Guided build · a weekend
Weekly report autopilot
Builds your recurring report from spreadsheets — automatically, on schedule.
No commands. No code. You're about to build this by SAYING what you want — in your own language. The only skill is describing the result well. Here's the whole thing, start to finish.
Builds your recurring report from spreadsheets — automatically, on schedule.
First, how to actually talk to the agent
- 1Describe the RESULT, not the tech: what's on screen, what each button does, what gets saved. The agent handles the 'how'.
- 2Be concrete about screens and fields — 'a form with amount, category and date' beats 'let me add expenses'.
- 3Ask for the smallest working version first. You grow it by talking afterwards — that's Step 2, not the first message.
- 4Decide what's YOURS, not the agent's: name the categories, colours, rules. Don't make it guess what only you know.
Step 1 — Build it live
Prompting for this kind of tool
- 1Nail THREE things: that you DEFINE your fields once (labels like 'Revenue', 'New clients', 'Issues closed'), that each week you open a FRESH entry and type this week's numbers into those exact labels, and that it assembles the report in your fixed format with a +/- change versus last week on each metric.
- 2Decide the format yourself — give Claude the exact wording and order you send your report in, or it'll invent a layout your boss has never seen.
- 3Spell out that every past week is SAVED in a list on your device so you can compare, and that 'copy report' gives clean text ready to paste — don't leave saving vague or each week overwrites the last.
- 4Always end with the magic line: 'build the whole thing and tell me exactly how to open it; don't stop to ask questions.'
claude --dangerously-skip-permissions
Open the terminal and run this (if Claude is already running, type /exit first). Then ask it to make a folder for this project and work inside it.
✕ what most people type
you ▸ automate my job
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a weekly report builder. First I define my report's
fields once (labels like 'Revenue', 'New clients', 'Issues
closed'); each week I open a fresh entry, type this week's
numbers into those labelled fields, and it assembles my report
in my fixed format with each metric showing the +/- change
versus last week. A 'copy report' button gives me clean text
ready to send, and every past week is saved in a list on my
device so I can compare. Clean, readable look. Build the whole
thing and tell me exactly how to open it; don't stop to ask
questions.Say it in YOUR language — Russian, Spanish, anything. Claude understands.
Build it now — tick as you go
0/6Step 2 — It's built. Now make it yours
Don't panic at the techy link. Claude tells you one of two things. Either a file like index.html — find it in your project folder and double-click it; it opens in your browser. Or a web address starting with http://localhost — copy it into your browser's address bar and press Enter. 'localhost' just means 'this is running on your own computer right now'. That's your tool. It's real.
Now tweak it until YOU like it — just talk
This is the part that makes it YOURS. Don't accept the first version — change it by saying what you want, right there in the same chat. Claude rebuilds and you refresh. Keep going until it fits how you actually work. For this tool, try things like:
you ▸ pull the numbers straight from my Google Sheet you ▸ email me the finished report every Monday morning you ▸ show the change versus last week as +/- percentages
I don't type long messages. I open voice-to-text (the mic in ChatGPT, or your phone keyboard), and just TALK through everything I think about what it built — what's wrong, what I want next — then select-all, copy, and paste the whole brain-dump into Claude Code. Messy spoken thoughts work fine; the agent sorts them out. It's several times faster than writing.
Step 2.5 — Test it like a real thing (it won't be perfect first try)
The truth no one tells beginners: the first build is a DRAFT. The agent makes something, you run it, you find what's off, you tell it — and THAT loop is the actual work. Don't read the code. Use the tool like a stranger would and watch where it lets you down. For this tool, check exactly this:
- 1Open it (Claude gives a localhost link or an index file — see Step 2) and define three fields with your own labels.
- 2Add 'this week' with some numbers, copy the report and paste it: is it in your fixed format with your labels in the right order?
- 3Add a SECOND week with different numbers — does each metric now show the +/- change versus last week, and is the math right?
- 4Open last week from the saved list — are its numbers untouched, separate from this week's?
- 5Refresh the page (F5 / Cmd-R). Are all your saved weeks still in the list? If they vanish, 'saves on my device' isn't wired up — fix that next.
