Inbound Lead Routing Diagnostic Engine
Diagnose lead routing failures and generate evidence-backed process improvements to optimize conversion and response times.
Customise & copy
Add the context you have. The prompt updates as you work.
Paste inbound lead records including timestamps, source, and demographic/firmographic data.
Paste current routing rules and territory assignment definitions.
Paste ownership data and lead-to-rep assignment history.
Paste response time logs and qualification outcomes with rejection reasons.
Live prompt
4 fieldsAnalyze the provided inbound lead-routing performance data to identify root causes of process failure and recommend evidence-backed rule and process changes. ### Input Data - Lead Records & Demographics: {{lead_records}} - Current Routing Rules & Territories: {{routing_rules}} - Ownership & Assignment History: {{assignment_history}} - Response Times & Qualification Outcomes: {{qualification_outcomes}} ### Analysis Instructions 1. Diagnose underlying root causes rather than surface symptoms (e.g., differentiate between slow response times caused by rep bandwidth vs. ownership gaps). 2. Categorize all identified failures strictly into one of these operational domains: data quality, routing logic, territory rules, qualification criteria, ownership gaps, or process execution. 3. Prioritize the failure modes by severity and impact using the provided evidence. 4. Formulate specific, actionable rule or process change recommendations designed to fix the root causes without generic filler. ### Output Format - Failure-Mode Breakdown: Structured categorization of issues by operational domain. - Impact Prioritization Ranking: Evidence-based ranking of failure points. - Actionable Recommendations: Concrete, implementable rule or process changes.
Proof before you use it
A real example
Tested on gemini-3.1-flash-lite on 2026-09-06
{
"lead_records": "2023-10-01 09:15, Organic Search, 50 employees, SaaS; 2023-10-01 09:22, Paid Ads, 1200 employees, Manufacturing.",
"routing_rules": "Rule A: Company size > 1000 goes to Enterprise team. Rule B: Company size < 1000 goes to SMB pool via round-robin.",
"assignment_history": "Lead 101 assigned to Rep A (Enterprise) then manually reassigned to Rep B after 4 hours. Lead 102 unassigned for 14 hours.",
"qualification_outcomes": "Average response time: 6.5 hours. Rejection reasons: 45% 'Wrong territory', 30% 'Unqualified budget', 25% 'Unresponsive'."
}A small ritual that works
How to use it
- 01Export your lead records, routing rules, assignment history, and qualification outcomes into CSV or text format.
- 02Paste the data into the corresponding input fields in the prompt.
- 03Run the prompt to generate the failure-mode breakdown and impact ranking.
- 04Review the actionable recommendations to implement specific rule or process adjustments.
Why it works
The prompt enforces a rigorous, evidence-based diagnostic process by forcing the LLM to categorize operational failures into exact domains and link impact rankings directly to provided input data, preventing generic filler recommendations.
Where it fails
INSUFFICIENT_EVIDENCE
Customisation tips
Adjust the failure-mode domain categories to match your specific CRM taxonomy (e.g., swapping 'territory rules' for 'account-executive regions') to better align with your internal routing architecture.
Watch-outs
- Ensure raw data inputs for lead records and routing rules are fully populated so the model doesn't hallucinate root causes or make unsupported assumptions about bottlenecks.
- Watch for arbitrary operational thresholds or time limits suggested in recommendations; verify them against your actual historical response times before implementing.
Works in
Was this useful?
Submit your variation
If your version helps, it may be published with your name and a link back to you.
Related prompts
Want to make AI useful across your team? Explore Atul's training.