Claude Training Program · Week 3 · Efficiency Track

Deeper Analysis with Claude:
From Data to Decisions

📖 Tutorial 5 of 8 ⏱ 60–75 minutes 👥 All team members 🎯 Prerequisite: Tutorials 1 & 2

Tutorials 1 and 2 focused on Claude for individual tasks — reviewing title tags, summarising audits, writing client copy. This tutorial goes a level deeper: using Claude for multi-step reasoning and strategic analysis. You'll learn how to upload and interrogate Search Console data, identify keyword cannibalisation, compare page structures, and generate full technical SEO briefs. The goal is to use Claude not just as a writing assistant, but as an analyst.

Learning Objectives
  • Structure complex, multi-part analysis prompts effectively
  • Use Claude to identify cannibalisation patterns in Search Console data
  • Compare competing pages and produce a content consolidation recommendation
  • Generate a complete technical SEO brief from a client intake form
  • Understand when to break analysis across multiple prompts vs. one long prompt

1The Shift from Tasks to Analysis

There's an important distinction between using Claude for tasks and using it for analysis. Tasks are discrete and well-defined — "rewrite this title tag", "fix this schema". Analysis is open-ended — "what's going wrong with our rankings and why?"

📋 Task-level use

Discrete, well-defined. Claude executes a specific instruction. Output is directly usable. One prompt, one output. Examples: rewrite, summarise, translate, format.

🔍 Analysis-level use

Open-ended, reasoning-heavy. Claude interprets data, identifies patterns, and makes recommendations. Often involves multiple follow-up prompts. Output informs decisions rather than being the final deliverable.

Analysis-level use requires a different prompting approach: you need to give Claude more context, guide it through a reasoning chain, and ask follow-up questions to drill into findings. The rest of this tutorial teaches exactly that.

2Preparing Your Data for Claude

Before any analysis prompt, the quality of data you provide determines the quality of insight you get back. Here's how to prepare the three main data sources used in this tutorial:

📊 Google Search Console Export

Go to Performance → Search results. Set your date range (last 3 months is ideal for spotting trends). Click Export → Download CSV. In the export, you want the Queries tab. Optionally, also export the Pages tab separately.

For cannibalisation analysis, use the Search type: Web filter and enable both Clicks, Impressions, CTR, and Position columns. The more date range you include, the more Claude can spot trends vs. one-off spikes.

Claude can handle up to roughly 200–300 rows pasted directly. For larger exports, filter to your most important queries first (e.g. top 200 by impressions), or run multiple focused analysis prompts.

📄 Page Content for Comparison

For page structure comparisons, you don't need to paste entire page HTML. Instead, paste: the page title, meta description, all heading tags (H1–H3) in order, and the first paragraph of each main content section. Claude can infer content structure from headings far more efficiently than from raw HTML.

A quick way to grab headings: open the page, open browser DevTools, and run Array.from(document.querySelectorAll('h1,h2,h3')).map(h => h.tagName + ': ' + h.innerText).join('\n') in the Console tab. Copy the output.

📝 Client Intake Information

For the brief generation workflow, you'll need: the client's website URL, industry and target audience, their top 3–5 business goals, any known technical issues, their current CMS and hosting setup, and any previous SEO work done. A one-page intake form filled out before an onboarding call gives Claude everything it needs.

A
Keyword Cannibalisation Analysis
Search Console

Keyword cannibalisation happens when two or more pages on the same site compete for the same search query — splitting clicks and confusing Google about which page should rank. It's one of the most common issues on established sites and one of the hardest to spot manually at scale.

This workflow uses a two-prompt chain: the first prompt identifies cannibalisation signals, the second produces specific recommendations for each case found.

