leestuart

3.4K posts

leestuart banner
leestuart

leestuart

@leestuart

Shaking the tree since 73

Around Beigetreten Eylül 2008
283 Folgt290 Follower
leestuart
leestuart@leestuart·
@shanejones Manchester is a good spot for your sun condition :)
English
0
0
0
2
Shane
Shane@shanejones·
Absolute winner of a day. I give it an hour before I have to go and seek shade because I can't handle the sun.
Shane tweet media
English
2
0
3
64
leestuart
leestuart@leestuart·
@dejanseo Trying to decipher. The bigger context window allows more ‘space’ for attention to degrade as coding tasks use up more of it?
English
1
0
1
22
DEJAN
DEJAN@dejanseo·
opus 4.6 1M is not the same model - it's significantly less compliant/aligned for coding work and not as sharp as lower context variant of opus 4.6
English
1
0
2
328
leestuart
leestuart@leestuart·
@campion_steve Bad luck mate. Wondering how long you stick with Eddie though? It is not a case of he has taken it as far as he can? Meanwhile we are steadily screwing up automatic promotion.
English
0
0
1
13
Steve Campion
Steve Campion@campion_steve·
Was always gonna be hard to beat 12 man Barcelona! But questions need to be asked about the the set piece coach!
English
2
1
3
137
leestuart
leestuart@leestuart·
@top5seo Nice. Do I get to choose my paths yet :)
English
1
0
0
42
David McSweeney
David McSweeney@top5seo·
What's left of your website after LLM compression? What does AI consider important? What gets the model's attention? And what's discarded? When you strip away the fluff, what does AI actually understand about your brand's positioning on any topic? Every page compressed to entities, claims, facts, and statements. Classified. Deduplicated. Searchable by topic. Coming in a day or so. (or keep arguing about silly things like llms.txt I dunno)
English
5
0
23
1.7K
leestuart
leestuart@leestuart·
@RCollings98 Absolutely spot on EVERY single time we don’t support the manager at the crucial point. Many many times this has happened. Going all the way back to Karanka in the prem.
English
0
0
1
7
leestuart retweetet
Rowan Collings
Rowan Collings@RCollings98·
This is what happens when you dont sign a goal scorer. A great season possibly thrown away by bad recruitment. Season was in our hands going into the last transfer window. #Boro
English
1
1
1
179
leestuart
leestuart@leestuart·
@randfish Nice Rand. QQ - Are those example prompts synthesised? At a glance they look very 'clean' and well formed.
English
1
0
3
111
Rand Fishkin (follow @randderuiter on Threads)
We make audience research software. It tells you lots of things about any group of people on the web. But... it couldn't tell you how they used AI tools (prompts, topics)... until today 👇
English
15
3
55
6.8K
leestuart
leestuart@leestuart·
@gaganghotra_ Tracking prompts = zero. Probing models = hundreds.
English
0
0
0
13
Gagan Ghotra
Gagan Ghotra@gaganghotra_·
How many total prompts u guys be tracking for your whole #SEO client portfolio? 🤔
English
3
0
4
585
leestuart
leestuart@leestuart·
@TJiMTS * 5 full tax years often means 6 or 7 in practice depending on time of the year and split year treatment in exit period
English
0
0
3
1.5K
Your Accountant
Your Accountant@TJiMTS·
Leave the UK, sell shares abroad, pay no UK tax. Come back within 5 years? HMRC claws it all back. It's called the Temporary Non-Residence rules. If an evacuation brings you home early, the clock doesn't stop.
English
20
36
476
116.1K
leestuart retweetet
Your Accountant
Your Accountant@TJiMTS·
UAE: 5bn spent in 2 days on defending non citizens who don’t pay income taxes UK: we can’t rescue our citizens from a war zone because it would be expensive and they don’t pay income taxes I wonder why they left 🤔
English
103
446
4.8K
242.4K
leestuart
leestuart@leestuart·
I thought that was a lot of extremists and brain dead Karen’s on here until I looked on Theads my god it’s like 10x
English
0
0
0
7
leestuart
leestuart@leestuart·
@dejanseo So the immense variability of the response is in part due to the immense variability of the grounding context?
English
0
0
0
35
DEJAN
DEJAN@dejanseo·
Only ~250 words from your page end up in Gemini's grounding context. This extractive summarization snippet is different for each query and can take different parts of the page as the highest scoring sequences.
DEJAN tweet media
English
1
4
18
1.3K
leestuart
leestuart@leestuart·
@searchmartin They are so far invested they don’t have a choice.
English
0
0
0
20
leestuart
leestuart@leestuart·
@MalteLandwehr If the involvement of AI improves the content processed by resolving the query, delivering the information or solving the users problem more accurately then it’s absolutely fine and no modern search engine will penalise this. These platforms not so much :)
English
1
0
1
212
Malte Landwehr
Malte Landwehr@MalteLandwehr·
Are AI content tools tanking their customer's rankings? I recently discovered the term "Mount AI" - and I love it! It perfectly describes what happens when a website starts to publish large amounts of AI-written content. First a rapid increase in SEO visibility. Often to millions of clicks per month. Followed by an equally quick decrease into oblivion. If you follow @glenngabe or @lilyraynyc, you have probably seen 20+ examples of this in recent months. I went ahead and looked at the case studies and reference customers of a popular AI content tool. The result is shocking: 57% of them tanked. 22% even with a perfect Mount AI shape. Those without a Mount AI never saw a significant increase. They just went from flat to downhill and skipped the ranking peak altogether. Important: these are not random customers. These are their flagship clients. The ones they interviewed for a case study. I don't even want to know what the development for the average customer looks like. I do not want to call out the responsible tool. I don't even think they are the worst offender. But I urge everyone to think before you automate content creation. Don't get me wrong. I have personally initiated and overseen the publication of millions of programmatic landing pages. And of hundreds of thousands of AI-written content pieces. They are one of my favorite SEO instruments. But the way some tools sell and market AI content is irresponsible. One last thing: If your Google rankings tank, you are less likely to be cited by LLMs. SEO is still the discovery layer for grounding.
Malte Landwehr tweet media
English
3
2
29
14.7K
leestuart
leestuart@leestuart·
@Boro At every single critical occasion over the last 10 yrs including when in the premier league Boro have refused to support there manager at the most critical point of a season. Preferring prudence to promotion. You get what you pay for. Cult of mediocrity. Every time.
English
0
0
2
743
Martin MacDonald
Martin MacDonald@searchmartin·
Look I'm trying REALLY REALLY hard not to call out these people, but....
Martin MacDonald tweet media
Kalash@kalashvasaniya

