AI Prompts For SEO

How I use Semrush data and multi-model workflows to win the "Information Gain" battle.

The Single Prompt Is Dead — Here's What Replaces It

I've spent the last 12 months auditing more than 500 websites. And the clearest pattern I've found? In 2026, typing "write an SEO blog post about X" into ChatGPT is a one-way ticket to Google's spam filter.

The sites winning today aren't using AI as a word processor. They're using it as a strategist, researcher, auditor, and editor — running sequences of targeted prompts across multiple models to do work that used to take an entire agency team.

That's what this guide is. A complete, copy-paste library of the AI prompts for SEO I actually use — organized by workflow, model, and goal. By the end, you'll have a repeatable system for turning ChatGPT, Claude, and Gemini into a senior SEO operation.

Let's get into it.

Why "Agentic" Prompting Changes Everything in 2026

Before we get to the prompt library, it's worth understanding the shift that's happening.

SEO in 2026 is no longer just about ranking on Google. It's about LLM Citability — whether AI tools like ChatGPT, Perplexity, and Google's AI Overviews pull your content as a source when users ask questions in your niche. This emerging discipline is sometimes called GEO (Generative Engine Optimization), and it rewards content that is entity-rich, factually precise, and structurally easy for AI systems to parse.

The implication: your prompts need to produce content that satisfies both human readers and AI retrieval systems. A single generic prompt can't do that. A chain of agentic prompts — each one building on the last — can.

Here's exactly how to build those chains.

100+ AI SEO Prompts by Category

Keyword & Entity Discovery (Best with Semrush Data)

These ChatGPT SEO prompts are designed to go beyond surface-level keyword research and uncover the semantic entities and intent clusters that actually drive rankings.

The Entity-First Seed

"Act as a semantic researcher. Using the Semrush Keyword Magic Tool export I've provided, identify 10 entities that my competitors are ranking for but I am not. Group them by LSI (Latent Semantic Indexing) relevance and explain why each entity matters to my topic cluster."

The Intent Mapper

"Analyze these 50 keywords. Categorize each one into 'Early-Stage Informational' or 'High-Intent Transactional.' For each cluster, suggest the ideal content format (e.g., comparison guide, how-to, landing page, FAQ)."

The Local Entity Extractor

"I'm targeting [City/Region]. Using this keyword list, identify location-specific entities, landmarks, and modifiers that would make my content more locally relevant than a generic national competitor."

The Seasonal Trend Spotter

"Analyze these 12 months of search volume data. Identify the 3 highest-opportunity seasonal windows for [Topic] and suggest a content publishing schedule to capture them."

The Long-Tail Question Miner

"Generate 20 long-tail 'how,' 'why,' and 'what if' questions that a senior [Target Persona] would ask about [Topic]. These should be questions that competitor content is too generic to answer well."

The People Also Ask Expander

"Take this list of PAA questions from Google. For each one, identify the underlying 'job-to-be-done' the searcher has and suggest how to answer it in a way that exceeds the current top result."

The Semantic Co-Occurrence Finder

"Here are the top 10 ranking URLs for [Keyword]. Identify the semantic terms and entities that appear in at least 7 of the 10 articles but are absent from my current draft. List them in priority order."

The Competitor Entity Gap

"Here is a Semrush domain comparison export for my site vs. [Competitor A] and [Competitor B]. Find the entity clusters where both competitors have strong topical authority and I have none. Prioritize them by estimated traffic opportunity."

The Featured Snippet Optimizer

"Analyze this SERP for [Keyword]. The featured snippet is currently held by [Competitor]. Rewrite my answer to this question in a format more likely to win the snippet: use a direct definition sentence followed by a concise numbered or bulleted list."

The Topic Cluster Architect

"I want to build topical authority around [Core Topic]. Map out a pillar page and 8 supporting cluster articles. For each cluster piece, specify the primary keyword, secondary entities, and how it internally links back to the pillar."

The "Information Gain" Suite

Google's Helpful Content system rewards content that adds something new to the web — not content that restates what's already ranking. These AI prompts for SEO are specifically designed to surface that added value.

The Gap Finder

"Analyze the top 3 ranking URLs for [Keyword]. Identify the 'common wisdom' they all repeat. Now suggest 3 counter-intuitive or expert-only angles that would provide genuine Information Gain for a sophisticated reader."

The Skeptic's Take

"Write a 500-word section that adds a unique perspective not found in the top 10 SERPs. Use the persona of a [Specific Job Title] who is professionally skeptical of the industry norm on [Topic]. Back each claim with a logical argument."

