Gnothi AI for Marketers

OCDevel
  • 0.0 (0)
  • Technology
  • Weekly

Write the email in your brand's voice, then build the workflow that gets it to the right customer. Learn AI marketing from producing one useful asset to connecting content, campaigns and measurement across your tools. The course starts with audience research, prompts, brand examples and editing, using recognizable work such as landing pages, ad copy, emails and social posts. Those foundations carry into SEO, visibility in AI search, CRM, email and lifecycle marketing, paid advertising and analytics. Build toward no-code and low-code automation, reusable content processes and agents that handle several campaign steps. The emphasis stays on judging the work: whether a claim is supported, the voice fits, the audience is right and the result justifies the cost. Examples explain the prompts, settings and checks behind a marketing task, alongside mistakes such as invented statistics and over-automated email. Relevant news and practical shortcuts add context as platforms change. For in-house marketers, freelancers, agency operators and founders doing their own marketing, no programming experience is assumed. This show's audio is narrated by AI-generated synthetic voices.

Episodes

  1. 3d ago

    9. One Search Article Worth Judging

    Ledgerlane tests search with one article on why a first Self Assessment bill is bigger than expected, covering topic research, fact-checked drafting, indexing checks and a dated baseline. It also looks at tracking visibility in AI answers and Search Console's new generative AI report. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Judging search with one article Ledgerlane tests search with a single article that answers a question contractors already type into Google, links to the offer page, and can be confirmed as indexable. A dated baseline is written down so that in a few months the team can say whether search brought qualified leads or only visits. The offer page, booking form, Plausible and lead sheet from earlier chapters are already in place. Finding the topic Research starts with Google autocomplete, run signed out, with stems like "hmrc penalty letter" and modifiers added one at a time. It shows that a phrase is searched, not how often. People Also Ask is treated as a bonus, since it comes and goes. Keyword Planner is used only to compare phrases with each other, because the competition column measures advertisers and volumes may appear as bands. Search Console's Performance report confirms topics after publishing and hides rare queries. The chosen topic is the first Self Assessment bill that is much bigger than expected. The cause is payments on account: in a first year the full bill plus the first advance instalment fall due on 31 January, roughly one and a half times a single year's tax. A late-filing appeal was rejected because Ledgerlane doesn't handle appeals. Drafting and checking The assistant drafts from the facts register only, tagging each sentence with its source row or writing "no source". Every figure is checked, including late filing and late payment penalties with their conditions. Sole traders inside Making Tax Digital fall under the points-based system, so the stage should be checked for the tax year. Payments-on-account facts are added to the register as new rows, then a voice edit follows. Structure, links and indexing The title should describe only this page, and the date changes only when the facts do. The article and offer page link to each other with plain, descriptive links and no UTM tags. After publishing, URL Inspection shows the indexing status and Google's chosen canonical. A robots.txt block stops Googlebot from ever seeing a noindex tag, and a canonical tag is a signal, not a command. The article is added to the sitemap. Watching AI answers AI answers can only be observed. Vendor studies from Ahrefs and Writesonic suggest that ranking in Google doesn't settle what assistants cite. The method is a fixed list of five to ten queries, rerun every two weeks in each assistant, logging answers, cited URLs and screenshots. The baseline sheet, dated 6 November 2026, records the queries, launch impressions, current citations, traceable qualified leads (a minimum), form submits and hours spent. The new Search Console AI report Google launched a generative AI report in Search Console on 3 June 2026. It shows impressions from AI Overviews and AI Mode, with no clicks or queries. Adding its impressions to classic totals double counts, so it gets its own column in the baseline sheet. Plausible referrers estimate visits from AI tools.

