The Scenario
Your sales ops analyst left three months ago. The person who set up the lead scoring model in LeadBoxer left with them. The sales team is complaining that leads labeled "hot" in their queue feel wrong — scores above 80 for companies that have never shown any real buying intent. You've been asked to review the scoring logic and present it to the VP of Sales on Thursday.
The problem: the scoring formula lives in LeadBoxer's dataset configuration. Nobody wrote it down anywhere. You need to get it into a Google Sheet so you can share it, annotate it, and flag the criteria that might be wrong.
The bad version:
- Open the LeadBoxer dataset settings, navigate to the lead score configuration, and manually read through each criterion
- Type the rule types, field names, conditions, and weights into a spreadsheet by hand — there are 23 rows of criteria and some of the field names are abbreviated in ways that aren't obvious
- Realize mid-way through that you're not sure whether "boost" and "weight" are the same thing in this context and spend 15 minutes reading the docs
This is documentation work. The value is in what you do with the model once it's in front of you — not in transcribing it.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Google Sheet. It connects to LeadBoxer through its built-in integration and can pull the scoring formula configuration directly into your sheet — one row per criterion, formatted and ready to annotate.
Fetch the lead score formula for LeadBoxer dataset ID in cell A1 and write each scoring rule to Sheet1 with columns: criteria type, field name, condition, weight or boost value
What You Get
- One row per scoring criterion in the formula
- Column A: criteria type (range, match, exists, event_boost, etc.)
- Column B: field name as stored in LeadBoxer
- Column C: the condition or match value
- Column D: the numeric weight or boost value
- Criteria with no weight value (like "exists" checks) surface with "N/A" in column D so nothing breaks your sort
What If the Data Is Not Quite Ready
You have multiple datasets with different scoring models and need all of them
For each dataset ID in column A, fetch the LeadBoxer lead score formula and write all criteria to Sheet2 — add a "Dataset ID" column at the start of each row so you can filter by dataset
The field names need to be mapped to human-readable labels from a reference table
Fetch the lead score formula for dataset ID in cell A1, write each criterion to Sheet1, then look up each field name against the reference table in Sheet2 column A and add the readable label from column B into column E
You want the model annotated with whether each criterion is helping or hurting score inflation
Fetch the scoring formula for dataset ID in cell A1, write it to Sheet1, and add a column F prompt: for each criterion with a weight above 20, flag it as "REVIEW — HIGH WEIGHT" so I know where to focus
Pull the formula, map field names, rank criteria by weight, and output a clean audit doc — in one shot
Fetch the LeadBoxer scoring formula for dataset ID in cell A1, write each criterion to Sheet1 with criteria type, field name, condition, and weight, sort by weight descending, look up readable field names from the reference table in Sheet2, and add a column G that says "HIGH IMPACT" for any criterion with weight above 25 and "STANDARD" for the rest
One prompt does the pull, the lookup, the sort, and the triage. You show up to Thursday's VP sync with a real audit, not a transcription.
Try It
Get the 7-day free trial of SheetXAI and open a Google Sheet with your LeadBoxer dataset ID, then ask it to pull the complete scoring formula into a structured table. See also pulling behavioral events for funnel analysis or the LeadBoxer integration overview.