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
Productivity

Audit expense reports

Every line checked against policy, with the ones worth a conversation flagged.

Fill it in

The expense data or receipts.

What is allowed, and the limits.

Repeated small breaches matter more than one big one.

Your prompt

Audit every line.

Policy:
[the policy]
Check 100%, not a sample. Sampling is a control designed for humans reading paper,
and the whole reason to do this differently is that every line can be read.

Look for PATTERNS rather than amounts. One 400 euro dinner is a conversation; the
same person claiming 49 euros of unreceipted taxi fare eleven times is a policy
problem, and only the second is invisible to a threshold.
Separate breaches from ambiguities. A claim outside policy is a finding; a claim
the policy does not cover is a policy gap, and reporting them together makes
everyone defensive about the wrong half.

Do not name people in the summary. Aggregate, then attach the detail.
Continue and pick your folderOpens with everything above already filled in.

Why this works

Sampling is a control designed for humans reading paper. This checks every line, and it looks for patterns rather than amounts, because one 400 euro dinner is a conversation while the same person claiming 49 euros of unreceipted taxi eleven times is a policy problem that no threshold sees.

More productivity skills

  • Document to slides
  • Meeting notes

Use it now in a chat in 1 click

Use Audit expense reports
Turn this into tasks
  • Weekly review
  • Decision brief
  • Build an investor deck