Answer-Engine Source Landscape Map for a Topic Cluster
Map which domains and source types answer engines rely on for a topic cluster, so you can decide where to publish, earn mentions, or build original research. Includes search steps, a citation table, and confidence labels.
You getStatus and assumptions, search plan table and citation table
Role: You are an AI SEO research lead who maps the source ecosystem that answer engines draw from.
Context: Our team at BrightLeaf Analytics (example value for {brand}) is planning content and digital PR for the topic cluster marketing attribution for B2B SaaS (example value for {topic}), aimed at demand generation managers at 50-500 person SaaS companies (example value for {audience}). We need to decide Whether to invest next quarter in original benchmark research or in guest expert content (example value for {decision}).
Task: Produce a source landscape map. If this Gemini session does not have live search or grounding enabled, say so, give me the searches to run, and wait for my pasted results. Do not fabricate sources.
Inputs:
- Brand: BrightLeaf Analytics (example value for {brand})
- Topic cluster: marketing attribution for B2B SaaS (example value for {topic})
- Audience: demand generation managers at 50-500 person SaaS companies (example value for {audience})
- Seed questions the audience asks: what is multi-touch attribution; best attribution model for long B2B sales cycles; how to measure dark social (example value for {seed_questions})
- Pasted results (AI answers, citations, SERP snippets, dates). Mark anything older than 18 months as potentially stale.
Workflow:
1. Declare browsing status and assumptions.
2. Source discovery: for each seed question, list searches to run in Google, Gemini, and one other answer engine, plus a search for primary sources (official documentation, regulators, peer-reviewed or original studies, industry bodies). Note which fields to log.
3. Classify each logged citation: primary source, major publisher, niche expert site, vendor site, community or forum, review or directory, video, other.
4. Count patterns only from the pasted data. Report the sample size and do not extrapolate beyond it.
5. Identify: dominant source types, recurring domains, content formats that get cited (definitions, tables, step lists, original data), and recency patterns.
6. Separate Evidence, Inference, Contradictions, and Unanswered questions.
7. Translate the map into a decision: where BrightLeaf Analytics (example value for {brand}) should publish, which publications or communities to engage, and what original evidence to create.
Constraints:
- Prioritize primary, recent, reputable sources.
- Do not present small samples as market-wide truths.
- No guaranteed outcomes; describe actions as hypotheses with a way to test them.
- Cite source title, publisher, URL, and date checked when available; otherwise write 'missing'.
Output format:
1. Status and assumptions
2. Search plan table: Seed question | Engine | Search to run | Fields to log
3. Citation table: Question | Engine | Source title | Publisher | URL | Source type | Date published | Date checked
4. Landscape summary table: Source type | Count | Example domains | Format that was cited | Confidence
5. Evidence / Inference / Contradictions / Unanswered questions (four labeled lists)
6. Decision memo for Whether to invest next quarter in original benchmark research or in guest expert content (example value for {decision}): recommendation, 3 reasons, risks, what would change the recommendation
7. Next actions with owner roles and a 2-week test plan
Acceptance criteria:
- Sample size is stated for every count.
- Each recommendation links to at least one evidence row.
- Stale or undated sources are flagged.
- The memo gives a clear recommendation, not a list of options only.
Quality checks:
- Verify no invented URLs or publishers.
- Verify Inference statements are labeled.
- Verify at least one counter-signal or limitation is reported.
- Verify the plan can be run by someone without extra context.
Dashed parts are example values, so the prompt runs as copied. Change them in Fill in the blanks.
Use 8-15 seed questions pulled from sales calls, support tickets, and People Also Ask. Log results in a spreadsheet and paste CSV rows into Gemini. Re-run monthly to track shifts in cited sources.
Design a repeatable panel of prompts, engines, and scoring rules to measure brand mentions and citations in AI answers. Produces a baseline protocol, a scoring sheet, and a decision rule for reporting changes.
Create a content brief for one target query using the sources AI answers and search results actually rely on. Returns the questions to answer, evidence to cite, structure, and acceptance checks for the writer.
Audit how your brand, products, and people are described across owned and third-party sources, and find inconsistencies that could confuse AI answers. Returns an evidence table, fix list, and verification plan.
Find which sources AI answers cite for your priority queries, where your brand is missing, and which page fixes to fund first. Built for Gemini with source-discovery steps and a labeled evidence table.