AI citation optimizer prompt

You are a GEO (Generative Engine Optimization) editor.

Use now

47 lines · 2,295 characters · paste it into ChatGPT, Claude or Gemini

Inside this prompt

prompt text · the author's own words

You are a GEO (Generative Engine Optimization) editor. Rewrite my content to maximize the chance AI engines cite it — using ONLY the measur…

MY PAGE:
[PASTE THE FULL CONTENT]

CONTEXT:
- Topic + the 3-5 questions I want AI engines to cite me for: [X]
- My credibility assets: [data I own, experience, original research, none]
- Real statistics/sources I can legitimately add: [list any — DO NOT let the
  rewrite invent statistics; if I provide none, use only clearly-attributed
  third-party stats you are confident exist, flagged for my verification]

THE EDITING PASS — apply in order:

1. THE CITABLE CLAIM AUDIT
   List every claim in my content. Mark each: SPECIFIC (quotable as-is) /

Word-for-word excerpt, not a result. Read the full prompt ↓

The prompt

47 lines · 2,295 characters

1	You are a GEO (Generative Engine Optimization) editor. Rewrite my content to maximize the chance AI engines cite it — using ONLY the measured tactics, not folklore.
2
3	MY PAGE:
4	[PASTE THE FULL CONTENT]
5
6	CONTEXT:
7	- Topic + the 3-5 questions I want AI engines to cite me for: [X]
8	- My credibility assets: [data I own, experience, original research, none]
9	- Real statistics/sources I can legitimately add: [list any — DO NOT let the
10	rewrite invent statistics; if I provide none, use only clearly-attributed
11	third-party stats you are confident exist, flagged for my verification]
12
13	THE EDITING PASS — apply in order:
14
15	1. THE CITABLE CLAIM AUDIT
16	List every claim in my content. Mark each: SPECIFIC (quotable as-is) /
17	VAGUE (rewrite) / UNSUPPORTED (needs a stat or source, or gets cut).
18	"Many marketers struggle with X" → vague. "X% of [audience] report Y (Source, year)" → citable.
19
20	2. STATISTICS INJECTION (+40% visibility tactic)
21	Where do numbers belong that aren't there? Insert from my provided list, or
22	mark [STAT NEEDED: description + suggested source type] slots for me to fill.
23	Every number gets source + year inline.
24
25	3. QUOTABLE LINES (quotation tactic)
26	Forge 3-5 single-sentence claim-lines an AI could lift verbatim — the
27	distilled position of the piece, placed at section tops. Punchy, specific,
28	self-contained (no "this" referring to a previous paragraph).
29
30	4. STRUCTURE FOR EXTRACTION
31	- One clear answer-paragraph (2-3 sentences) directly under the H1 answering
32	the primary question — the paraphrasable summary.
33	- Question-shaped H2s matching my target questions.
34	- Tables/lists for anything enumerable; definitions in "X is Y" form.
35
36	5. FRESHNESS & ENTITY SIGNALS
37	- "Last updated / data as of [date]" placement (real changes only — date-only
38	edits show no benefit per Ahrefs' freshness analysis).
39	- Name entities fully on first mention (people, products, orgs + what they are).
40
41	6. FLUENCY PASS (+15-30% tactic) — tighten, de-jargon, cut throat-clearing.
42	NO keyword stuffing anywhere — it measured BELOW baseline.
43
44	OUTPUT:
45	- The rewritten content, with [STAT NEEDED] and [VERIFY] flags visible
46	- The extracted quotable-lines list (I'll reuse them on social)
47	- A 3-line change log: what was added/cut and which tactic each serves

Discussion

Alternatives

AI Search / GEO Optimization (May 2026)Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. Generative Engine Optimization (GEO) analysis including brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "SGE", GEO", "AI search", "LLM optimization", "Perplexity", "AI citations", ChatGPT search", or "AI visibility".Marketing · MIT geo-sleuth (v2)Geolocate or chronolocate a photo with tool-verified reasoning (where was this taken / when was it taken / photo geolocation / geo-guessing). Given one or more photos, intake.py does metadata, OCR and reverse image search (Baidu/Yandex) in one command; clues and candidates go on a candidate board (board.py) that ranks them and gives the next step; clues.py looks up calling codes, driving side, plates and area codes from region packs; for satellite and street view the machine ranks first and you look only at the top few (CLIP in sat_scan.py, DINOv2+SIFT in match.py); plus sun and shadow math, OSM Overpass and DEM skylines. Every conclusion is checked against real data; output is coordinates + error radius, evidence images and tiered confidence. Use when the user shares a photo and asks where was this taken / geolocate this / when was this taken / 这是哪 / 在哪拍的 / 帮我定位这张照片 / 网络迷踪 / 图寻 / 几点拍的.Marketing · MIT AI visibilityMeasure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they cite — from actual GA4 referral data, not prompt sampling. Use when asked "AI visibility", "GEO/AEO check", "do LLMs cite us", "traffic from ChatGPT", or "how do we show up in AI search".Marketing · MIT AI Search SEO: Citation StrategiesUse GEO and AEO as legacy labels for AI citation readiness. For Google, theMarketing · MIT

Browse more free AI prompts or everything in Marketing.