Most people use Claude one question at a time. This weekend you set up five things that keep working after you close the laptop: a page that shows your whole life at a glance, a project that has read every important document you own, an agent that reviews your day, a brand kit that makes everything you publish look like you, and a library of everything you learn.
The plan · 5 builds, 11 prompts, 0 lines of code
- 1Build 1: the Life Dashboard plus the morning brief
- 2Build 2: the Second Brain project
- 3Build 3: the nightly review and the Sunday rollup
- 4Build 4: the brand kit in Claude Design
- 5Build 5: the Life Library
I picked these five because each one changes what Claude is for you. Right now it answers questions. After this weekend it knows your schedule, your documents, your habits, your brand and your reading, and three of the five run on their own. None of it needs code. All of it needs one thing most people skip: a couple of hours of setup, done once.
Two builds use connectors (Claude reading your Google Calendar, Gmail and to-do app). Two run on scheduled tasks, which is Claude doing a job in the cloud on a timer while your computer is closed. One lives in Claude Design. The rest is Projects, which work on every plan.
What Each Build Needs
| Build | Claude feature it runs on | Plan | Setup time |
|---|---|---|---|
| 1. Life Dashboard | Gmail + Google Calendar connectors, a to-do connector, an artifact, one scheduled task | Connectors: all plans. Scheduled task: paid | 45 min |
| 2. Second Brain | A Project with your documents as project knowledge | All plans (Free: up to five projects) | 60 min, mostly finding files |
| 3. Review Agent | Two scheduled tasks + Gmail | Paid (Pro, Max, Team, Enterprise) | 20 min |
| 4. Brand Kit | A design system in Claude Design | Paid (beta) | 30 min |
| 5. Life Library | A Project + one prompt you reuse | All plans | 15 min, then 2 min per book |
Saturday and Sunday
Saturday morning: connect Calendar, Gmail and your to-do app, then Build 1. Saturday afternoon: Build 2, because gathering the documents is the slow part and you want it done while you have momentum. Sunday morning: Build 3, it is twenty minutes, and the first review lands that night. Sunday afternoon: Builds 4 and 5.
Build The Life Dashboard
One page, four sections: what is on today, who is waiting on a reply from you, what is due, and the single most important thing to do. Claude builds it as an artifact that pulls from your connected apps, so it is current every time you open it. Then a scheduled task writes you a morning brief so you do not even have to open it.
Connect the three apps
In any chat, click the + button at the bottom left of the message box, hover Connectors, then Manage connectors. Or go to Customize in the left sidebar, then Connectors. Click +, find the app, click Connect and sign in. Gmail, Google Calendar and Google Drive are available to everyone. For to-dos, Todoist, Notion, Asana and Linear all have official connectors. There is no Google Tasks connector, so if that is where your list lives, move it to Todoist for this weekend (the import takes five minutes).
Start a new chat, open the + menu, and make sure all three are toggled on. On a paid plan, run this in Cowork (or the unified chat, which is now the same thing): artifacts built there are saved to your account and can use your connected apps live.
Prompt 1: Build My Life Dashboard
Build me a life dashboard. Pull my Google Calendar for today and the next 7 days, my Gmail from the last 7 days, and my open tasks in [Todoist]. Build one artifact called My Life Dashboard with four sections. Today: every event with time, place and who, and any gap of 90 minutes or more marked as a focus block. Treat my day as [8am] to [9pm]. Needs A Reply: emails from real people with no reply from me yet, one line each, oldest first. Skip newsletters, receipts and notifications. Tasks: due today, overdue in red, then the rest of this week. The One Thing: the single most important thing to do today and why, in two sentences. Make the artifact read the live data each time I open it so it is always current. If it cannot call my apps live, say so and add a Last Updated line instead of pretending. Do not ask me questions. If an app is not connected, tell me which one and build the rest.
What comes back
Claude reads the three apps, then opens an artifact panel and builds the page. In my test the Today section showed a standup, a dentist visit, a 2pm review and a birthday dinner, with two focus blocks between them. Needs A Reply listed four real people, oldest first, and correctly skipped the newsletters and an Amazon receipt. Tasks had two due today, three overdue in red. The One Thing picked the slide a VP was waiting on for the 2pm meeting, with the reason. That is the whole point: it does not list your life, it tells you what to do first.
Why the prompt says 7 days and 8am to 9pm. The first version of this prompt read 48 hours of email. The oldest unanswered thread, three days old, was exactly the one that mattered and it never showed up. Seven days catches it. The day window stops Claude marking midnight to 9am as a nine-hour focus block. Both came out of testing, not theory.