  2. Oct 26

    8. Following One Lead From Link to Inbox

    Ledgerlane gains measurement: a definition of a qualified lead, UTM-tagged links captured in Tally hidden fields, and analytics set up within the UK's 2026 consent rules. A test lead reveals that the labels were lost, and embedding the form fixes it. The chapter closes by weighing three ways to move Tally records into a future CRM. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Defining a qualified lead for Ledgerlane Success is a booked diagnostic call from a one- or two-van trade contractor who arrived with a penalty letter or a large year-end bill. A form submission alone doesn't count. Until the Calendly step is unblocked by the open question on call length, a booked call is logged by hand once the founder agrees a time. Reach, engagement, leads, conversion, revenue These five measures answer different questions. Only qualified leads, conversions and revenue (£180 a month for one van, £260 for two) come from records the business controls. A made-up example shows a post that reaches thousands and still produces one customer. Events and UTM-tagged links Four events are tracked: page view, button click, form submit and call booked. UTM source, medium and campaign labels are added in lower case with fixed spellings. Tally hidden fields store those labels beside each submission. The field names are case-sensitive, and the fields only work after the form is published. Counting clicks and submits The button click reaches Plausible as a CTA Click goal, either through a plausible-event-name class on the button or through a short script. A submit inside an embedded form is recorded by a short listener that waits for Tally's FormSubmitted message and calls Plausible's event function. In Plausible that is set up as a Form Submission goal. UK consent after the Data (Use and Access) Act Since 5 February 2026, PECR has had an exception for aggregate statistics used to improve a site. Visitors must be told about it and given a free way to object, and providers must not reuse the data. The ICO finalised its storage and access guidance on 29 April 2026 and sets out what the exceptions cover. Advertising-linked setups, such as GA4 with Google Signals turned on, still need opt-in consent. Plausible's cookieless approach avoids a banner, and consent banners lead to under-counting by an unknown amount. Leads the reports miss Private sharing, switching devices, refused cookies and phone calls all leave leads without a label. Campaign counts are therefore minimums. A Google Sheet lead sheet follows each person from first contact to signing. A failed test and the fix A phone test with "test" labels arrived with empty hidden fields, and no submit event was recorded. The button had sent visitors to Tally's share address, which drops the labels. Embedding the form on the page passes the labels through, and a retest filled all three fields. The reply-time placeholder still blocks launch, and the follow-up email is still sent by hand. Routes into a CRM Tally's native integrations feed Sheets or Airtable but not sales CRMs. Zapier or Make can create or update HubSpot contacts by email address, at a cost that grows with usage. Webhooks give full control but put duplicate checking on the user and require a reply within ten seconds.

  3. Oct 19

    7. The Booking Form Behind the Button

    The offer page's booking button gets a destination: a six-field Tally form, a confirmation and a first follow-up email, with every line traced to a source and invented promises replaced by placeholders for the founder. The form is then checked for phones, keyboards and screen readers, and weighed against native CRM forms. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Six fields, each tied to a decision The "Book a diagnostic call" button on the Ledgerlane offer page finally leads somewhere: a short form, a confirmation message and a first follow-up email. Every field has to feed a decision. Name, email and phone let the founder reach the lead. A one-van or two-van choice maps straight onto the two price rows. A trigger question (penalty letter, big year-end bill, something else) shows what the call is about, and an optional box comes last. Income, postcode, business name and "how did you hear about us" are left off. A qualifying note above the fields says what Ledgerlane covers and what it does not, including that penalty appeals are not part of the service. Why Tally over Calendly, Typeform and Google Forms Calendly's free plan has fixed intake questions. Its answer-based logic and redirects need a paid plan, as its guide to routing forms and pricing page show. Tally's free plan includes branching logic and redirects, as its own comparison with Google Forms describes, and it is hosted in Belgium, as its GDPR page states. Typeform's free plan caps answers at ten a month, according to Typeform's pricing. A test entry produces a stored record and a notification email to the account owner. Catching invented promises Claude drafts the labels, the confirmation and the email inside the Ledgerlane Marketing project, and tags each sentence to a source. The illustrative fault is a confirmation that promises a call "within 24 hours" for "a quick 15-minute chat". Both numbers are invented, because call length and reply time are still open owner questions. The fix is a marked placeholder for the founder to fill, not a softer guess. The follow-up email restates the price, the inclusions and exclusions, and the two-week setup. It asks only whether the lead is VAT-registered. Checking it on a phone and without a mouse Each field needs a visible label tied to it in the page's code, as WCAG's guidance on labels or instructions requires. Errors must appear as text, not just colour, and focus must not be hidden behind the sticky button. Text needs a contrast ratio of 4.5:1. The email and phone fields need the right keyboard hints. Tap targets must meet the WCAG 2.2 24-pixel minimum. Lighthouse, axe or WAVE catch only part of the problems that matter, so the manual checks are the real inspection. Native forms versus a separate builder A native HubSpot form turns a submission straight into a contact record and matches it against existing contacts by email. In 2026 HubSpot added in-CRM meeting booking in its July updates and spam controls for native forms in its September updates. Klaviyo added multi-step landing pages in its February release. Tally records will need a connection that checks for duplicates once a CRM arrives, and that requirement goes in the fault note.

