1
of 5— Understand What Makes Good Commentary
What you'll accomplish
By the end of this guide, you'll have a set of tested prompts and a structured process for generating high-quality forecast variance commentaries in under 15 minutes — compared to the 60–90 minutes most demand planners spend writing them from scratch each cycle.
What you'll need
- Free Claude account at claude.ai
- Your actuals vs. forecast variance data (can be a simple table)
- Context on the key variance drivers (you know these from your analysis)
- Time needed: 30 min setup; 10–15 min per commentary thereafter
- Cost: Free
How-To Guide: Build a Variance Commentary System with Claude
Step 1: Understand What Makes Good Commentary
Before building prompts, clarify what your demand review requires. Good variance commentary should:
- State the overall performance (total actual vs. plan, the %)
- Explain the top 2–3 drivers (what caused the variance — not just that it happened)
- Distinguish between structural shifts (lost customer, new competitor) vs. temporary factors (weather, timing)
- Set up the forward-looking implication (does this variance continue?)
- Be specific enough that someone who wasn't in the analysis can follow the logic
Tools:Claude