APAI Praveen
← All projects
STARTUPS & ENTREPRENEURSHIPSTARTER~60 minFREE SAMPLE

Keep a three-day diary of everyday annoyances and pick one to solve

Good ventures begin with a real irritation, yet many students start with a solution and then go looking for a problem.

WHAT YOU HAND IN

A three-day diary with at least fifteen entries, and a half-page note choosing one problem and saying who else has it.

YOUR AI BUILD GUIDE

This is a field study project. Collect your own evidence (a survey, interviews, a diary or a visit) and find the pattern in it.

The approach: Decide what you need to learn before writing a single question → Collect from real people or real places → Code the answers into themes → Report the pattern and how sure you can be.

Think first

The task is to catch real irritations as they happen, then choose one that is frequent, painful and shared. You are looking for a problem, not a product, so the diary must stay free of solutions until the very end.

ANSWER THESE BEFORE YOU OPEN ANY AI TOOL
  • What counts as an annoyance: anything that wastes time, money or patience, however small?
  • How will you note entries the moment they happen, so memory does not tidy them up?
  • How will you tag each entry for how often it happens and how much it bothers you?
  • Which two friends live a similar routine and could tell you honestly whether they share it?
WHAT GOOD LOOKS LIKE

A diary of at least fifteen raw entries with time, place and two simple tags, a grouping into a few themes, and a half-page note that picks one problem, says why it beat the others and who else has it, based on what two friends actually said.

THE COMMON WRONG TURN

Writing entries as solutions, such as 'need an app for canteen queues'. The moment a fix appears in the diary, you stop noticing the problem itself. Write only what happened and how it felt.

Gather

COLLECT
  • Phone notes written at the moment of each annoyance, with time and place
  • Two tags per entry: how often it happens and how much it bothers you, each on a small scale
  • Short notes from two friends on whether they face the same annoyance
WHAT AI MUST NOT MAKE UP

AI must not add annoyances, guess how common a problem is, or invent what your friends said. Every entry and every friend's reaction comes from your own notes.

Build with AI

  1. 3.1 Set up a quick diary formatCLAUDE CHAT

    Why this tool: A short, fixed format makes it easy to log entries in seconds on your phone.

    Ask for a one-line entry format and tag scale, then save it as a note on your phone and use it for three days.

    Prompt to copy · fill in the [brackets]
    I am keeping a three-day diary of everyday annoyances to find a problem worth solving. My days are mostly spent [where you spend your days, e.g. hostel and college]. Suggest a one-line format I can type in under thirty seconds, plus a simple scale for how often it happens and how much it bothers me. Keep it short.
  2. 3.2 Log the raw entries in a sheetGOOGLE SHEETS

    Why this tool: A sheet keeps every entry with its tags and lets you sort by the two scores later.

    At the end of each day, copy your phone notes into rows. Do not edit the wording. Add a column for theme that you leave empty for now.

  3. 3.3 Group the entries into themesCLAUDE CHAT

    Why this tool: Claude can suggest a grouping quickly; you decide whether each entry really belongs.

    Paste the entries with their tags. Check every grouping against your own memory and move entries that were put in the wrong theme.

    Prompt to copy · fill in the [brackets]
    Here are my diary entries of everyday annoyances, each with a frequency and a bother score:
    [paste your rows]
    Group them into four to six themes. For each theme, show which entries belong and add up the scores. Where an entry could fit two themes, say so. Do not suggest any solutions or products.
  4. 3.4 Test your pick and write the noteCLAUDE CHAT

    Why this tool: Being questioned before you write keeps the note honest about how sure you are.

    Ask your two friends about the top theme first. Then let Claude ask you questions, and write the half-page note in your own words.

Check the AI's work

  • Count the entries: at least fifteen, spread across all three days
  • Re-read every theme and confirm each entry in it is about the same kind of problem
  • The chosen problem scores high on both frequency and bother, or you explain why not
  • The 'who else has it' line quotes what your two friends really said
  • Read a sample of raw answers yourself before trusting any grouping
  • Say how many people or observations the finding rests on
WHAT AI USUALLY GETS WRONG HERE

AI quickly turns a theme into a startup idea and starts describing an app. Keep the note about the problem; a solution written now will narrow what you notice in interviews later.

Finish and show

DONE WHEN
  • Fifteen or more raw entries with time, place and tags
  • Entries grouped into themes with totals
  • Two friends asked about the top theme
  • A half-page note choosing one problem and saying who else has it
HOW TO PRESENT IT

A short table of themes with totals at the top, the chosen problem in a box, and the full diary underneath as evidence.

FOR YOUR PORTFOLIO

Describe the problem you chose, one entry that convinced you, and what your friends said that changed or confirmed your pick.

Which tool fits

  • Claude chat: A short, fixed format makes it easy to log entries in seconds on your phone.
    Free plan works; Pro gives longer conversations.
  • Google Sheets (free alternative): A sheet keeps every entry with its tags and lets you sort by the two scores later.
    Free with a Google account.
  • Google Forms (free alternative): a free survey that fills a sheet for you
    Free with a Google account.
LEVEL UP

Ask five classmates to keep the same diary for three days, then compare themes across everyone. A problem that shows up in several diaries is a far stronger starting point.

AI helps you think, check and polish. The work, and the judgement, stay yours.

Like this one? There are many more.

This is a free sample. Full Access opens every project in full and lets you submit your finished work.

See Full Access →
More starter projects in Startups & entrepreneurship
STARTUPS & ENTREPRENEURSHIPSTARTER
Rewrite the problem that Airbnb and Uber each set out to solve

Founders who cannot state their problem in one plain sentence often build things that nobody asked for.

~75 min🔒 Details
STARTUPS & ENTREPRENEURSHIPSTARTER
Shortlist and test five names for a new venture with classmates

A name that is hard to say, spell or remember quietly costs a small venture customers before it has even started.

~1.5 hrs🔒 Details
STARTUPS & ENTREPRENEURSHIPSTARTER
Summarise a founder's early story from a long public interview

Founder stories are told as luck and genius, which hides the small, repeatable choices that got the business moving.

~1.5 hrs🔒 Details