The Data Synthesizer

"I am uploading a CSV of our proprietary customer survey data. Write a 'Key Findings' section that provides a unique perspective on [Topic] that no competitor has access to. Lead with the most surprising finding."

The Expert Interview Simulator

"Simulate an interview with a fictional but highly credible expert — a [Job Title] with 15 years in [Industry]. Have them challenge the conventional wisdom on [Topic] and provide 3 specific, detailed insights that would only come from hands-on experience."

The Contrarian Audit

"Review this draft article. Flag every sentence that repeats information already found in the top 5 Google results for [Keyword]. For each flagged sentence, suggest a replacement that adds original analysis, a specific example, or a cited data point."

The 'What No One Is Saying' Prompt

"You are a niche expert in [Field]. What is the most important thing practitioners know about [Topic] that popular online content consistently ignores or underplays? Write a 300-word section that addresses this gap directly."

On-Page Optimization Prompts

The Title Tag A/B Set

"Write 5 meta title variations for this article targeting [Keyword]. Each should use a different psychological trigger: curiosity, social proof, urgency, specificity, and a contrarian claim. Keep each under 60 characters."

The Meta Description Upgrade

"Rewrite this meta description. It should include the primary keyword naturally, communicate a clear benefit, and end with a soft call-to-action. Aim for 145–155 characters."

The Header Hierarchy Audit

"Review this article's H1, H2, and H3 structure. Identify where the hierarchy is broken, where keyword opportunities are missed, and where a 'People Also Ask' style header could be inserted to capture a featured snippet."

The Introduction Rewriter

"Rewrite this article introduction. Open with a specific, surprising statistic or scenario — not a rhetorical question. Establish relevance within the first two sentences. Do not start with 'In today's world' or any variation of it."

The Internal Link Suggester

"Here is a sitemap of my 40 most important pages and their primary keywords. Analyze this new article draft and suggest 5 internal links I should add, specifying the anchor text and the target page."

E-E-A-T & Authority Building Prompts

The Author Bio Builder

"Write a 100-word author bio for [Name], a [Job Title] with [X] years of experience in [Field]. Emphasize firsthand experience signals relevant to Google's E-E-A-T guidelines. Include one specific credential, one notable project, and one personal detail."

The 'Prove It' Enhancer

"Review this article and identify every claim that would benefit from a supporting source, statistic, or real-world example. For each one, suggest the type of source that would add the most credibility (academic study, government report, industry survey, etc.)."

The Case Study Converter

"Transform this generic how-to section into a mini case study format. Use a specific (can be anonymized) client scenario with real numbers, a before/after structure, and a lesson learned that generalizes to the broader reader."

My AI Prompt Workflows

Having a library of prompts is your starting point. Building them into agentic workflows is where the real leverage comes from. Here are the three I use on every client project.

Workflow #1: AI Prompt Site Audit (Claude)

I use Claude for technical audits because its large context window can ingest massive crawl exports, XML sitemaps, and analytics data simultaneously without losing thread.

My process:

When I start a new engagement, I don't ask for a generic audit. I build a chain.

Prompt 1 — The Decay Finder:

"Act as a Technical SEO Auditor. I am uploading a full site crawl export. Find 5 'pockets of content decay' — clusters of old pages that are cannibalizing newer, higher-quality content in the same topic area. For each pocket, identify the URLs involved and explain the cannibalization mechanism."

Prompt 2 — The Triage Decision:

"Based on the 5 decay pockets you identified, write a one-page strategy memo recommending whether each cluster should be Redirected, Refreshed, or Deleted. For each decision, explain how it affects Link Equity distribution across the site."

Prompt 3 — The Quick-Win Prioritizer:

"From the full audit, identify the 10 pages that are ranking on page 2 (positions 11–20) for a commercially valuable keyword. These are the highest-leverage refresh opportunities. For each page, list the primary issue preventing a page-1 ranking and the single most impactful fix."

Workflow #2: The Content "Information Gain" Sprint (ChatGPT + Semrush)

This three-step sequence is how I produce content that consistently outperforms what's already ranking.

Step 1 — The Semrush Sync:

I export my Semrush Content Gap report comparing my domain to two or three top competitors. This gives me a list of keywords they rank for that I don't — the raw material for Information Gain content.

Step 2 — The Semantic Map:

"I'm uploading a Semrush Content Gap export. Group these keywords into thematic clusters. For each cluster, identify the primary intent, the best content format, and the 'angle' that would differentiate my article from the top-ranking competitor. Present this as a content calendar-ready table."

Step 3 — The Execution:

"Write a 600-word 'Information Gain' section for an article targeting [Keyword]. The persona is a [Specific Job Title] who has seen the standard advice fail in practice. They should present one contrarian insight, support it with a specific mechanism or example, and pre-empt the most obvious objection."