Prompt: You are an expert Programmatic SEO Content Architect and Technical SEO Strategist. Your task is to generate scalable, high-quality, non-duplicate SEO pages based on the 12 Programmatic SEO Playbooks listed below. GOAL: Generate structured, indexable, unique, valuable, and fully functional page content and metadata for large-scale pSEO deployment (100,000+ pages) with ZERO thin pages, ZERO duplicate pages, and ZERO broken or 404 URLs. --- ### PLAYBOOKS YOU MUST SUPPORT 1. Templates 2. Curation 3. Conversions 4. Comparisons 5. Examples 6. Locations 7. Personas 8. Integrations 9. Glossary 10. Translations 11. Directory 12. Profiles --- ### GLOBAL RULES (STRICT) 1. Every page must provide real, useful, user-first value. 2. Never generate placeholder or generic filler content. 3. Each page must include unique angles, examples, or insights. 4. Every URL generated must map to real generated content. 5. If valid data does not exist → DO NOT generate that page. 6. Generate internal linking suggestions between related pages. 7. Avoid keyword stuffing. Write naturally. 8. Each page must be optimized for search intent satisfaction. 9. Each page must include structured schema-ready data. 10. Output must be consistent and machine-readable. --- ### PAGE SCALE STRATEGY Generate pages using safe combinational expansion based on: • Categories • Subcategories • Locations • Personas • Tools/Products • File formats • Industries • Languages • Integrations • Use cases Only generate combinations where meaningful real-world value exists. --- ### URL VALIDATION RULES Before generating a page: - Confirm the URL slug is unique. - Confirm input data exists. - Confirm content length minimum threshold is met. - Confirm at least 3 internal linking opportunities exist. If validation fails → discard the page. --- ### REQUIRED PAGE OUTPUT FORMAT Return output strictly in JSON format: { "url": "", "playbook_type": "", "seo": { "title": "", "meta_description": "", "primary_keyword": "", "secondary_keywords": [], "search_intent": "" }, "content": { "h1": "", "introduction": "", "sections": [ { "heading": "", "body": "" } ], "faq": [ { "question": "", "answer": "" } ], "call_to_action": "" }, "schema": { "type": "", "structured_data": {} }, "internal_links": [], "related_pages": [], "data_requirements_used": [] } --- ### PLAYBOOK-SPECIFIC REQUIREMENTS #### TEMPLATES Include: • Download or usage instructions • Multiple variations • Practical implementation guidance --- #### CURATION Include: • Ranking criteria • Pros/Cons • Comparison summary table --- #### CONVERSIONS Include: • Real conversion logic • Related converters suggestions • Example conversions --- #### COMPARISONS Include: • Feature matrix • Use-case recommendations • Verdict summary --- #### EXAMPLES Include: • Real world examples • Analysis explaining why examples work • Categorization filters --- #### LOCATIONS Include: • Location-specific insights • Pricing/regulation/local trends • Local recommendations --- #### PERSONAS Include: • Persona pain points • Use-case solutions • Persona-specific benefits --- #### INTEGRATIONS Include: • Setup steps • Use cases • Workflow examples --- #### GLOSSARY Include: • Beginner-friendly explanation • Technical depth section • Related term linking --- #### TRANSLATIONS Include: • Native language SEO optimization • Cultural localization • hreflang reference mapping --- #### DIRECTORY Include: • Filtering metadata • Listing attributes • Categorization tags --- #### PROFILES Include: • Verified factual data • Timeline or milestones • Unique insight summary --- ### CONTENT QUALITY RULES Minimum Requirements: • 900+ words informational pages • 600+ words utility pages • 3+ FAQs • 5+ internal links • 2+ related page suggestions • Human readable formatting • Semantic heading hierarchy --- ### SCALABILITY SAFETY CHECK For each batch: 1. Detect duplicate intent 2. Detect overlapping keyword cannibalization 3. Reject thin or repetitive pages 4. Enforce diversity in headings and examples 5. Validate slug uniqueness --- ### INTERNAL LINKING STRATEGY Each generated page must link to: • Parent category page • At least 2 sibling pages • At least 2 cross-playbook pages --- ### OUTPUT BATCH RULES Generate pages in batches of 100. Ensure: • No repeated slugs • No repeated primary keyword • Each batch contains mixed playbook types --- ### DATA INPUT FORMAT (DYNAMIC) You will receive structured input datasets like: { "categories": [], "tools": [], "locations": [], "personas": [], "file_formats": [], "languages": [], "integrations": [] } Only generate pages using this dataset. --- ### FAILURE HANDLING If insufficient input data exists: Return: { "status": "SKIPPED", "reason": "" } --- ### FINAL GOAL Create highly indexable, conversion-focused, evergreen SEO pages that can scale safely to 100,000+ URLs while maintaining content uniqueness, search value, and technical SEO integrity. Use Claude Opus 4.6 MAX

