Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
All skills
Data

Chart your spending

Categorise a year of transactions and see where the money actually goes.

Fill it in

A CSV export from your bank or card.

For the axis labels and totals.

Anything the obvious rules would get wrong.

Flag charges that repeat monthly, and what they add up to a year.

Your prompt

Categorise these transactions and build a dashboard from them.

My own rules, which beat yours where they conflict:
[your own categories]
Categorise from the description text, and SHOW the rules you used. A category
assigned by an invisible judgement is one nobody can correct, and the whole
thing is worthless if a third of it is filed wrong. List anything you could not
place rather than dropping it into Other and moving on.

Find the repeats. A charge that lands every month at roughly the same amount is
a subscription, and the annual total of those is usually the single most useful
number here.
Then build one self-contained HTML page: totals by category, a month-by-month
trend, the biggest movers, and a filterable table of every row so a wrong
category can be spotted. Amounts in [your currency].

No CDN, no build step. One file that opens.
Use Chart your spendingOpens with everything above already filled in.

Why this works

Categorising by description is the easy half. The hard half is that a category assigned by an invisible judgement is one nobody can correct, so a third of the file ends up filed wrong and the dashboard looks fine. This shows its rules, lists what it could not place, and finds the subscriptions, which is usually the number people actually wanted.

Questions

Does my data leave?
It is processed in your workspace and the output is a self-contained page. Nothing is published.
My bank's export is odd.
Describe your own rules and they beat the defaults.

More data skills

  • Extract to a table
  • Analyse a spreadsheet
  • Chart this data

Use it now in a chat in 1 click

Use Chart your spending
  • Clean a dataset
  • Write a data dictionary
  • Read out an A/B test