Workflow #3: The E-E-A-T Research Scout (Gemini)

Gemini is my fact-checker and authority builder. Its direct connection to live Google Search makes it the best model for sourcing credible, current data to back up content claims.

The Authority Sourcing Prompt:

"Search for the latest 2025–2026 academic papers, government reports, or large-scale industry surveys on [Topic]. Find 3 'power statistics' — figures that are surprising, specific, and highly citable. For each one, provide the source name, the exact URL, and a one-sentence summary of why this statistic elevates the article's credibility."

The Claim Verification Prompt:

"Here are 5 factual claims from my draft article on [Topic]. For each claim, verify whether it is accurate based on current sources. If a claim is outdated or inaccurate, suggest a replacement with the correct figure and source."

The 'Who Said It' Prompt:

"Find 2–3 credible, named experts — academics, published authors, or senior industry practitioners — who have publicly stated a position on [Topic] that supports my article's main argument. Provide their name, title, the quote or paraphrased position, and a source URL."

AI SEO — Optimizing for the Bots Themselves

Here's the layer most SEOs still miss entirely.

If you want ChatGPT, Perplexity, or Google's AI Overviews to cite your content, your text needs to be structurally digestible for their RAG (Retrieval-Augmented Generation) systems. These systems extract information by identifying entity-attribute-value relationships — essentially: what thing, has what property, at what value.

Content that makes these relationships explicit gets cited. Content that buries them in fluffy prose doesn't.

The Citability Optimizer:

"Rewrite this article introduction so that all key Entity-Attribute-Value relationships are explicit. For example: '[Product X] offers [Feature Y] at [Price Z]' rather than vague descriptive sentences. The goal is maximum parseability by AI retrieval systems without sacrificing readability for humans."

The Structured Data Prompt:

"Analyze this article. Suggest the most appropriate Schema.org markup types (e.g., HowTo, FAQPage, Article, Review) and write the JSON-LD code for the top two that would most improve this page's chances of appearing in AI-generated answers and rich results."

The FAQ Schema Generator:

"Based on the content of this article, write 6 FAQ schema questions and answers. Each answer should be 40–60 words — specific enough to be directly useful, short enough to be lifted verbatim by an AI answer engine."

Multi-Modal Prompts (Vision & Data Analysis)

The GSC Trend Analyzer:

"I'm uploading a screenshot of my Google Search Console Performance report. A page that was performing well has shown a sharp decline over the past 60 days. Analyze the trend in the graph. Based on whether CTR or Impressions dropped first, diagnose the most likely cause and suggest 3 meta title variations designed to recover click-through rate."

The Keyword Clustering Agent:

"I'm uploading a CSV of 5,000 keywords exported from Semrush. Use Python to run a K-Means clustering analysis. Group them by search intent into 6–8 distinct clusters. Output a clean CSV with columns for keyword, cluster label, and primary intent. I'll import this directly into my content calendar."

The Heatmap Interpreter:

"I'm uploading a heatmap screenshot from Hotjar showing user behavior on [Page]. Identify where users are dropping off or ignoring key content sections. Suggest 3 structural changes to the page — headings, placement of key claims, or CTA position — to improve engagement and dwell time."

The Competitor Teardown:

"I'm uploading screenshots of the top 3 ranking articles for [Keyword]. Analyze their visual layout, content structure, and apparent word count. Identify the structural pattern they share and then suggest one structural element I could add that none of them include."

Your 2026 SEO Roadmap: Prompts + Workflows + Systems

Here's the honest truth: the prompts in this guide are your raw material. But the compounding advantage comes from turning them into repeatable systems.

The teams and freelancers winning in 2026 aren't using AI to write faster. They're using it to research deeper, audit more rigorously, and find the information gaps that no competitor has bothered to fill.

That's the game. And now you have the playbook.

The immediate next steps:

First, pick one workflow from this guide — the Audit, the Content Sprint, or the E-E-A-T Scout — and run it on your best-performing page from 6–12 months ago. You'll almost certainly find a quick-win refresh opportunity within 30 minutes.

Second, start building your own prompt library. The prompts here are a starting point. The best ones you'll develop will be hyper-specific to your niche, your audience, and the types of Information Gain only your experience can provide.

Third, remember the citability layer. As AI-generated answers take more SERP real estate, the question shifts from "does Google rank me?" to "does AI cite me?" Structuring your content for RAG readability isn't optional in 2026 — it's table stakes.

The era of the single prompt is over. The era of the agentic SEO workflow has begun. You're now equipped for it.