Prompt 2: The Morning Brief (Scheduled, Daily)
Click Scheduled in the left sidebar, then New task, then Set up manually. Name it Morning Brief, set the frequency to daily and the time to whenever you get up, paste the prompt below, and choose the approval mode Automatically approve so it can send the email without you awake to click yes. Paid plans only. It runs in the cloud, so your laptop can be closed.
Read my Google Calendar for today, my Gmail from the last 3 days, and my open [Todoist] tasks. Write me a brief under 200 words: my schedule in one paragraph, the three emails from real people that most need a reply from me (if fewer than three qualify, say so, do not pad), tasks due today and anything overdue, and the one thing most likely to wreck today with a suggestion. Email it to [YOUR EMAIL ADDRESS] with the subject "Brief: [weekday, date]". Do not reply to anyone, and do not create, move or delete any event or task.
In the test the brief came in at 194 words: schedule in one paragraph with the free windows named, two emails that qualified and a plain note that a third did not, the overdue list, and the risk (walking into the 2pm review without the slide, because the dentist eats the late morning). It reads like a good assistant wrote it before you woke up, because that is what happened.
Build The Second Brain
A Project is a folder inside Claude with its own instructions and its own documents. Everything you drop in is read on every chat inside that project. Put your lease, insurance policies, contracts, warranties and receipts in one project and you can ask "when does my insurance renew" and get the date, the line it came from and the file name, in seconds.
Create the project
Hover the left sidebar, click Projects, then + New Project at the top right. Name it Second Brain. On the project page, the panel on the right is project knowledge: click + to upload files. Free accounts get five projects; every plan gets 30MB per file, and the number of files is not capped as long as they fit. On paid plans, when the project grows past what Claude can hold at once, it switches to searching your documents automatically, so big projects still work.
Gather the documents
| Category | What to upload | Where it usually is |
|---|---|---|
| Home | Lease or mortgage, renters or home insurance declarations page, HOA rules | Email from the landlord or agent, insurer portal |
| Money | Car insurance card and declarations, credit card benefits guide, phone and internet bills | Insurer app (download the PDF), card website |
| Contracts | Gym, storage unit, subscriptions with a term, freelance contracts | Search Gmail for "agreement" and "contract" |
| Stuff you own | Receipts and warranty cards for anything over a few hundred dollars | Search Gmail for "order confirmation" and "warranty" |
Aim for fifteen to thirty documents on day one. Photos of paper documents work: Claude reads the text out of them. Skip anything with numbers you would not want in a chat, like full card numbers or your Social Security number. The brain is for dates, terms and amounts.
Project Instructions: Second Brain
On the project page click Set project instructions, paste this, and save. This is what stops Claude guessing. The line about quoting the exact text is the whole reason you can trust the answers.
You are my second brain. Everything in project knowledge is a real document from my life. When I ask a question, answer from the documents only. Give the date or number plainly first, then quote the exact line you used and name the file. If a document has a deadline that comes before its end date (like a notice period), tell me both. Mark anything already past as expired. When I ask about a deadline, tell me the date and how many days from today; if I forget to give you today's date, ask before counting. If the answer is not in the documents, say "Not in your documents" and tell me which document would have it. Never guess and never fill gaps from general knowledge.
Questions That Work (One Per Message)
Today is [DATE]. When does my renters insurance renew? Today is [DATE]. How much notice do I have to give to move out, and what is the last day I can give it? What is my car insurance deductible? Today is [DATE]. Is my laptop still under warranty? How do I cancel the gym, exactly? What am I paying every month across everything in here?
In the test, all six came back right and each one quoted its line: renewal on November 15 (54 days), notice is 60 days so the last day to give it is October 1 (nine days, with a flag that the lease says "received"), a $500 collision and $250 comprehensive deductible, a warranty that ended five weeks ago, and the gym's certified-mail rule. "What is my passport number" got "Not in your documents". No invented facts, which is the test that matters.
Prompt 3: My Renewals
Today is [DATE]. Build me an artifact called My Renewals: one row per document with what it is, the renewal or end date, days until then, the amount, and the action needed, sorted soonest first. Include notice deadlines as their own rows. Flag anything inside 60 days, mark anything past as expired, and leave out documents with no date.
You get a table of every date in your life with the ones inside 60 days flagged. Re-run it on the first of each month after adding new documents.
Build The Review Agent
The video version is simple: every night Claude asks how the day went, every Sunday it tells you what to change. The catch is that a scheduled task runs with nobody there to answer questions. So the build uses your inbox as the notebook. Every night at 9pm Claude reconstructs your day from your calendar, sent mail and completed tasks, emails you the review with three questions, and you reply in two minutes. Sunday evening it reads the week of threads, including your replies, and writes the analysis.