  4. Oct 12

    6. An Offer Page That Answers the Penalty Letter

    Ledgerlane's offer page gets built section by section: the order of the promise, one evidenced objection and two labelled hypotheses, and a draft from the assistant with three sourcing faults fixed. The page is checked at phone width, and the saved reply instruction is tested in a fresh chat. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website A page in the order a reader needs it Ledgerlane's offer page is written for a problem-aware trade contractor reading alone on a phone. It opens with the penalty-or-bill moment in contractors' own words. Copy research such as Copyhackers on writing landing pages recommends mirroring the visitor's symptoms above the fold. The next section covers the monthly timing that sets Ledgerlane apart from the once-a-year accountant. The price appears earlier than the usual pattern puts it: £180 a month for one van, £260 for two. Nielsen Norman Group on showing prices finds that buyers who see no price tend to assume it is too high. The exclusions sit beside the price, so a reader who needs a penalty appeal learns early that Ledgerlane doesn't handle one. Proof is limited to facts a reader can check, and the page has no invented testimonials. The button reads "Book a diagnostic call". The line under it about call length or reply time stays blank because no fact supports it. Objections, evidenced and hypothetical Three doubts are answered, and each FAQ question is phrased the way a visitor would ask it, in line with NN/g on FAQs that deliver value. "My accountant does this once a year" comes from an evidenced category. "Software is cheaper" and "Is it too late?" are labelled hypotheses because nothing in the evidence file quotes them. The "too late" answer gives the HMRC deadlines and penalty stages with their conditions and promises no outcome. It names what the page can't know, and that is why the call is the next step. Fixing the assistant's draft Each sentence carries a source tag. Three sentences fail: a reassurance line resting on a citation that doesn't support it a claim about saving time, which the assistant tagged "no source" itself a £100 penalty with its three-month condition missing One revision pass fixes all three. It also confirms the page implies no result from HMRC. Checking at phone width The chapter walks through Chrome DevTools device mode at widths of 320–390 px and notes that the tool only imitates a phone. The checks cover line breaks and the WCAG minimum target size of 24 px, or 44 px at the stricter level. A sticky button must never cover the exclusions or the penalty condition. The saved instruction in a fresh chat From early September to 12 October, Anthropic's documentation shows no change in how Projects apply instructions and files in new chats. That check excludes the September coordinator update and memory changes. A new inquiry from a two-van electrician about a large year-end bill passes all four checks. That shows the instruction carries over for this kind of message, not for every case.

