Prompt Engineering Lesson 6: Long Documents and Summaries
Summarise and question long documents: summary types, asking for quotes and page references, chunking very long files, comparing versions and meeting-minutes prompts.
Read article →AI & ML
Artificial intelligence explained by building it: machine learning, neural networks, LLMs, RAG and agents — plus how to build your own language model.
Prompt Engineering Lesson 5: Getting Structured Output — Tables and JSON
Prompt Engineering Lesson 5: Getting Structured Output — Tables and JSON
Ask for answers you can use directly: markdown tables to paste into Excel, CSV, JSON with a fixed schema, and extracting fields from messy…
Read article →Prompt Engineering Lesson 4: Step-by-Step Reasoning and Checking
Prompt Engineering Lesson 4: Step-by-Step Reasoning and Checking
Get better answers on calculations and decisions: ask for steps, break big tasks into stages, have the model check its own work, and verify…
Read article →Prompt Engineering Lesson 3: Examples and Templates (Few-Shot)
Prompt Engineering Lesson 3: Examples and Templates (Few-Shot)
Show, don’t tell: give the model one to five examples to copy tone, structure or classification rules, and build reusable prompt templates with placeholders.
Read article →Prompt Engineering Lesson 2: Clear Instructions — Role, Task, Context, Format
Prompt Engineering Lesson 2: Clear Instructions — Role, Task, Context, Format
Write prompts that work first time with the role-task-context-format pattern, constraints, audience and length, plus before/after examples for office tasks.
Read article →Prompt Engineering Lesson 1: How Chat AI Reads Your Prompt
Prompt Engineering Lesson 1: How Chat AI Reads Your Prompt
What happens when you send a prompt: tokens, context windows, next-word prediction, why wording matters, why answers vary, and what the model does and…
Read article →Why AI Chatbots Make Things Up (and 6 Ways to Catch It)
Why AI Chatbots Make Things Up (and 6 Ways to Catch It)
LLM "hallucinations" explained simply: why a next-token predictor can sound confident and still be wrong, and six practical habits to catch fabricated facts, formulas…
Read article →Run an LLM on Your Own Laptop with Ollama (Private, Free, Offline)
Run an LLM on Your Own Laptop with Ollama (Private, Free, Offline)
Install Ollama, run open models like Llama and Qwen locally, call them from Python and Excel-friendly scripts, and create a custom model with a…
Read article →LoRA Fine-Tuning Explained: Teach an LLM New Tricks on One GPU
LoRA Fine-Tuning Explained: Teach an LLM New Tricks on One GPU
How LoRA fine-tuning works, why it trains less than 1% of a model’s parameters, when fine-tuning beats prompting or RAG, and a minimal Hugging…
Read article →Build a RAG Chatbot That Answers From Your Own PDFs and Excel Files (Complete Guide)
Build a RAG Chatbot That Answers From Your Own PDFs and Excel Files (Complete Guide)
Step-by-step guide to retrieval-augmented generation in Python: load PDFs and Excel sheets, chunk them, create embeddings, search by meaning, and answer with a local…
Read article →AI Agents and Tool Calling Explained (With a 20-Line Example)
AI Agents and Tool Calling Explained (With a 20-Line Example)
What people mean by AI agents: a model in a loop that can call tools such as search, a calculator or your database. How…
Read article →Writing Prompts That Get Working Excel Formulas (and Why Vague Prompts Fail)
Writing Prompts That Get Working Excel Formulas (and Why Vague Prompts Fail)
How to ask an AI assistant for Excel formulas, VBA and SQL so the answer actually works: describe the layout, give sample rows, state…
Read article →