AI for Marketing

AI Marketing

Use AI for market research, copywriting frameworks, and audience segmentation — with prompts that produce genuinely usable marketing assets, not generic filler.

AI Ad Manager

Generate ad copy variants at scale, brainstorm targeting angles, and use AI to analyze ad performance data for Google and Meta campaigns.

AI Content Creation

Write faster with AI without sounding like AI, generate on-brand images, and repurpose one piece of content into many formats.

AI YouTube Management

Script videos faster, write titles and thumbnails that actually get clicked, and use AI to plan a channel content calendar and read your analytics.

AI SEO & Search Visibility

Use AI to do keyword research, optimize content for search, and get your brand cited by AI answer engines like ChatGPT, Perplexity, and Google AI Overviews.

Ship a Portfolio Site in an Afternoon

Use a template plus AI-written copy to put a real portfolio online. The hard part is not the code, it is writing about your own work without sounding like everyone else, so most of this project is about the words.

Run an Honest CV Review

Build a review process that tells you what is weak in your CV instead of politely rewriting it. Includes a screening simulation that shows how it reads in the six seconds it actually gets.

Write Landing Page Copy That Says Something

Produce a full landing page — headline, subhead, three benefits, objection handling, call to action — for a real product. The method is research-first: you interview the customer before you write a word.

Build a Meeting Notes System

Turn rambling notes into decisions, owners and deadlines — in a format consistent enough that you can search it six months later. The value is in the structure, not the summary.

Plan a Month of Content Without Burning Out

Build a content calendar grounded in a small set of themes rather than thirty unrelated ideas. Includes the repurposing pass that most people skip and then wonder why the work feels endless.

Build Your Own Prompt Library

Stop rewriting the same prompt. Build a small, organised, tested personal library — and learn the versioning habit that stops it rotting into a folder of near-duplicates.

The Explanation Ladder Challenge

Get a model to explain one concept at four levels of expertise without dumbing it down into nonsense. Tests whether you can control depth precisely rather than just asking for "simpler".

The Constraint Stack

Add constraints one at a time until output quality collapses, and find where the ceiling actually is. Teaches more about prompt design in twenty minutes than reading about it for a week.

The Same Message, Five Ways

Rewrite one difficult message for five audiences without changing what it says. Tests whether you can control register precisely — the skill behind almost all professional AI writing use.

Refactor Without Breaking It

Improve code structure while proving behaviour is unchanged. Tests the discipline of characterising existing behaviour before changing anything — the part everyone skips.

The Wrong Chart Challenge

Deliberately visualise the same data four wrong ways to learn why the right one is right. Faster and more memorable than reading chart-selection guidance.

Two Versions, One Difference

Write two variants of a piece of copy that differ in exactly one respect, so the result would actually tell you something. Harder than it sounds and the reason most informal tests are uninformative.

What Is Prompt Engineering? A Practical Guide for 2026

Prompt engineering is the craft of writing model inputs that reliably produce the output you want. This guide covers the five-part framework, the techniques that actually matter, and the mistakes that make output generic.

GPT vs Claude vs Gemini: An Honest Comparison

A practical comparison of the three leading AI models across writing, coding, reasoning, long documents and cost — including which one to reach for on which task, and where each genuinely falls short.

Context Engineering vs Prompt Engineering: What Actually Changed

Context engineering is the term that replaced prompt engineering in serious AI work. It is not a rebrand — the job genuinely shifted from writing better instructions to controlling what the model can see. Here is the difference and why it matters.

Prompt

A prompt is the input you give an AI model to produce an output. Effective prompts specify five things: the role the model should adopt, relevant context, the specific task, the output format, and any constraints.

Prompt engineering

Prompt engineering is the practice of designing model inputs that reliably produce the output you want. It combines clear instruction-writing, structured formatting, worked examples, and systematic testing.

Temperature

Temperature controls how random a model's word choices are. Low values (0-0.3) make output focused and repeatable; high values (0.8-1.2) make it more varied and creative but less reliable.

