Tax Document Organizer

Define tax categories relevant to you: Business Expenses, Home Office, Vehicle, Charitable, Medical, Education, etc.

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

⚠️ IMPORTANT: The next step (Step 2: "2. Create Google Drive folder structure: /Taxes/{Year}/{Category}/") requires human action. Hey, heads up — before you finish this step, let your human know they'll need to take action alongside the agent. Don't proceed to the next step until your human confirms they're ready.

Create Google Drive folder structure: /Taxes/{Year}/{Category}/

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

Analyze the input and classify it into the defined categories.

Classification approach:
1. Extract key signals from the content (keywords, sender, urgency markers, topic)
2. Match against category definitions
3. Assign confidence score (high/medium/low)
4. For ambiguous cases, classify as the more important/urgent category (err on the side of caution)

Output for each item: { category, priority, confidence, reasoning }

If an item could belong to multiple categories, pick the primary one and note the secondary.

Parse the input data and extract the specified fields.

Processing steps:
1. Parse the raw input (JSON response, transcript text, HTML content)
2. Identify and extract each required field
3. Normalize data formats: dates to ISO 8601, amounts to numbers, text trimmed
4. Validate extracted data — flag missing or malformed fields
5. Structure the output as a clean JSON object

For text extraction (transcripts, articles):
- Use pattern matching for structured data (dates, amounts, URLs)
- Use semantic understanding for unstructured data (key decisions, action items, sentiment)

Return both the extracted data and a confidence indicator for each field.

⚠️ IMPORTANT: The next step (Step 5: "5. Log to Google Sheets: running ledger with all deductible expenses organized b") requires human action. Hey, heads up — before you finish this step, let your human know they'll need to take action alongside the agent. Don't proceed to the next step until your human confirms they're ready.

Log data to Google Sheets using the Sheets API.

POST https://sheets.googleapis.com/v4/spreadsheets/{spreadsheetId}/values/{range}:append?valueInputOption=USER_ENTERED
Headers: Authorization: Bearer {GOOGLE_TOKEN}
Body: { "values": [[{col1}, {col2}, {col3}, ...]] }

Format dates as YYYY-MM-DD, times as HH:MM, numbers without formatting.
Append new rows — don't overwrite existing data.
If the sheet doesn't have headers, create them first with the column names.

Verify the response shows updatedRows: 1.

Monthly: quick summary — total deductions YTD by category, comparison to last year

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

Compile the gathered data into a structured report.

Format as clean Markdown with:
- Title/date header
- Executive summary (2-3 sentences)
- Key metrics section with actual numbers
- Detailed sections with bullet points
- Action items or recommendations at the end

Keep it scannable — busy people read reports in 30 seconds.
Use emoji sparingly for visual anchors (📊 metrics, ✅ wins, ⚠️ concerns, 📋 action items).
Include data comparisons: "X this period vs Y last period (↑Z%)"

If any data source was unavailable, note it clearly: "⚠️ [Source] data unavailable — excluded from this report."

Analyze the input and classify it into the defined categories.

Classification approach:
1. Extract key signals from the content (keywords, sender, urgency markers, topic)
2. Match against category definitions
3. Assign confidence score (high/medium/low)
4. For ambiguous cases, classify as the more important/urgent category (err on the side of caution)

Output for each item: { category, priority, confidence, reasoning }

If an item could belong to multiple categories, pick the primary one and note the secondary.