How to structure the analysis chain

Prompt 1 — Surface patterns
"Analyse this Search Console data and identify queries where multiple pages are competing..."
Claude returns a list of suspected cannibalisation pairs
Prompt 2 — Drill into a specific case
"For the cannibalisation between /blog/seo-audit and /services/seo-audit, what do you recommend — consolidate, canonicalise, or differentiate?"
Claude reasons through the specific case with more nuance
Optional Prompt 3 — Generate the fix
"Write a developer brief for implementing the canonical tag fix on these three pages."
Claude produces an actionable output directly from the analysis
Prompt A1 · Cannibalisation Detection Search Console
You are a senior SEO analyst. Analyse the following Google Search Console data for [DOMAIN]. I want you to identify keyword cannibalisation signals — cases where two or more pages are competing for the same or closely related queries. // Paste your GSC Queries export here (CSV format is fine) [PASTE SEARCH CONSOLE DATA] For each cannibalisation signal you identify: 1. List the query (or query cluster) at issue 2. List the pages competing for it with their average positions 3. Assess severity: Critical (both pages ranking 1–10 and splitting clicks), Medium (one page ranking well, one occasionally appearing), Low (positional fluctuation suggesting Google is uncertain) 4. Suggest the likely root cause: duplicate content, overlapping topics, or missing differentiation Format your response as: - A summary paragraph (how widespread is the issue on this site?) - A table: | Query | Page A | Pos A | Page B | Pos B | Severity | Likely Cause | - After the table, list your top 3 highest-priority cases to address first
Prompt A2 · Consolidation Recommendation (follow-up) Search Console
// Run this as a follow-up in the same conversation — Claude already has the data For the cannibalisation case between [PAGE A URL] and [PAGE B URL] competing for "[QUERY]": Recommend one of these three approaches and explain your reasoning: 1. CONSOLIDATE — merge the two pages into one, redirect the weaker to the stronger 2. CANONICALISE — keep both pages but set a canonical tag pointing to the preferred one 3. DIFFERENTIATE — keep both pages but rewrite them to target clearly distinct intents Base your recommendation on: - Which page has stronger performance signals (more clicks, better average position) - Whether the two pages serve genuinely different search intents - The likely implementation effort Then write a one-paragraph brief explaining the recommendation in plain English for a client who will need to approve the change.
B
Page Content Structure Comparison
Content Analysis

When two pages are cannibalising, or when a page is underperforming against a clearly stronger competitor, you need to understand why at a content level. This prompt takes the heading structure and key content sections of two pages and produces a direct, actionable comparison.

What to paste: Use the DevTools console trick from Section 2 to quickly extract headings from both pages. For each page, also paste the meta title, meta description, and URL. You don't need to paste full body copy — headings alone give Claude a strong structural signal.

Prompt B1 · Page Structure Comparison Content Analysis
You are a senior SEO content strategist. Compare the structure of these two pages that are competing for the query "[TARGET QUERY]". PAGE A — [URL A] Title: [TITLE A] Meta description: [META A] Headings: [PASTE HEADING STRUCTURE OF PAGE A] PAGE B — [URL B] Title: [TITLE B] Meta description: [META B] Headings: [PASTE HEADING STRUCTURE OF PAGE B] Analyse these two pages and answer: 1. INTENT ALIGNMENT — Does each page match the likely search intent for "[TARGET QUERY]"? (informational / commercial / transactional) 2. STRUCTURAL DIFFERENCES — What topics does Page A cover that Page B doesn't, and vice versa? 3. OVERLAP — Which headings/topics are near-duplicates across both pages? 4. RECOMMENDATION — Should these pages be consolidated, differentiated, or is one clearly the right page to optimise? 5. ACTION PLAN — If we keep both pages, what specific heading changes would remove the overlap? If we consolidate, what structure should the merged page follow? Be specific and concrete. Name the exact headings to add, remove, or rewrite.
C
Generating a Full Technical SEO Brief
Strategy

One of the highest-value uses of Claude in agency work is turning a client intake conversation into a structured, comprehensive SEO brief — the kind that previously took a senior strategist a half day to write. This prompt generates the full brief in one pass, ready for review and light editing.

The intake form template

Before running this prompt, fill out this intake form for the client. The more detail you provide, the more actionable the brief will be:

📋 Client Intake Form — paste into the prompt below
BUSINESS
- Company name: [NAME]
- Website: [URL]
- Industry / niche: [INDUSTRY]
- Main products or services: [LIST]
- Target audience: [WHO ARE THEIR CUSTOMERS?]
- Key geographic markets: [e.g. UK, US, Global]

SEO GOALS
- Primary goal: [e.g. Increase organic leads by 30% in 6 months]
- Secondary goals: [e.g. Improve rankings for [keyword cluster], fix site speed]
- Any upcoming events: [e.g. site migration, product launch, rebrand]

TECHNICAL CONTEXT
- CMS: [e.g. WordPress, Shopify, custom]
- Hosting / CDN: [if known]
- Site size (approx. pages): [NUMBER]
- Known technical issues: [e.g. slow page speed, duplicate content, no schema]
- Previous SEO work: [e.g. Audit done 12 months ago, on-page work only]

COMPETITIVE CONTEXT
- Main organic competitors: [LIST 2–4 DOMAINS]
- Where do they currently rank vs competitors? [e.g. Page 2 for most head terms]

CONSTRAINTS
- Development resource available: [e.g. One developer, 2 days/month]
- Content resource available: [e.g. In-house writer, 2 articles/month]
- Budget level: [e.g. Limited / Medium / Significant]
  