Zero-shot prompting

Zero-shot prompting means asking a model to do a task with no worked examples — just an instruction. It works well for common tasks the model has seen extensively in training.

Meta-prompting

Meta-prompting is using a model to write, critique or improve prompts. You describe the task and the failure modes you want to avoid, and the model drafts the prompt.

Reasoning model

A reasoning model is trained to generate extended internal deliberation before answering. It trades latency and cost for substantially better performance on maths, logic, coding and multi-step problems.

Multimodal model

A multimodal model accepts or produces more than one type of data — commonly text plus images, and increasingly audio and video. It processes them in a shared representation rather than through separate pipelines.

Fine-tuning

Fine-tuning continues training a pre-trained model on your own examples to specialise its behaviour. It is the right tool for teaching consistent style, format or classification behaviour — not for adding knowledge.

Prompt caching

Prompt caching stores the processed form of a repeated prompt prefix so subsequent requests reusing it are cheaper and faster. Cached input tokens typically cost a fraction of normal input tokens.

Prompt injection

Prompt injection is an attack where malicious instructions hidden in content the model processes override the developer's intended behaviour. It is the most serious unsolved security issue in LLM applications.

Blog Post Outline Generator

Planning long-form content before writing

Tone Rewriter

Adjusting tone without rewriting from scratch

Cold Email Opener Generator

Outbound sales / partnership outreach

Competitor Positioning Snapshot

Competitive research with citations. Use this before a positioning workshop, a pricing review, or writing comparison copy — the table format makes it easy to spot where a rival is genuinely stronger versus where they are just louder. Always run it on a search-grounded model like Perplexity so every claim carries a source and a date you can verify.

Ad Angle Brainstorm

Generating creative directions before writing ad copy

Product Photo Prompt (Studio Style)

Clean product shots for a store listing. Useful when you need placeholder or concept imagery before a real photoshoot, or for a product that does not physically exist yet. Keep the subject description first and the styling details after — most image models weight earlier tokens more heavily, so leading with the object keeps it recognisable.

Brand Mood Board Prompt

Visual direction before a brand shoot. Generating a mood board first gives designers and photographers something concrete to react to, which is far faster than describing a feeling in a brief. Run it several times with different adjectives and keep the two or three frames that feel closest — the misses are as informative as the hits.

YouTube Video Idea Generator

Content calendar brainstorming

Role + Constraints to Kill Vagueness — ChatGPT

When answers are generic, the fix is almost always more specificity, not a longer prompt.

Meta-Prompting: Prompts That Write Prompts

The fastest way to a great prompt is asking the model to write and critique one.

Auto Content Repurposing Pipeline

Trigger: new blog post published (RSS or webhook) -> AI node: generate a Twitter/X thread, LinkedIn post, and email blurb from the article -> Route each to the right channel.

AI Email Triage & Auto-Responder

Trigger: new email in inbox -> AI node classifies intent (support, sales, spam, urgent) -> conditional branches route to auto-reply, Slack alert, or human queue..

Human-in-the-Loop Approval Gates

The highest-trust automations pause for approval at the moments that matter: before sending externally, before spending money, before deleting anything.

Finding Your Audience's Real Language

Before writing copy, use AI to mine the language your audience actually uses — their complaints, objections, and desires — so your copy sounds like them, not like a brochure..

AIDA and PAS Prompts — ChatGPT

AIDA (Attention, Interest, Desire, Action) and PAS (Problem, Agitate, Solution) are proven copy structures.

AIDA and PAS Prompts — Claude

AIDA (Attention, Interest, Desire, Action) and PAS (Problem, Agitate, Solution) are proven copy structures.

AI-Assisted Audience Segments

Feed AI a description of your customer base or CRM export summary and ask it to propose segments with distinct messaging angles — a fast way to go from "everyone" to targeted campaigns..

AI-Assisted Positioning Statements

Positioning comes before copy: who it's for, what category you're in, what alternative you replace, and the one difference that matters.

