MarketingContent Strategistintermediate 45 min saved

Strategic Content Topic Generator

Transform raw customer feedback and market signals into prioritized, high-impact content topics aligned with business goals.

Customise & copy

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

Raw Market Signals or Feedback *

Paste raw customer inquiries, market signals, or data points.

Recently Covered Topics *

List recently published or previously covered content themes to avoid duplication.

Current Sales or Product Priorities *

Specify current business goals, sales targets, or product launches.

Primary Content Format *

Select the target format for the generated content topics.

Live prompt

4 fields

Analyze the provided inputs to generate a prioritized list of distinct content topics. Do not use conversational filler, pleasantries, or meta-commentary.

Input Data:
1. Raw Signals & Feedback: Customer support tickets mentioning confusion around API rate limits; sales call notes about enterprise security requirements; churn feedback citing lack of automated reporting.
2. Recent Topics Covered: Getting started with our API, Introduction to enterprise security features, Q3 roadmap overview.
3. Current Strategic Priorities: Drive adoption of the new enterprise tier; reduce support ticket volume for developer onboarding.
4. Target Content Format: Long-form blog post

Instructions:
- Extract core audience needs and pain points directly from the raw data.
- Cross-reference against recent topics. If a theme overlaps, provide a genuinely distinct angle or explicitly mark it for exclusion.
- Map every proposed topic directly to one of the current strategic priorities.
- Ensure all source notes tie back exclusively to the provided raw data without inventing unverified testimonials.

Output Format:
Provide a structured table or list containing the following fields for each topic:
- Candidate Topic
- Underlying Audience Need
- Sales/Product Priority Mapping
- Suggested Format (e.g., Long-form blog post)
- Source Notes (linking back to raw data)
- Differentiation Notes (distinguishing from recent coverage or marking as excluded)

Proof before you use it

A real example

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

{
  "raw_data": "Customer support tickets mentioning confusion around API rate limits; sales call notes about enterprise security requirements; churn feedback citing lack of automated reporting.",
  "recent_topics": "Getting started with our API, Introduction to enterprise security features, Q3 roadmap overview.",
  "content_format": "Long-form blog post",
  "business_priorities": "Drive adoption of the new enterprise tier; reduce support ticket volume for developer onboarding."
}

A small ritual that works

How to use it

01Paste your raw customer feedback, support tickets, or sales notes into the raw_data field.
02List your recently published content to ensure the model identifies gaps and avoids repetition.
03Input your current product or sales priorities to ensure every topic serves a business goal.
04Review the generated table to select the highest-impact topics for your editorial calendar.

Why it works

The prompt enforces a strict structural mapping between raw customer inputs, strategic priorities, and content generation. By requiring explicit differentiation against recent topics and direct citation of source notes, it prevents the creation of disconnected or duplicate content themes. Test Output A demonstrates how the structure forces a direct translation of raw signals (support tickets, sales notes, churn feedback) into targeted, prioritized table rows.

Where it fails

INSUFFICIENT_EVIDENCE

Customisation tips

Modify the 'business_priorities' and 'content_format' variables to target different lifecycle stages or publishing channels without altering the core analytical extraction logic. Adjust the raw data input structure if your organization tracks signals across different channels, such as user research interviews or community forum threads.

Watch-outs

Avoid inputting overly broad raw signals, as this can lead to speculative extensions or unverified feature framing in the differentiation notes.
Ensure that the recent topics list is accurate; otherwise, the differentiation step may fail to catch genuine content overlaps.
Strictly adhere to the provided raw data to prevent the generation of unsupported claims or embellished product capabilities in the table output.