Prompt C1 · Technical SEO Brief Generator Strategy
You are a senior technical SEO strategist at an SEO agency. Using the client information below, write a comprehensive technical SEO brief that will guide our team's work for the next 3–6 months. [PASTE COMPLETED INTAKE FORM HERE] The brief should contain these sections: 1. SITUATION SUMMARY (2–3 paragraphs) A clear-eyed assessment of where the client is now, what their main challenges are, and what success looks like. 2. TECHNICAL AUDIT PRIORITIES Based on the known issues and context, list the 5–8 most important technical areas to audit, in priority order. For each: what to audit, why it matters for this specific client, and what a good outcome looks like. 3. QUICK WINS (first 30 days) 3–5 specific, actionable tasks that can deliver visible improvement quickly given their constraints. 4. 90-DAY ROADMAP A phased plan: Month 1 (technical foundation), Month 2 (on-page and content), Month 3 (authority and measurement). Each phase should have 3–5 concrete deliverables. 5. SUCCESS METRICS What KPIs should we track? How do we measure progress against their stated goals? Include both leading indicators (crawl coverage, Core Web Vitals scores) and lagging indicators (organic traffic, conversions). 6. RISKS AND DEPENDENCIES What could slow progress? What decisions or access do we need from the client? Write in a professional but direct tone. The primary reader is a senior SEO specialist on our team. Be specific — name the actual tools, checks, and page types relevant to their CMS and industry.

Editing the brief: Claude's first draft will be ~80% ready. The most common edits needed: (1) making quick wins more specific to the actual client's stack, (2) adjusting timelines to match real developer availability, (3) adding any client-specific context Claude couldn't infer. A 15-minute edit is all that's usually needed.

6Getting Better Reasoning from Claude

For complex analytical tasks, there are several techniques that produce significantly deeper and more reliable reasoning:

Ask Claude to reason before concluding

Adding "think step by step" or "reason through this before giving your answer" prompts Claude to work through the problem explicitly rather than jumping to a conclusion. This is especially useful when the answer isn't obvious.

Without reasoning instruction

"Which of these two pages should we consolidate into?"

With reasoning instruction

"Which of these two pages should we consolidate into? Before giving your recommendation, reason through: backlink profile, content quality signals, URL structure, and historical ranking performance."

Ask for confidence levels

Claude can't be certain about things it can only infer. Adding "flag any assumptions you're making and your confidence level in each recommendation" produces more honest, trustworthy output — important when the output informs real client decisions.

Ask Claude to steelman the opposite view

For strategic decisions, ask: "Now argue the case for the opposite recommendation — what would make consolidation a bad idea here?" This surfaces risks and edge cases Claude might not have volunteered.

Break very large analyses into focused sub-questions

Instead of one giant prompt…Use a sequence of focused prompts
"Analyse everything wrong with this site's SEO"Prompt 1: "Analyse crawlability issues only." → Prompt 2: "Now analyse the on-page issues." → Prompt 3: "Summarise the top 5 priorities across both analyses."
"Tell me why our rankings dropped"Prompt 1: "Here's our GSC data — what queries declined most?" → Prompt 2: "For those queries, what are the most likely causes?" → Prompt 3: "Which cause is most likely given that we did [X] on [date]?"

7Practice Exercises

✏️ Exercise 1 — Cannibalisation hunt

Run the cannibalisation analysis on a real client's Search Console data:

  1. Export the last 3 months of query data from GSC for one client
  2. Filter to the top 150–200 queries by impressions
  3. Run Prompt A1 and review Claude's cannibalisation findings
  4. Pick the most severe case and run Prompt A2 as a follow-up
  5. Compare Claude's recommendation to your own instinct — do you agree? If not, push back and ask Claude to reconsider given your additional context
✏️ Exercise 2 — Brief generation

Generate a full technical SEO brief for a new or existing client:

  1. Fill out the intake form template from Section 5 for a real client
  2. Run Prompt C1 and read the output brief carefully
  3. Identify 3 things the brief got right without you having to spell them out
  4. Identify 2 things that need editing or are inaccurate — make the edits
  5. Estimate: how long would this brief have taken to write manually? What's the time saving?
✏️ Exercise 3 — Test the reasoning techniques

Experiment with the reasoning techniques from Section 6:

  1. Take any analysis prompt from this tutorial and run it without any reasoning instructions
  2. Run the same prompt again, adding "reason step by step before giving your final answer"
  3. Compare the two outputs — is the reasoning more transparent? Is the recommendation different?
  4. Try adding "flag any assumptions and your confidence level in each point" to the second run
  5. Share both outputs with a colleague and discuss which they find more useful

8Summary

🔗
Chain Your Prompts
Surface patterns first, then drill into specific cases — don't try to do everything in one prompt
🧠
Ask for Reasoning
"Think step by step" and "flag assumptions" produce more reliable, trustworthy analytical output
📋
Brief in Minutes
A well-filled intake form + Prompt C1 produces an 80%-ready strategy brief in under 2 minutes

Key takeaway: The difference between Claude as a task tool and Claude as an analyst is in how you prompt it. Provide rich context, ask for structured reasoning, chain your prompts from broad to specific, and always apply your own SEO expertise when reviewing the output. Claude is the analyst — you're the senior partner who reviews the work.