Full-Funnel Message Mapping

Different funnel stages need different messages: problem-aware content at top, comparison and proof in the middle, urgency and risk-reversal at the bottom.

Project: Research → Position → Launch Assets

Deliverable: a complete mini campaign kit for a real or invented product. Steps: 1.

Generating High-Variance Ad Sets — ChatGPT

Ad platforms reward variety for testing.

Generating High-Variance Ad Sets — Grok

Ad platforms reward variety for testing.

Reading Ad Performance Data with AI

Paste raw campaign metrics and ask AI to find the story in the numbers — which angle, audience, or creative is actually winning, and what to do next..

Creative Testing Systems (Not One-Off Tests)

Scaling accounts run a creative system: a backlog of angles ranked by hypothesis strength, batches of 3-5 new creatives weekly, and a kill/scale rule applied without emotion (e.g., kill under 0.8× account-average CTR after 2k impressions; scale winners into new formats).

Landing Page ↔ Ad Message Match

Half of "ad fatigue" is actually message mismatch: the ad promises one thing, the landing page opens with another, and CVR dies.

Project: Design, Launch (or Simulate) and Read a Test

Deliverable: a complete documented ad test — real if you have an account, fully simulated if not. Steps: 1.

Killing the "AI Voice"

Generic AI writing tends to over-use certain patterns (excessive "moreover," perfectly balanced sentences, hedge-everything tone).

Structuring Image Prompts

Good image prompts (for DALL·E, Stable Diffusion / Hugging Face models, Midjourney-style tools) generally follow: Subject -> Setting -> Style/medium -> Lighting/mood -> Composition/technical details..

One Article, Five Formats

Turn a single long-form piece into a newsletter blurb, Twitter/X thread, LinkedIn post, Instagram caption, and short-form video script — with one well-structured prompt..

Building a Reusable Brand Voice Prompt

Instead of re-describing your tone every time, create a single "voice block" you paste at the top of every content prompt.

Batch-Creating a Week of Content

Once you have a voice block and a topic, you can generate a whole content calendar in one structured request — then refine individual pieces..

The Two-Pass Edit: Structure Then Line — Claude

Professional editing is two separate passes: a structural pass (does the argument build? is anything missing or redundant?) and a line pass (rhythm, word choice, cuts).

The Two-Pass Edit: Structure Then Line — Claude (2)

Professional editing is two separate passes: a structural pass (does the argument build? is anything missing or redundant?) and a line pass (rhythm, word choice, cuts).

Original Insight: The Thing AI Can't Fake

AI averages the internet; audiences reward what the average doesn't contain — your data, your contrarian take, your first-hand story.

Project: One Pillar Piece + Four Repurposed Assets

Deliverable: a published (or publish-ready) pillar piece with its full repurposing kit, all in your voice. Steps: 1.

Hook-First Script Structure

The first 5-10 seconds decide retention.

Title & Thumbnail Text Pairing — Claude

Titles and thumbnail text should never repeat the same words — they should work together to create curiosity.

Title & Thumbnail Text Pairing — Perplexity

Titles and thumbnail text should never repeat the same words — they should work together to create curiosity.

Reading Your Analytics with AI

Paste your YouTube Studio export and ask AI to find patterns across your best and worst performing videos — topic, length, hook style, and thumbnail pattern..

Scripting for the Retention Graph

Retention drops happen at predictable points: the 30-second mark (promise not yet paid), mid-video (a segment overstays), and any moment of throat-clearing ("before we start…").

Series & Format Design

Channels grow on repeatable formats, not one-off videos: a recognizable structure (same open, same segments, same visual grammar) lowers production cost and trains the audience to return.

Project: One Video, Fully Engineered

Deliverable: a complete production package for one real video on your (or an invented) channel. Steps: 1.

Competitor Content Gap Analysis

Paste a competitor's page structure (headings, topics covered) alongside yours and ask AI to find gaps — subtopics they cover that you don't, questions they answer, and angles they missed that you can own..

Writing Docs That Retrieve Well

Retrieval quality starts with document quality.