AI Fluency & Building · AI Knowledge Systems
Start here. Short, guided tasks that build the basics and give you your first piece of proof.
Task 1 of 3
Build a tagged library of 30 pieces.
What to do
Collect 30 pieces of content from one brand (blog posts, FAQs, product pages, social posts). Organise them in a spreadsheet with title, date, type, topic and tags, and explain your tagging scheme.
You’ll make
Done looks like
A 30-row sheet with title, date, type and tags, plus your tagging scheme.
Task 2 of 3
A one-page visual and a tiny demo.
What to do
Explain embeddings to a non-technical friend with a one-page visual and a tiny demo showing similar sentences (for example, similar product descriptions) sitting close together.
You’ll make
Done looks like
A visual explainer and a demo showing similar sentences close together.
Task 3 of 3
Compare two kinds of search on 50 documents.
What to do
Search 50 product descriptions or FAQs with keyword search and with embedding search, and show 3 queries where the results differ and why.
You’ll make
Done looks like
A demo with 3 queries where keyword and embedding results differ, explained.
Learn before you build
Free course
A free course on transformers, embeddings and building with LLMs.
Free tool
A free open-source vector database that runs on your laptop.
Article guide
Clear explainers on embeddings, chunking and vector search.
Article guide
A practical technique that sharply reduces failed retrievals.
Article guide
A framework for connecting LLMs to your own data.
Article guide
Build a question-answering app over your own documents.