Prompt 4: The Nightly Review (Scheduled, Daily 9pm)
Scheduled in the sidebar, New task, Set up manually. Name it Nightly Review, frequency daily, time 9pm, approval mode Automatically approve. Paste this.
It is the end of the day. Look at today's Google Calendar events, the emails I sent today, and the [Todoist] tasks I completed and did not complete. Assume calendar events happened unless they were moved or cancelled. Write me a review email under 250 words: what was planned versus what actually happened, what got done, what slipped and your best guess why, then three questions for me to answer by replying: What went well? What did not? What would I do differently tomorrow? Send it to [YOUR EMAIL] with the subject "Review: [Month D, YYYY]". Apply the Gmail label "Daily Review" and create the label if it does not exist. Do not email anyone else and do not change any event or task.
The test review came in at 220 words. It listed the four events, noted the slide got sent at 8:50 before the review, that the tax approval went out a day late, and that the deck review slipped, with a guess: the afternoon went to two other things and the deck needed a bigger block than the day had. It then noticed the two overdue admin tasks had not moved and named the pattern: small, unpleasant, nobody chasing you. Then the three questions. You hit reply and type three lines.
Prompt 5: Week In Review (Scheduled, Sunday 6pm)
Second task. Name it Week In Review, frequency weekly, Sunday at 6pm, Automatically approve.
Find the seven most recent "Review:" email threads in Gmail, including my replies. Write my weekly analysis under 400 words: what I said went well and what did not, the patterns in what slipped (be specific, name the days), where my time actually went by category using the calendar (categories: work meetings, focused work, client, family, health, travel, admin), the three changes for next week with one concrete rule each, and the one thing to stop doing. Email it to me with the subject "Week in review: [date range]". Then, on any review thread I never answered, save a draft (do not send) with the three questions as bullets I can fill in.
The test week had six replies out of seven. The analysis found that the expense report was named on four different nights and never happened, that "first thing tomorrow" was the default fix and it failed every time the morning already held something, and that the two days with a slip were the two heaviest personal days. Time by category: 7 hours of meetings, 7.5 travel, 5 client, 5 family, 0 hours blocked for the work that slipped. The three rules were specific enough to put on a calendar (Monday 8:00 to 8:45 is Admin, expense report first). That is a coach, not a diary.
Why the inbox and not a document. Gmail is the one place both tasks can read and write reliably from the cloud, threads keep your replies attached to the question, and the label makes the whole history searchable. After a month, ask Claude in a normal chat with Gmail on: "read every Daily Review thread from September and tell me what changed."
Maverick's tip
Run each task once by hand from the Scheduled page before you trust the timer. If the first review is thin, it is usually because your calendar is thin; the agent can only see what you put on it, so this build quietly makes you better at keeping a calendar.
Build The Brand Kit
Claude Design (claude.ai/design, paid plans, in beta) makes websites, social posts, one-pagers, email campaigns and decks by conversation. The part that makes it useful is the design system: your colors, fonts and components saved once, then applied to everything new. Give Claude your voice and your values and it builds the kit. You never pick a hex code.
Prompt 6: Build My Design System
You can do this in any normal chat or inside Claude Design. Fill the brackets in one message. Be specific in the "never do" line; it does more work than the rest combined.
Build me a design system I can reuse for everything. Who I am: [NAME, WHAT YOU DO]. Who it is for: [AUDIENCE]. My voice in three words: [WORDS]. My values: [VALUES]. How I want people to feel: [FEELING]. Brands whose look I like: [TWO OR THREE], use them as direction only, do not copy their colors or fonts. Never do: [THINGS YOU HATE]. Give me: a palette with primary, secondary, accent and neutrals as hex codes with one line on why each; two Google Fonts (headline and body) with sizes for H1, H2, body and captions; components: primary and secondary buttons, a card, a section header, a quote block, an Instagram post template, an email header and footer; and my voice rules, five do and five don't. Show it all on one page so I can see it, then save it as my design system.
In the test (a personal finance coach, voice "calm, plain, honest") Claude came back with a deep green primary, a warm sand neutral, one amber accent for calls to action, a serif headline font with a clean sans body, and every component rendered on one page with the reasoning in one line each. The voice rules were the best part: "say the number, then the feeling" and "never write 'unlock' or 'hack'" came straight out of the never-do line.
Save it and check it
Design systems live under Settings, then Design systems. Open yours, read it once, and fix anything with Remix ("make the accent less orange"). You can keep more than one. From now on, every new Claude Design project inherits it automatically, so you never re-explain your look.
