FREE PRACTICAL AI LEARNING · LEARN BY DOINGNO SIGNUP NEEDED · YOUR WORK STAYS YOURS
Open PracticePRACTICAL AI ENGINEERING
EARN BY DOING · BUILD 10 · REPORTING & DATA

Build a weekly business report

Owners drown in data and still cannot answer “was this a good week?”. A weekly report picks four or five numbers that drive decisions, calculates them the same way every week and fits on one screen. You will choose the measures, write the formulas, test them against hand counts and design the one-page summary.

⏱ About 20–30 minutes to draft · the real-world steps take days · Works with or without AI · No signup

You will make

  • Report
  • Formulas
  • QA tests

You will practise

  • Choosing a few measures that lead to decisions
  • Writing formulas that are tested, not trusted
  • Presenting numbers an owner understands in a minute

Download the practice pack (.zip)See a finished exampleOffer contract (.md)

No AI key needed. The guided template works for everyone.

  1. 1Brief

    Specific answers make better results — with or without AI.

  2. 2Make

    Pick a route. The template gives you a structure with [[blanks]] to fill in yourself. Your own key drafts it for you — then you still check it.

    See the exact prompt — copy it into any AI chat you already use

  3. 3Check

    The same rules run on every draft, human or AI. Most first drafts fail something — that is the point.

      Self-check — judgement no checker can make
    • 4Improve

      Fix one item at a time, then check again. Notice which fixes made it better — that is the skill.

      1. Run the check first.
    • 5Ship

      Use it for real: send it, post it or save it. Record what happened — that is your evidence of learning.

    A finished example

    The business, people and numbers are invented. It passes every check above, so you can see what “done” looks like before you start.

    Show the worked example
    > Worked example. The business, people and numbers are invented to show the shape of a finished deliverable.
    
    # Weekly report: a small grocery shop
    
    ## Measures
    Decisions each week: what to restock, whether to stay open later on Fridays, which supplier to pay first.
    
    - Sales this week vs last week · informs: whether the week was normal · formula: SUMIFS on the Amount column by week
    - Top 10 items by quantity · informs: what to restock · formula: a pivot of Item by Quantity, top 10
    - Sales after 18:00 on Friday · informs: whether to stay open later · formula: SUMIFS with a time condition
    - Supplier bills due within 7 days · informs: who to pay first · formula: FILTER on the Bills tab by due date
    
    Candidates I dropped, and why: "customers per day", because the notebook does not record it.
    
    ## Formulas
    Data comes from: a sales notebook copied into a sheet each evening
    ```
    =SUMIFS(Sales!C:C, Sales!A:A, ">="&B1, Sales!A:A, "<"&B1+7)
    =SUMIFS(Sales!C:C, Sales!A:A, ">="&B1, Sales!B:B, ">=18:00", Sales!D:D, "Fri")
    =FILTER(Bills!A:C, Bills!C:C <= TODAY()+7)
    ```
    
    ## QA tests
    - Test 1: sales on Monday 3 November · hand count: 214.50 · formula: 214.50 · match
    - Test 2: bread loaves sold this week · hand count: 96 · formula: 91 · fixed: five rows typed "Bread " with a space
    - Test 3: a week with a public holiday · hand count: 0 for the holiday · formula: 0 · match
    
    ## One-page report
    - Top line: sales this week, US$1,412, up 6% on last week
    - Then: top 10 items, Friday late sales, bills due, each with an arrow up or down
    - Last: one sentence, e.g. "Restock bread and cooking oil; pay the dairy supplier by Thursday"
    
    ## Boundary
    - Every formula was checked against a hand count. Example numbers are invented.
    - The report shows what happened. It does not predict sales.
    

    Pro moves

    Methods this build practises

    Each method in the directory has a starter kit: the offer prefilled, first-sale steps, proof checks and the offer contract.

    Questions people ask

    Which spreadsheet should I use?

    Any free one: Google Sheets, LibreOffice Calc or Excel online. The formulas here use functions they all share.

    Should the report forecast next week?

    Not at first. Report what happened accurately for a month before trying to predict anything, and label any forecast clearly as a guess.

    Will this make me money?

    Nobody can promise that, and Open Practice never does. This workshop helps you make work that is worth paying for and keep the evidence. Whether anyone buys depends on your market, your outreach and your work.

    Do I need an AI key to use this?

    No. The guided template teaches the same skill with no AI at all. If you add your own free key (Groq, Google Gemini, OpenRouter, Mistral or Cerebras), the tool can also draft and revise. The key stays in your browser and requests go straight to that provider.

    Where is my work saved?

    In this browser only (local storage), until you copy or download it. Nothing you type is sent to Open Practice.

    Keep building