Simon Willison Portfolio
Creator of the Datasette open-source data tool and the `llm` command-line tool for working with language models; his blog publishes near-daily, deeply technical posts tracking model releases, agentic coding patterns, and AI security issues, tagged and archived back over two decades.
What makes it work
A breakdown of the choices that make this portfolio stand out.
A shipped, maintained CLI tool as the primary proof of skill
The `llm` command-line tool is a real, installable piece of software for running and comparing language models — a working tool is a stronger engineering credential than a writeup describing one.
Fast, specific analysis of new model releases
Same-day posts comparing releases like new Claude and GPT versions demonstrate hands-on testing, not secondhand summary — the kind of applied judgment that signals real usage, not just reading announcements.
An extensive tagging system across years of posts
Consistent tagging lets the archive function as a searchable knowledge base rather than a disposable feed, which is what makes years-old posts still get found and cited.
What AI Engineers can take from this
Specific, actionable tips to apply to your own portfolio — no generic advice.
Ship an actual tool, even a small CLI utility, rather than only writing about how you'd solve a problem.
When a new model or tool releases, publish your own hands-on test results quickly — firsthand testing is worth more than secondhand summary.
Tag and organize your writing consistently from the start so old posts stay discoverable as a reference, not just a stream.
More AI Engineer portfolios
Ready to build your portfolio?
Follow the AI Engineer roadmap — skills, projects, and timeline to get hired.