Research & Fundamentals

AI Marketing

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

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.

Build a Personal Study Assistant

Turn a stack of lecture notes into a study partner that quizzes you, explains what you got wrong, and tracks which topics you keep failing. You will finish with a reusable system prompt you can point at any subject.

Build a Research Brief Generator

Create a repeatable workflow that turns a vague question into a structured research brief with sources, open questions and a confidence rating. The output is something you can hand to a colleague, not a wall of text.

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.

The Fabrication Hunt

Deliberately induce a confident, wrong answer, then find the prompt wording that prevents it. The most useful twenty minutes you can spend on calibrating how much to trust a model.

The Cover Letter That Is Not Generic

Write a cover letter that could only have been written by you, for this job. Tests whether you can force specificity out of a model that defaults hard to platitudes.

Summarise Without Losing the Point

Compress a long document to a tenth of its length while keeping what matters, then verify nothing important was dropped. Tests whether you can direct compression rather than just requesting it.

How Many Tokens Is My Prompt? Counting and Why It Matters

Tokens determine what you pay and what fits in context. Here is how tokenization works, how to estimate counts quickly, and the practical thresholds worth knowing.

Context Windows Explained: Why Bigger Is Not Always Better

What a context window is, why it includes the response, why models under-use the middle of long inputs, and how to design prompts that work within real limits rather than theoretical ones.

What Is RAG? Grounding AI in Your Own Documents

Retrieval-Augmented Generation lets a general model answer questions about your specific data without retraining. Here is how the pipeline works and the details that determine whether it works well.

What Are AI Agents? The Loop, the Limits, and the Hype

An AI agent plans and acts through tools in a loop rather than producing a single response. Here is how the ReAct pattern works, why agents fail, and what actually works in production today.

What Are MCP Servers? The Standard for Connecting AI to Your Tools

Model Context Protocol is an open standard that lets any AI client connect to any tool through one interface. Here is what it replaces, how it works, and why it matters for developers.

n8n and AI: Build Your First Real Automation

A practical walkthrough of wiring an AI model into an n8n workflow — the node structure, the prompt that makes it reliable, and three automations worth building first.

How to Evaluate AI Output: Building Evals That Catch Real Problems

Most teams ship AI features with no way of knowing whether a change made things better or worse. This is a practical guide to building evaluations — what to measure, how to build a test set, and why "it looks good" is not a method.

Token

A token is the unit of text an AI model reads and writes — roughly four characters or three-quarters of a word in English. Models price by the token and cap context by the token, so token count determines both what you pay and what fits.

Tokenizer

A tokenizer is the component that splits text into tokens before a model processes it. Different model families use different tokenizers, which is why the same text can have different token counts on GPT versus Claude.

Context window

The context window is the maximum number of tokens a model can consider at once — your prompt, any attached documents, the conversation history, and the response it generates. Exceed it and the earliest content gets dropped.

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.

System prompt

A system prompt is a standing instruction that shapes a model's behaviour across an entire conversation, separate from individual user messages. It typically defines persona, rules, tone and output format.

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.

Top-p (nucleus sampling)

Top-p limits the model to choosing from the smallest set of tokens whose combined probability exceeds p. At top-p 0.9, the model samples only from options making up the top 90% of probability mass, ignoring the unlikely tail.

Large language model (LLM)

A large language model is a neural network trained on vast amounts of text to predict the next token in a sequence. That single objective, at sufficient scale, produces the ability to write, summarise, translate, reason and code.

Transformer

The transformer is the neural network architecture behind virtually all modern language models. Its key innovation is self-attention, which lets every token directly consider every other token in the input.

Parameters

Parameters are the learned numerical weights inside a model, adjusted during training. Parameter count — 7B, 70B, 405B — is a rough proxy for capacity, but not a reliable predictor of quality.

Open-weights model

An open-weights model has publicly downloadable parameters, letting anyone run it on their own hardware. Llama, Mistral, Qwen and DeepSeek are prominent examples.

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.

LoRA

LoRA (Low-Rank Adaptation) is a fine-tuning method that trains small adapter matrices instead of updating all model weights. It cuts the compute and storage cost of fine-tuning by orders of magnitude.

Quantization

Quantization reduces the numerical precision of model weights — from 16-bit to 8-bit or 4-bit — shrinking memory use and speeding inference at a modest cost in quality.

RAG (Retrieval-Augmented Generation)

RAG retrieves relevant passages from your own documents and inserts them into the prompt before the model answers. It grounds responses in your data, cuts hallucination, and needs no retraining.

AI agent

An AI agent is a system where a model plans and takes actions through tools in a loop, rather than producing a single response. It decides what to do next, does it, observes the result, and continues until the goal is met.

Context engineering

Context engineering is the practice of deciding what information enters a model's context window and in what order. As windows grew, choosing what to include became more consequential than wording the instruction.

Mixture of experts (MoE)

Mixture of experts is an architecture where only a subset of the model activates per token. A router selects a few specialised sub-networks, so a very large model runs at the cost of a much smaller one.

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.

Fact-Check This Claim

Verifying a statistic or claim before publishing. Run this on anything you did not source yourself, especially numbers pulled from a chat model — statistics are exactly the kind of detail models hallucinate confidently. Use a search-grounded tool so you get a live primary source and a date, and treat "no source found" as a reason to cut the claim rather than to keep looking.

The 5-Part Prompt Framework — Claude

Every strong prompt combines five parts: Role (who the AI should act as), Context (background info it needs), Task (the specific ask), Format (how you want the output structured), and Constraints (length, tone, things to avoid).

Giving Loops Memory

For loops that run over many steps (research agents, multi-turn assistants), summarize prior steps into a short running memory instead of replaying the full history every time — this keeps context small and cheap..

Project: Research → Position → Launch Assets

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

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..

Mining Keywords and Search Intent — ChatGPT

AI is excellent at expanding a seed topic into keyword clusters and classifying search intent (informational, commercial, transactional, navigational).

Mining Keywords and Search Intent — Perplexity

AI is excellent at expanding a seed topic into keyword clusters and classifying search intent (informational, commercial, transactional, navigational).

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..

Titles, Metas & Headings That Rank

Generate title tag and meta description variants that include the target keyword naturally, fit character limits, and give a reason to click.

Getting Cited by ChatGPT & Perplexity — Perplexity

AI answer engines favor content that is clearly structured, directly answers questions, cites data, and demonstrates first-hand expertise.

Getting Cited by ChatGPT & Perplexity — Claude

AI answer engines favor content that is clearly structured, directly answers questions, cites data, and demonstrates first-hand expertise.