Found something wrong? Say it like this
You fix nothing yourself — you DESCRIBE what's wrong in plain words and the agent fixes it. Be specific: what you saw vs. what you expected. Real examples for this tool:
you ▸ 'the +/- change is wrong — compare each metric against the most recent earlier week, not a random one' you ▸ 'when I add a new week it overwrites last week — keep every week as its own saved entry' you ▸ 'the copied report isn't in my format — use exactly this layout and wording: [paste your real report]'
Don't stop at v1 — grow it
A tool you built in ten minutes is a starting point, not the finish line. The people who get hooked keep saying 'now also…'. Each line below is one sentence you paste into the same chat to level this tool up:
you ▸ 'pull this week's numbers straight from my Google Sheet instead of me typing them' — kills the manual data entry (this connects to the Google Sheets API — see APIs). you ▸ 'email me the finished report every Monday morning automatically' — it goes from a tool you open to one that just shows up. you ▸ 'add a small chart of each metric over the last 8 weeks' — the trend tells more than one week's number. you ▸ 'write a one-line plain-English summary of what changed this week at the top' — your boss reads the headline first (this uses an AI service like Claude — see APIs).
Step 3 — Connect it to the world (optional)
Free data & APIs for this one
An API is just how your tool pulls in outside data or sends things out — many are free. You rarely need to research them yourself; the move that works for ANY idea is to ask the agent to find them:
- 1To start you need NO external API — defining fields, typing numbers and the +/- math all run locally on your device.
- 2Want it to pull numbers automatically instead of typing them? Connect the Google Sheets API (free) — ask Claude: 'wire this to read this week's numbers from my Google Sheet and show me how to give it access.'
- 3Want it emailed every Monday, or a written summary at the top? Gmail (free) sends it; an AI service like Claude (needs a key) writes the summary — or ask Claude: 'find free or open APIs that fit a weekly-report tool and tell me which actually need a key.'
About paying for the AI parts
- 1You don't pay for Claude twice. With a Claude subscription you create an API key right in the terminal and use it inside your projects — within your plan.
- 2From June 15 the rule splits: automation through that key gets its own monthly credit — about $20 on Pro, $100 or $200 on Max. Stay under it and it works as before.
- 3Run out and you pay per use (pay-as-you-go); unused credit doesn't roll over. So check your account and see whether the included credit already covers what you're building.
A tool gets superpowers when it can talk to other services — send you a message, read a sheet, pull live data. Each service hands out an 'API key' (a long password that says 'this is me'). For THIS tool, the useful ones are:
Which keys this tool can use
- 1Google Sheets — pull this week's numbers straight from your spreadsheet
- 2Gmail — email yourself (or your boss) the finished report every Monday
Getting any key is the same recipe: log into the service → find Settings → 'API' or 'Developers' → 'Create key' → copy it → paste it to Claude once ('here's my key: …'). Claude stores it and you never touch it again.
Step 4 — Put it online (only if someone else needs it)
Just for you, on your computer? You're already done — skip this step with a clear conscience. Put it online only if someone ELSE should open it, or you want to reach it from your phone away from home.
Step 6 — Stay safe (two easy habits)
- 1Back up anything you'd hate to lose. If the tool holds real data (your budget, health log, client list), ask Claude early: 'add an export/backup button' — one click saves your data to a file. Do it before you ever rebuild from scratch or move the folder.
- 2Don't hand Claude the keys to dangerous rooms. Keep it pointed at this project's own folder. Never connect a learning project to your bank, your crypto, or anything irreversible. Receipts and calendars — yes. Savings — no.
- 3Think before you ask. Claude does what you say in the folder you're in. 'Optimize my photos' optimizes them; it won't delete them — unless you ask for something reckless. Sane requests, clean workspace, and there's simply nothing scary left.
The mistakes that stop most people
- 1Asking for something vague ('make me an app') and getting something vague back. Name the screens, the buttons, what gets saved.
- 2Cramming in ten features at once. Ask for the tiniest working version first — then grow it with follow-up requests.
- 3Stopping at the first error. An error isn't failure — paste it to Claude or describe what you see, and it fixes it. That loop IS the work.
- 4Deciding you need to 'learn programming first'. You don't need to understand the code Claude writes. You need to describe the result.
- 5Forgetting the magic line — 'build the whole thing, don't stop to ask questions' — then wondering why it keeps pausing.
- 6Building for an imaginary audience. Build the version YOU will open tomorrow. Polish never; use immediately.
Normal. Tell Claude what's wrong in plain words ('the button does nothing', 'the page is blank') or paste the red error text. It finds and fixes it. You check. Repeat until it works.
That's it. You built a real tool.
Notice what just happened: no commands, no code — words. This is the entire skill. The people who 'can build things' are just people who describe what they want and let Claude do the typing.
More to build