Prospect Objection Pattern Analyzer
Turn raw sales feedback into actionable playbook updates by identifying the root causes behind prospect objections.
Customise & copy
Add the context you have. The prompt updates as you work.
The specific job title or buyer persona being targeted.
The industry or market sector of the prospects.
Paste raw call transcripts, email replies, and CRM notes containing prospect objections.
Live prompt
3 fieldsAnalyze the following SDR/BDR prospect interaction data to categorize objections, contrast stated concerns with underlying drivers, separate actionable feedback from noise, and provide enablement recommendations. Target Persona / Segment: Enterprise VP of Sales Industry Context: B2B SaaS Raw Interaction Data: Prospect 1 (Call): 'We use Salesforce natively, your tool sounds nice but budget is frozen until Q4.' Prospect 2 (Email): 'Not interested, we built our own internal dashboard.' Prospect 3 (CRM Note): 'Stalled after pricing reveal. Said $50k/yr is too steep compared to incumbent.' Instructions: 1. Categorize the objections into genuine types (product, price, timing, authority, competitive) versus non-actionable noise. 2. Distinguish between the literal stated objection and the evidence-backed underlying concern using direct data references. 3. Indicate frequency for every identified pattern (widespread pattern vs. isolated incident). 4. Provide specific, evidence-backed recommendations for modifying messaging, qualification criteria, or discovery questions based strictly on the provided data without outside assumptions.
Proof before you use it
A real example
Tested on gemini-3.1-flash-lite on 2026-09-06
{
"target_segment": "Clinical Operations Director",
"industry_context": "Healthcare / Medical Devices",
"raw_interactions": "Prospect X: 'HIPAA compliance is a massive hurdle for us; I doubt your cloud architecture clears our security review.' Prospect Y: 'We have an existing vendor contract locked in through 2026.' Prospect Z: 'Not relevant to our clinic staff right now.'"
}A small ritual that works
How to use it
- 01Compile raw call transcripts, email replies, and CRM notes into a single text block.
- 02Input the target persona and industry context to provide necessary framing.
- 03Run the prompt to generate a structured analysis of objection patterns.
- 04Apply the recommended messaging and discovery adjustments to your team's sales playbooks.
Why it works
The prompt enforces a rigorous, evidence-based approach to sales interaction analysis by mandating strict categorization of objections, direct data references for underlying concerns, explicit frequency tracking for patterns, and actionable enablement recommendations derived solely from the provided text.
Where it fails
INSUFFICIENT_EVIDENCE
Customisation tips
Ensure the raw interaction data variable includes a balanced sample size across multiple accounts to prevent false pattern recognition from isolated incidents.
Watch-outs
- Do not infer psychological drivers or business hurdles (such as vendor fatigue or risk aversion) that are not explicitly stated in the prospect text.
- Avoid classifying single data points as widespread patterns.
- Do not introduce outside assumptions regarding product capabilities, pricing models, or industry standards into the recommendations.
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.
Want to make AI useful across your team? Explore Atul's training.