How do I build my first AI portfolio project?

02 · See it in action

Follow the steps

1. Choose one problem and a measurable success criterion.
2. Document data sources, permissions and your baseline.
3. Include setup instructions, examples and evaluation results.
4. Write a limitations section and identify your own contribution.

Worked example

Project: search a public tutorial catalogue
Baseline: keyword search
Experiment: semantic retrieval
Evaluation: 20 labelled queries, hit@3, error examples
Limitations: small test set; no private documents

Read the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.

Sign in to save your reading progress.