  5. Oct 5

    5. Adapting a Defended Message to One Contractor's Situation

    A trade contractor's HMRC penalty letter becomes the test case for adapting a defended marketing message to one customer without adding promises, guesses or unsupported VAT claims. It ends with how a Claude Projects change spreads saved instructions across parallel threads. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Reading the brief against one penalty letter A one-van contractor with no bookkeeper writes to Ledgerlane after an HMRC late-filing penalty letter, asking for help and a price. Their message holds four facts, and anything else in a reply has to come from the brief, the product-facts register or the evidence file. The brief already covers this contractor in three places: the penalty trigger, a competitor that is the once-a-year accountant plus inertia, and the one-van price of £180 a month. It leaves three gaps: the penalty details, VAT status (the register's VAT row is still open with the founder), and the contractor's deadlines. Deadlines and penalties go in as register rows, conditions included The assistant doesn't recite tax rules from memory. Each deadline and penalty stage becomes a row taken from HMRC's guidance on Self Assessment penalties, with the condition kept in the same cell as the figure. "The penalty is £100" is false for many people. "A return up to three months late gets a fixed £100 penalty" is true. A Making Tax Digital row records the thresholds, including the drop to over £20,000 from April 2028. The reply may say the rules exist. It may not say they apply to this contractor, whose income is unknown. The reply must also fit the CAP Code's rules on misleading advertising. It can't guarantee or imply that a penalty will be cancelled. It can't leave out that interest keeps building up during an appeal. Penalty appeals aren't one of Ledgerlane's inclusions, so the reply only points to the appeal instructions in HMRC's letter. Auditing the assistant's draft The request asks for a bracketed source tag after every changed sentence and a list of unknowns at the end. The first draft reads well and has four faults: "We'll sort it out," which borrows a true citation to carry an untrue promise "Including VAT," the same unsupported claim that came back from the last chapter An undated deadline promise A £100 figure missing its condition After one revision, the reply passes the new-claims audit and the voice check. It closes by asking the contractor three questions. Situation versus person The offer-page section speaks to everyone with a penalty letter. The personal reply uses only the facts this contractor supplied. A correct guess still teaches the reader that you invent things. The method is saved as a reusable "situation adaptation" instruction, with a two-van tax-bill inquiry as practice. Parallel threads in Claude Projects The chapter reports that from 17 September 2026, a coordinator can send project work to parallel threads, and each thread inherits the project's instructions and files when it starts. One stale file now reaches every thread, so update the register before starting a job. To check that the instruction works without this chapter's chat history, test it in a fresh chat against four checks. If a check fails, fix the instruction, not the draft.

  6. Sep 28

    4. The Brand Guide Built From Passed and Rejected Drafts

    Ledgerlane's facts sheet becomes a dated, owned register, and its brand guide is rebuilt from accepted and rejected examples. Both are tested on a fresh FAQ answer that slips in an unsupported VAT claim. The chapter closes with how Custom GPT retirement and Gemini file-reading failures affect keeping reference files current. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Turning the facts sheet into a register A standard only helps when a draft can be checked against it. Ledgerlane's product-facts sheet, which lists the one-van and two-van prices, four inclusions, three exclusions and onboarding "about two weeks from signing", becomes a register. Each fact gets its own row with a claim, value, source, named owner, date last checked, and status. Conditions like "from signing" stay inside the value. A header gives the file's owner and its next full check. Clearly labelled sections, as Anthropic's prompting guidance recommends, let the assistant see where one fact ends and the next begins. Why a stale file slips through A Claude Project treats every uploaded file as available knowledge. A newer upload does not replace an older one. When two files disagree, Claude may blend them, hedge, or pick one. The result is a confident email quoting last year's price. There are three fixes. Keep one current register. Delete the old file before uploading the new one. Tell the project instructions to use only current rows, to ask when sources conflict without dates, and to list the rows each draft used. A fresh-chat audit then confirms the project is clean. Instructions guide the model, but only removing the old file removes the risk. A brand guide built from what passed and failed Adjectives like "friendly" and "clear" rule nothing out. Paired examples do. Two pieces of accepted work are included: the plain onboarding email and the corrected hero section. Two rejected pieces sit beside them. One is the "stress-free, hassle-free" ungrounded draft. The other is an on-voice benefit sentence with no customer evidence behind it. The assistant drafts seven rules, each tied to an example. Two get cut: "light humour" and "warm, approachable tone". Five checkable rules remain. The guide is laid out as a dated header, a who-we-sound-like description, phrases to use and avoid, the rules, and the side-by-side pairs. Testing both on a fresh request A fresh chat produces an FAQ answer for a two-van contractor. It passes on voice, but it states the price "including VAT", and no register row supports that. The phrase is removed. A new VAT row is added with its status left open, assigned to the founder to confirm. Keeping files current across assistants OpenAI is retiring Custom GPTs on 11 December 2026 and moving them to Plugins and Skills (migration FAQ). Skills are called up only when ChatGPT judges them relevant, so voice rules may not apply every time. Rerun the fact-listing audit after migrating. Gemini Gems can silently fail to read complex PDFs or oddly named files. Plain text with clear headings is safer.

