What Simon Willison's Friction-Free Learning Method Taught Our Open-Source Agent
The creator of Datasette and Django built a publishing practice that makes perfectionism irrelevant — and it turns out it applies directly to how agents should handle open-source data tooling
By The Data Workers Team
Simon Willison is the creator of Datasette, co-creator of Django, and one of the most consistent public learners in open source software. Since 2021 he has maintained a site at til.simonwillison.net — 577 entries and counting — where he publishes every small thing he figures out, immediately after figuring it out. He coined the term 'prompt injection' in 2022 when it did not yet have a name. In October 2025 he proposed 'vibe engineering' to describe what responsible AI-assisted development actually looks like.
The Publishing Tax That Produces Nothing
The core problem Willison identified is one every technical writer recognizes: 'If I'm writing a blog entry, I feel like it needs to say something new. This pressure for originality leads to vast numbers of incomplete, draft posts and a sporadic publishing schedule that trends towards not publishing anything at all.' The fix is radical simplicity: 'The bar for a TIL is literally did I just learn something? — they effectively act as a public notebook.'
His stated goal: 'My hope is that by publishing a constant stream of TILs I can reinforce the idea that even if you've been working in this industry for twenty years there will always be new things to learn, and learning any new trick — even the most basic thing — should be celebrated.'
Three Ideas That Do the Real Work
- •Friction-free capture: publish the moment you learn it, before the insight decays into background knowledge. The TIL format is a public notebook, not a finished essay.
- •SQLite-first pragmatism: Willison's breakthrough with Datasette was the realization that 'read-only data packaged as a SQLite database could be deployed to inexpensive serverless hosting' — scaling from zero cost to unlimited traffic without a running server. A file beats a server until a server is actually needed.
- •Accountable amplification: 'AI tools amplify existing expertise... The more skills and experience you have as a software engineer the faster and better the results.' Accountability cannot be delegated. Vibe engineering means seasoned professionals accelerate their work with LLMs while staying accountable for the software they produce.
How a Method Becomes a Skill
The friction-free-public-learning skill encodes seven steps: identify the learning unit; publish it immediately as a minimal faithful record; default to SQLite until a concrete constraint makes escalation necessary; use AI tools to amplify while maintaining full accountability for every line; design for plugins only after two concrete use cases exist; write design thinking in GitHub issues rather than private notes; and treat unreviewable AI output as noise rather than knowledge.
One of More Than 400
The friction-free-public-learning skill is one of more than 400 method-named skills across 19 agents in the Data Workers swarm. The goal is the same as Willison's TIL practice: capture what actually works, in a form that compounds.
A note on this post: This is independent commentary and homage. It distills publicly available writing and talks by Simon Willison to illustrate a working method, and every quote is drawn from and verified against the primary sources linked above. The skill it describes is named for the method, not the person, and contains no marketing claims attributed to them. Data Workers is not affiliated with, sponsored by, or endorsed by Simon Willison. If you are Simon Willison and would like anything adjusted or removed, email hello@dataworkers.io and we will respond promptly.
Related Posts
What Ralph Kimball's Dimensional Modeling Taught Our Pipelines Agent
Ralph Kimball's four-step dimensional design process is one of the most durable ideas in data engineering — here is what it taught our pipelines agent.
What Jay Kreps's Log-Centric Architecture Taught Our Streaming Agent
Jay Kreps's core insight is deceptively simple: an append-only, totally-ordered log is not just a message bus — it is the single source of truth that eliminates N² integration pipelines and makes reprocessing routine. We studied his published writing and built a reusable streaming skill around the method.
What W. Edwards Deming's Plan-Do-Study-Act Taught Our Data Quality Agent
W. Edwards Deming spent a career arguing that quality comes from improving the process, not inspecting for defects. His Plan-Do-Study-Act cycle is the most rigorous improvement loop in the field. Here is how we encoded it into our data quality agent.