MarketingContent Strategistintermediate 45 min saved

Audience Demand & Signal Validator

Transform raw feedback into validated content signals while filtering out noise and contradictory data.

Customise & copy

Add the context you have. The prompt updates as you work.

Target Audience Segment *

Who is the specific audience providing this feedback?

Primary Data Source Type *

Select the primary origin of the raw data.

Analysis Rigor Level *

Determine how aggressively to filter out weak or isolated signals.

Raw Audience Data *

Paste the raw comments, interview notes, or support logs here.

Live prompt

4 fields

Analyze the following raw audience data to extract verified demand, objections, use cases, and content signals. Strictly separate direct evidence from inferred themes, and explicitly flag weak or contradictory signals.

Context & Analysis Parameters:
- Target Audience Segment: B2B SaaS Founders
- Primary Data Source Type: Customer Discovery Transcripts
- Analysis Rigor Level: Strict (High threshold for proven demand)

Raw Input Data:
User A: 'I love the UI, but I can't justify the cost without SSO.' User B: 'Does this integrate with Salesforce?' User C: 'We tried setting it up but documentation for webhooks is completely missing.' User D: 'Honestly, the current reporting works fine for us, we don't need custom dashboards.'

Provide your analysis using the following mandatory structure:

1. DIRECT EVIDENCE (Verbatim quotes or direct data points only - no speculation)
- Repeated Questions:
- Specific Objections:
- Concrete Use Cases:

2. INFERRED THEMES (AI-synthesized interpretations and overarching patterns derived from the evidence above)
- Emerging Content Topics:
- Underlying User Pain Points:

3. WEAK & CONFLICTING SIGNALS (Explicitly flag isolated comments, ambiguous statements, or contradictory feedback that should NOT be treated as proven demand)
- Low-Frequency or Outlier Mentions:
- Conflicting Viewpoints:
- Ambiguous Signals to Re-test:

Proof before you use it

A real example

Tested on gemini-3.1-flash-lite on 2026-09-05

{
  "raw_data": "Prospect 1: 'We need SOC2 compliance before we can even run a pilot.' Prospect 2: 'Your pricing model per seat penalizes us for adding part-time reviewers.' Prospect 3: 'Can we export audit logs via API?' Prospect 4: 'Security is fine for us as is, we just want faster load times.'",
  "rigor_level": "Strict (High threshold for proven demand)",
  "source_type": "Support Tickets & Sales Objections",
  "target_segment": "B2B SaaS Founders"
}

A small ritual that works

How to use it

01Select your data source type and set the rigor level to match your project needs.
02Paste your raw interview transcripts, support tickets, or social comments into the data field.
03Run the prompt to generate a structured report separating verified evidence from inferred themes.
04Review the 'Weak & Conflicting Signals' section to identify feedback that requires further validation.

Why it works

The prompt enforces a rigorous, analytical structure that strictly separates direct verbatim evidence from AI-synthesized themes and weak signals. By forcing users to feed specific variables (target segment, source type, rigor level) alongside raw data, it tailors qualitative analysis to specific business contexts while maintaining strict anti-hallucination boundaries.

Where it fails

INSUFFICIENT_EVIDENCE

Customisation tips

To adapt this prompt for different domains, adjust the 'Rigor Level' select options to match your team's threshold for action (e.g., changing 'Strict' to 'Enterprise' or 'Early-Stage discovery'). You can also swap out the target segment and source type defaults to fit product research, user interviews, or churn feedback.

Watch-outs

Ensure raw input data actually contains verbatim quotes or concrete logs; empty or highly generalized input will result in thin or speculative analysis.
Watch for LLMs attempting to invent frequency counts in the 'Repeated Questions' section if the raw data only contains isolated or single-instance statements.
Calibrate the analysis strictly against the selected rigor level to prevent the model from turning outlier complaints into major product roadmap mandates.

Works in

ChatGPTClaudeGeminiQwenMeta AI

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.