  7. Sep 21

    3. Writing a Positioning Claim You Can Trace Back to a Line

    Ledgerlane's accurate hero copy speaks to nobody, so this chapter makes the audience decision out loud and turns it into a six-part brief with evidence line numbers behind every element. It covers picking a well-supported trigger situation over a thin one, naming the real competitive alternatives, splitting proof from inference, and the three citation faults found in the first draft — then how to reuse approved copy across channels without altering a single claim. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Choosing one situation and declining the others Ledgerlane's hero section is accurate and aimed at nobody. The missing piece is a decision no evidence file can make: which situation the message speaks to, and what it stops speaking to. Three independent lines in the evidence file describe the same trigger — months of nothing, then a penalty notice or an unexpectedly large tax bill, then someone looking for help that week. One line stands alone: a contractor who hands his paperwork to his sister-in-law once a quarter. The chapter explains why a message built on a single line fails unreadably, and sets a promotion rule — two independent sources to reach emerging support, three to carry a message of its own. The competitive set is five options: spreadsheet or glovebox, the once-a-year accountant, a spouse, self-managed software on a monthly subscription, and doing nothing. The incumbent is the year-end accountant plus inertia, which makes the difference a matter of when rather than how good — the fourth piece of positioning most drafts skip. Boundaries are named: accountant and bookkeeper are unprotected titles, chartered designations are not, and anyone providing bookkeeping or tax services as a business must register for money-laundering supervision before trading. The benefit is written for a problem-aware buyer in the vocabulary of the lines themselves. Exclusions work as a filter that improves who books. Proof splits into three piles, with the Self Assessment and CIS penalty timetable — one hundred pounds at a day late, ten pounds daily from three months, VAT registration at ninety thousand, Making Tax Digital from April 2026 — counted as proof of understanding the customer's year, not a claim about Ledgerlane. Client counts, testimonials and tax-saved figures stay out. The draft came back with three faults: an uncited benefit sentence about confidence, the single-source line promoted into proof, and a citation claiming monthly visibility the lines never mention. All three, and the revision, are shown. Getting more out of the approved copy Adapting the hero section to other channels under claim parity: format and pacing change, every number, timeframe, qualifier and exclusion holds. Channel limits set the shape — email preview truncation, the See more cut, two hundred and eighty characters on X. The assistant is asked for a claim breakdown before the variant. When a mandatory qualifier will not fit, link to full terms or pick a different claim.