Prompts 7 To 9: Use The Kit
Open claude.ai/design and start a new project. Then, one at a time:
# The website Using my design system, build a one-page website for [WHAT YOU DO]: hero with one line and one button, three things I help with, one short story about a client, an email signup, a footer. Copy in my voice rules. Mobile first. # The posts Using my design system and the Instagram template, make five posts for this week. Topics: [FIVE TOPICS]. Each one: a headline under eight words, one supporting line, and a caption under 60 words in my voice. Show all five on one page so I can compare them. # The newsletter Using my design system's email header and footer, write and lay out this week's newsletter. Subject line, a 60-word intro, three sections with headers, one call to action, the footer. Content: [PASTE NOTES OR BULLETS].
Export lives on the share menu: standalone HTML for the site (drop it into any host), PDF or PPTX for decks, and direct handoffs to Canva, Google Slides and others. For the newsletter, export the HTML and paste it into your email tool, or just copy the text and use the colors.
Maverick's tip
One design system, then everything else is a one-line prompt. The reason most people's content looks different every week is that they redesign every week. You just stopped.
Build The Life Library
From today, everything you finish gets a library card: a summary, the five ideas worth keeping, the lines that stuck, how it connects to what you already know, and one action. The cards live in a project, and "what have I learned about focus" answers from your own reading, with sources.
Create the project
Projects, + New Project, name it Life Library. Instructions: "Project knowledge is my library cards. When I ask what I have learned, answer only from the cards, name each source, say if two disagree, and if a card is only loosely related say so or leave it out."
Prompt 10: The Library Card
Inside the project, paste this the moment you finish something. It will not invent quotes.
Log this into my Life Library. What I just finished: [TITLE, AUTHOR OR CREATOR, TYPE: book/article/video/podcast]. Lines that stuck with me: [PASTE OR SAY NONE]. Write me a library card under 220 words: a two-sentence summary, the five ideas worth keeping, the quotes I gave you (none if I gave none), how it connects to anything already in my library, one action I could take this week, and tags. Plain text, title on the first line, so I can paste it straight into my library file.
Copy the card into the project: knowledge panel, +, paste as text, or keep one running Library.txt you re-upload after each entry. Test cards came in under 200 words, five ideas each.
Prompt 11: Search My Library
Search my Life Library: what have I learned about [TOPIC]? Answer only from my library cards, name each source, and tell me if two sources disagree. If a card is only loosely related, say so or leave it out.
With four test cards, "what have I learned about focus" answered from two, named both, left out the negotiation article, and flagged a real tension between 90-minute deep blocks and the two-minute rule. Once a month, ask: "Which five ideas show up most, and which one have I not acted on?" Nobody else read what you read.
Mistakes That Break These Builds
| Mistake | What to do instead |
|---|---|
| Attaching documents to a chat instead of the project | Only the knowledge panel on the project page counts. Chat attachments vanish when the chat does. |
| Scheduling a task that needs a folder on your computer | Cloud tasks can only use connectors and files in your Claude account. Keep it inside Claude. |
| Leaving the approval mode on Manually approve | A scheduled task with nobody there to click yes just stalls. Use Automatically approve for these five. |
| Reading 48 hours of email for Needs A Reply | The oldest unanswered thread is the one that matters. Seven days for the dashboard, three for the brief. |
| Asking the second brain a deadline without today's date | It cannot count days from a date it does not have. Put today's date in the message. |
| Naming a brand and expecting its exact look | Use them as direction only. Claude misremembers other brands' colors and fonts. |
| Not replying to the nightly review | The Sunday rollup is only as good as your three lines a night. Two minutes. |
| Building all five on Free | Projects and connectors are free. Scheduled tasks and Claude Design need a paid plan. Do 2 and 5 first if you are not sure. |
The One-Page Version
| Build | Where | Prompts | Runs itself? |
|---|---|---|---|
| 1. Life Dashboard | Chat with Gmail, Calendar, to-do connected; Scheduled page | 1, 2 | Yes: brief every morning, dashboard live when opened |
| 2. Second Brain | A Project with your documents | Instructions, questions, 3 | No, but it answers in seconds |
| 3. Review Agent | Two scheduled tasks + Gmail | 4, 5 | Yes: 9pm nightly, Sunday 6pm |
| 4. Brand Kit | Claude Design, Settings, Design systems | 6, 7, 8, 9 | Applies itself to every new design |
| 5. Life Library | A Project + a two-minute habit | 10, 11 | Only as fast as you read |
Do this Saturday morning. Connect Gmail and Google Calendar, paste Prompt 1, and look at your own life on one page. Then put Prompt 2 on a schedule for tomorrow at 7am. That is forty-five minutes, and tomorrow morning you will know whether you want the other four. You will.
One weekend of setup. Then Claude does the remembering.