Analyze my fleet's CSA safety scores and plan how to lower them
Explains which safety categories are driving high scores, which inspections and crashes matter most, and what to fix first.
The prompt
Help me understand and reduce my carrier safety scores.
Scoring system: [e.g. "FMCSA CSA / SMS BASICs" or my country's carrier rating]
Current scores and thresholds: [PASTE CATEGORY PERCENTILES OR RATINGS - e.g. Unsafe Driving, HOS Compliance, Vehicle Maintenance, Controlled Substances, Hazmat, Driver Fitness, Crash Indicator]
Inspection and violation list: [PASTE - date, location, violation code, description, severity, driver, unit, out-of-service yes/no]
Crash list: [DATES, PREVENTABILITY IF KNOWN]
Fleet size and annual miles: [NUMBERS]
Do the following:
1. Rank categories by how close they are to or over intervention thresholds.
2. Within each category, find the violations carrying the most weight (severity, recency, out-of-service).
3. Group repeat violations by driver, unit, terminal, and inspection state or lane.
4. Identify any violations worth challenging through the data correction process, and what evidence I would need.
5. Note how time-weighting means old violations will age off, and estimate which ones drop off soonest only if dates are given.
Return:
- A table: Category | Current status | Top 3 contributing violations | Main driver or unit | Fix.
- A 90-day action plan: pre-trip inspection focus, maintenance fixes, driver coaching, clean inspection strategy.
- A one-paragraph explanation I can give my insurer or a customer asking about our scores.
Do not guess at score formulas or percentiles you cannot calculate from my data; mark them [CONFIRM]. Verify any data challenge rules with the regulator's current guidance.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- e.g. "FMCSA CSA / SMS BASICs" or my country's carrier rating
- DATES, PREVENTABILITY IF KNOWN
- NUMBERS
- CONFIRM
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Explain my Excel model to a non-technical executiveTurns a complex spreadsheet or model into a plain-English walkthrough an executive can follow, trust, and question.
- Run a fair lending review of loan pricing and approval dataA structured fair lending analysis plan and readout that tests for disparities in approvals, pricing, and exceptions.
- Find what drove my store's weekly sales resultBreaks a store's sales variance into traffic, conversion, ATV, and UPT, then gives specific actions for next week.
- Plan an RNA-seq differential expression analysisA reproducible, step-by-step RNA-seq workflow from raw reads to differentially expressed genes, with QC checkpoints and common pitfalls flagged.