't start writing right away. Following her preferences, it first asks for the supplier's name, the order number, and the deadline. It also says the email will open with the main request, with no emoji. This is the sign that preferences are working. Dewi didn't type any rules, yet Claude already follows the way she works. Compare that with before, when the same rules had to be typed every morning.

Step 3: Choosing a response style

Step three is choosing a response style. Claude usually offers several built-in styles. The normal style suits most work. The list of styles in your app may be slightly different. The concise style suits busy moments when you only need the core answer. The explanatory style suits learning a new topic, like in the previous episode, because Claude includes the reasons and the steps. The formal style suits official letters and reports to your boss. You can pick a style near the chat box and switch it at any time in the middle of your work. So a style doesn't change who you are in Claude's eyes. It only changes how Claude delivers the answer, just as we speak differently to customers, bosses, and friends. Let's see the difference. Dewi uses the concise style and asks why deliveries to the Sinar store were late, with the data included. The answer is just two sentences: three causes and the biggest one. That's enough for Dewi herself while she's in a hurry. Then Dewi needs an explanation for the Sinar store. She switches to the formal style and asks for an explanatory paragraph. The content is the same, but the tone changes completely. There's an apology, a polite explanation, and a fix. One set of data, two styles, for two different readers.

Step 4: Creating your own style from samples

Step four is creating your own style. Nadia, a social media freelancer, wants Claude to write like her. She gives it her three best captions for small business clients. Claude reads all three samples and looks for patterns in her writing. The result is four features: a light question to open, casual language that speaks straight to the reader, just enough emoji, and always a clear call to action at the end. The style is saved as Nadia Casual. Pick samples that truly represent your voice. If the samples are a mixed bag, the resulting style will be a mixed bag too. Now Nadia tests her style on a real task: a cold brew caption for her client, Sunset Coffee. The result feels like Nadia's own writing. It opens with a light question, has one emoji, mentions the price, and ends by inviting people to order via DM. Nadia gives just one correction for this client: replace gonna with going to. A small adjustment like this can be saved into the style, or simply written in a Project instruction just for that client. With her own style, Nadia saves a lot of time. She no longer rewrites Claude's results to make them sound like her.

Step 5: Test and maintain your settings

The last step is testing and maintaining. After changing your preferences or style, test them with three real questions from your daily work. If the results aren't right yet, change one rule at a time. That way, you know which rule made the difference. Update your settings when your role or work changes. Preferences written a year ago may no longer fit. Remember too that a request in the chat can still change the direction of an answer. If your preferences say concise, you can still ask for a long explanation for one question. And once again: don't write sensitive data in your preferences, including in writing samples for a style. Remove customer names and numbers from any samples you use first. Let's sum up the four layers. Preferences hold who you are, your language, and the limits that always apply. A style controls how Claude writes, and you can switch it to suit the reader. A Project holds the rules for one particular job. And a prompt in the chat is for one-time requests. With these four layers set up neatly, Claude becomes an assistant that knows how you like things, and your daily work routine feels much lighter.

Done!

We've finished the Daily Productivity session: weekly plans, meeting minutes, brainstorming, learning new topics, and now preferences and response styles that help Claude understand how we like things. In the next episode we move up to the intermediate level in the Intermediate Artifacts session, starting with an interactive sales dashboard built from your own business data. See you there!

Practice exercises

Try these on your own after watching to lock in what you learned.

Write personal preferences covering your role, language, answer length, and things to avoid
Ask the same question in two different styles and compare the results
Create your own style from your three best writing samples, then test it on one real task

Ask the class material

Type a question or keyword; we find the part of this episode that explains it and jump the video there.

My notes

Notes are saved with the current video time and are only visible to you.

Questions & answers

Stuck on a step? Ask here; the instructor and other learners can answer.

No questions yet.

Your instructor

Cerdas Inovasi Digital Team

Software developers, BIM & 3D engineers, and AI practitioners

53 video classes1,296 episodes

We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.

See our clients →

Memuat

Claude from Zero to Expert Class #35: Setting Response Style and Personal Preferences

0 views

Software

Claude

Level

Beginner

Duration

± 8 min

Series total

15 h 1 min · 100 videos

Published

October 28, 2026

Episode 35 of 100 · view syllabus

▶ Watch the video lesson0 plays

Transcript

The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.

Show transcript

Introduction

Step 1: Four layers of settings

Step 2: Writing personal preferences

Step 3: Choosing a response style

Step 4: Creating your own style from samples

Step 5: Test and maintain your settings

Done!

Practice exercises

Try these on your own after watching to lock in what you learned.

Write personal preferences covering your role, language, answer length, and things to avoid

Ask the same question in two different styles and compare the results

Create your own style from your three best writing samples, then test it on one real task

Your instructor

Cerdas Inovasi Digital Team

Software developers, BIM & 3D engineers, and AI practitioners

53 video classes1,296 episodes

See our clients →

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

0:24Step 1: Four layers of settings

1:59Step 2: Writing personal preferences

3:56Step 3: Choosing a response style

5:19Step 4: Creating your own style from samples

6:35Step 5: Test and maintain your settings

7:47Done!

Practice exercises

Ask the class material

My notes

Questions & answers

Your instructor

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

0:24Step 1: Four layers of settings

1:59Step 2: Writing personal preferences

3:56Step 3: Choosing a response style

5:19Step 4: Creating your own style from samples

6:35Step 5: Test and maintain your settings

7:47Done!

Practice exercises

Ask the class material

My notes

Questions & answers

Your instructor

Introduction

Step 1: Four layers of settings

Step 2: Writing personal preferences

Step 3: Choosing a response style

Step 4: Creating your own style from samples

Step 5: Test and maintain your settings

Done!

Introduction

Step 1: Four layers of settings

Step 2: Writing personal preferences

Step 3: Choosing a response style

Step 4: Creating your own style from samples

Step 5: Test and maintain your settings

Done!