English
2
0
5
812
leestuart
leestuart@leestuart·
@foley_seo Agreed. I wonder though at what point the contextual proof provided by organic is diminished to the point the ads lose their validation?
English
0
0
1
500
Daniel Foley Carter
Daniel Foley Carter@foley_seo·
As an SEO specialist who audits and runs an agency, I have seen firsthand SO much decimation from Google's practices and advancements in AI. Google is killing off the value of exchange, now they've digested the web & trained their models, they have far less need to serve the results they once did for the exchange of value. Now, they are PROACTIVELY pushing organic out of the way - JUST AI OVERVIEWS + blended sponsored results alone have done untold damage to hundreds of millions of websites. Google WANTS PAID CLICKS, it wants USERS TO STAY in the ecosystem and not to click away. But where do webmasters go from here? After years of seamingly unending punishment (Google HCU, Blended Core Updates, AIOs and then Blended Sponsored Results) - it's FAR HARDER to get clicks. Initially - it was easy to say that it only really ate into informational traffic - but, not only is that not true, but its where a lot of "pre-purchase" buyers go before deciding. We can call Google's incessant push on Gemini, AIOs and AI Mode progress, but, we should also see it for what it is - another corporate giant who stands to profit from the losses of tens of millions of websites/businesses globally. It's clear, Google is going more and more towards PAY TO PLAY. Some may call it progress, others call it greed, but let's be real here.......... I see more SEOs bickering over GEO or giving themselves new titles "AI Experts" so they can muscle in on the tiny % share of traffic that comes from AI vs the ONCE large plethora of traffic that was available to SEOs. The thing is, Google has NO shame whatsoever. Look at the untold damage they've done to businesses globally - look at the carnage of Helpful Content - and what did millions of webmasters end up having to contend with? Decimated CTRs as AIOs rolled out - rechurning peoples content with minimal / no proper source citation or anything meaningful enough to garner a click. LLM traffic isn't going to account for a FRACTION of the traffic that Google has systemically taken away by entrenching more and more users in "in-page" features be it an AIO or AI MODE. It's not that SEO isn't viable, it 100% still is, but the effort to get a click is HARDER at a time businesses are battling with touch economic climates, shrinking budgets + shiny object syndrome with AI. I love SEO, but honestly, for the first time in my 25+ years in this industry, I can see the first cracks appearing in viability when Google is shifting more and more towards pay to play.
Daniel Foley Carter tweet media
English
37
15
236
20.9K
leestuart
leestuart@leestuart·
@gaetano_nyc Flat is definitely the new up for mature sites in competitive knowledge domains.
English
0
0
1
52
Gaetano DiNardi
Gaetano DiNardi@gaetano_nyc·
I don't think executives realize that FLAT organic traffic is actually a GOOD thing right now. I am going to publish a case study from last year where we busted our asses on content (net-new plus updates) and the GAINS we made were not able to outpace the LOSSES we experienced with the declining pages that we ignored. In other words, if we didn't bust our asses to stay FLAT we would have TANKED. So we did all that work just to stay FLAT overall but the traffic was BETTER quality in the long-run which proved evident in the conversion data 🧠 🤓
English
9
0
29
1.3K