AI for Coding

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.

Debug a Real Bug With AI

Practise the debugging loop that works — evidence first, hypothesis second, fix last — on a bug you actually have. The habit this builds is refusing to accept a fix you cannot explain.

Review Code the Model Wrote

Generate code, then review it properly. The habit this builds — never shipping generated code you have not read — is the single highest-value habit in AI-assisted development.

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.

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.

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.

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.

Function calling

Function calling lets a model request that your code run a specific function with specific arguments. You expose tool definitions; the model returns a structured call, your code executes it, and the result goes back into the conversation.

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.

Reranking

Reranking takes an initial set of retrieved candidates and reorders them with a more accurate but slower model. It is one of the cheapest ways to materially improve RAG quality.

ReAct pattern

ReAct (Reason + Act) is the core agent loop: the model reasons about what to do, takes an action via a tool, observes the result, then reasons again. It repeats until it can answer.

Tool use

Tool use is a model invoking external capabilities — search, code execution, database queries, APIs — to do things it cannot do from parameters alone, such as fetching current data or performing exact arithmetic.

Model drift

Model drift is when a hosted model's behaviour changes over time as the provider updates it, causing prompts that worked reliably to degrade without any change on your side.

SQL Query Explainer

Understanding or debugging unfamiliar queries. Ideal when you inherit a legacy codebase, review a teammate's pull request, or hit a slow query you did not write. Asking for a plain-English walkthrough before the optimisation notes means you understand the intent first, so you can tell a genuine bug from a deliberate design decision.

Code Review Pass

Pre-review pass before submitting a pull request

Meta-Prompting: Prompts That Write Prompts

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

What RAG Actually Does

RAG (Retrieval-Augmented Generation) retrieves the most relevant passages from your documents and injects them into the prompt before the model answers.

Chunking: Why Split Size Matters

Documents are split into chunks before embedding.

Custom GPTs & Claude Projects

Both ChatGPT (Custom GPTs) and Claude (Projects) let you upload documents and set standing instructions — a no-code RAG setup.

Writing Docs That Retrieve Well

Retrieval quality starts with document quality.