  8. Sep 14

    2. What Customers Actually Said, and What You Assumed

    Instead of a made-up persona, the chapter builds a sourced file of verbatim customer language from the assistant's web research and uploaded call notes, with every quote checked against its link, separates observation from inference, and sets up a reusable brand brief in the project instructions. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Customer language with a source on every line An assistant asked for a customer persona produces a fluent "Dave, forty-one" whom nobody ever described; it was predicted, not gathered. The fix is one rule: a line counts as evidence only when you can name its source. The chapter names where UK trade contractors write about money in their own words, from review sites and Google Business Profiles to trade forums such as electriciansforums.net and the ContractorUK accounting and legal board, plus search phrasing, inbound notes, competitor FAQs and interviews run on Rob Fitzpatrick's Mom Test, and says which way each source is biased. It then puts the assistant to work. Web search or a longer Research run is asked for verbatim quotes with link, handle and date under four headings (who has the problem, their words, how they buy, what they compare against), and every link is opened, with smoothed or missing quotes dropped. Uploaded call notes, lost-deal notes and search phrasings, with personal details removed, go through the same questions. Surviving lines go into a twelve-line evidence file kept in the customers' own words, the in vivo coding described in Saldaña's coding manual. Each line is marked observation or inference, with three independent sources needed for a pattern, two for an emerging finding and one for a hypothesis. The assistant groups the lines by situation, names groups from their own words and cites line numbers, and the grouping is checked for invented names and extra quotes. A brief you write once Voice rules, a banned-words list and one accepted and one rejected example go into the project instructions, facts stay in files, a precedence rule settles conflicts, and a bare request in a fresh chat tests whether the brief is being inherited.

  9. Sep 10

    1. The Source Packet That Makes a Draft Publishable

    The course opens with which AI tool does which marketing job, then builds a source packet for an invented bookkeeping business inside a Claude Project and uses it to draft, inspect and fix a landing-page section claim by claim, followed by a short note on Claude's memory change. This episode is narrated by AI-generated synthetic voices. Episode page & show notes Visit website Which AI tool does which marketing job The course opens with a map of today's tools. Research, copy and editing go to a general assistant (Claude, ChatGPT or Gemini) working inside a project that holds the product facts, audience notes and brand examples. Images go to the image tools in ChatGPT and Gemini, Midjourney or Adobe Firefly, and video to Google's Veo, OpenAI's Sora or Runway. Work already held in a platform often suits that platform's own AI: HubSpot's Breeze, the writing and segment tools in Klaviyo and Mailchimp, Google's Performance Max and Meta's Advantage+. Zapier, Make and n8n move work between tools. The course starts with the assistant, because every other tool depends on the brief built there. Building a landing page you can defend Working with an invented small business, Ledgerlane Bookkeeping, the chapter builds a four-item source packet: product facts with prices and exclusions, an audience paragraph, a one-sentence goal (a booked diagnostic call, its length not yet set) and a real sample of the business's own writing. The packet goes into a Claude Project with standing instructions, following the file rules for uploading documents to Claude, and ChatGPT Projects and Gemini Gems are compared on file limits. The same request runs twice. The bare chat invents a company name, a discount and a wrong price. The project-backed draft ties every number to a line in the product facts, and a four-pass inspection still finds a dropped condition on the onboarding timeline and a missing scope line, both fixed in one further pass. The chapter closes by separating what the model, the project and the packet each contribute, and warns that an assistant's description of "your typical customer" is not evidence. Where the assistants changed this month Claude's memory now writes during a session and is sorted into editable topics, as set out in Anthropic's rundown of Claude's personalization features. Brand voice and facts belong in files you control, and saved memory deserves a quick audit.

  • 9 Episodes

About

Write the email in your brand's voice, then build the workflow that gets it to the right customer. Learn AI marketing from producing one useful asset to connecting content, campaigns and measurement across your tools. The course starts with audience research, prompts, brand examples and editing, using recognizable work such as landing pages, ad copy, emails and social posts. Those foundations carry into SEO, visibility in AI search, CRM, email and lifecycle marketing, paid advertising and analytics. Build toward no-code and low-code automation, reusable content processes and agents that handle several campaign steps. The emphasis stays on judging the work: whether a claim is supported, the voice fits, the audience is right and the result justifies the cost. Examples explain the prompts, settings and checks behind a marketing task, alongside mistakes such as invented statistics and over-automated email. Relevant news and practical shortcuts add context as platforms change. For in-house marketers, freelancers, agency operators and founders doing their own marketing, no programming experience is assumed. This show's audio is narrated by AI-generated synthetic voices.

Information

  • Creator
    OCDevel
  • Years Active
    2026
  • Episodes
    9
  • Rating
    Clean
  • Copyright
    © All rights reserved 2026, OCDevel
  • Show Website
    Gnothi AI for Marketers