TabliSync Command Writing Guide
Purpose
Teach you how to craft effective commands so TabliSync produces exactly the result you want—quickly, consistently, and with minimal rework.
Why This Matters
TabliSync relies on your natural language instructions. Vague or underspecified commands force the AI to guess, increasing chances of incomplete, incorrect, or overly generic outputs. Clear intent = better table extraction, faster.
1. Command Writing Basics
Focus on 4 pillars:
ACTION
What should be done? (remove duplicates, calculate, group, forecast, visualize, extract, format)
SCOPE
Which columns / rows / sheets / files? Use exact column names in single quotes.
CONDITION(S)
Filters, thresholds, date ranges, business rules.
OUTPUT FORM
New sheet, overwrite, summary only, chart, cleaned file, add column, etc.
Good vs Bad (Core Examples)
| Goal | Bad (Vague) | Good (Specific) | Why Good |
|---|---|---|---|
| Remove dups | Fix my file | Remove duplicates based on 'Customer ID'; keep first occurrence; output as new sheet 'Cleaned'. | Specifies key column + rule + output target |
| Summarize sales | Analyze data | Sum 'Sales' by 'Region' and 'Quarter'; include total row and descending order by Sales. | Clear aggregation + grouping + sort |
| Sort data | Make it nicer | Sort by 'Date' ascending, then by 'Revenue' descending; keep headers. | Explicit multi-level sort |
Simple Pattern
ACTION + TARGET COLUMNS + CONDITIONS + TRANSFORMATION + OUTPUT FORMAT
Example: Example: Calculate average 'Order Value' by 'Channel' for last 90 days (where 'Order Date' >= 2025-05-28); output summary table + bar chart.
2. Expanding Precision
Use these wording techniques:
Be Specific with Column Names
Use exact column names in single quotes: 'Customer ID', 'Order Date', 'Revenue'
Define Output Clearly
Specify: "Create new sheet 'Results'", "Add column", "Replace existing data"
Include Formatting
Add: "format as percentage 2 decimals", "sort descending", "include totals"
3. Advanced Command Techniques
A. Conditional Logic
"Add column 'Status' = IF 'Revenue' > 1000 THEN 'High' ELSE 'Low'"
"Filter rows where 'Date' >= 2025-01-01 AND 'Region' IN ('North', 'South')"
B. Combining Tasks in One Pass
Chain related operations when order is clear.
Example: Clean 'Orders' by removing duplicates on 'Order ID', fill missing 'Cost' with median, add 'Margin'=(Revenue-Cost)/Revenue*100, then create bar chart of average 'Margin' by 'Region'.
C. Output Management
Specify: "Create new sheet 'Cleaned'", "Replace existing 'Sheet1'", "Add chart to new sheet 'Charts'", "Return only summary (no row-level export)".
4. Common Command Templates
Copy, adapt, and run. Replace bracketed items.
Cleaning & Preparation
Analysis
Visualization
Transformation
Forecasting
Multi-File Operations
5. Good vs Bad Command Gallery
| Scenario | Bad | Improved | Best |
|---|---|---|---|
| Cleaning | Fix this | Remove duplicates | Remove duplicates on 'Order ID', fill null 'Cost' with median, standardize 'Date' to YYYY-MM-DD, output new sheet 'Cleaned'. |
| Analysis | Analyze sales | Sum sales | Sum 'Sales' by 'Region' and 'Quarter'; include growth vs prior quarter and sort by 'Sales' desc. |
| Visualization | Make chart | Bar chart products | Bar chart: x='Product', y='Sales', top 15 only, sorted desc, title 'Top 15 Products', new sheet 'Charts'. |
6. Troubleshooting & Refinement
Symptom → Action:
Refinement Loop Template
7. Your First Practice Command
Upload a recent sales export, then run:
Remove duplicates on 'Order ID'; fill missing 'Unit Cost' with median; add 'Gross Margin %'=(Revenue-Cost)/Revenue*100 formatted percent 1 decimal; create bar chart average 'Gross Margin %' by 'Region' sorted descending; place chart in new sheet 'Charts'.
Refine from there—you're now writing like a power user.