Beyond Vibe Coding
- 2025
- First edition, 2025
- paperback
- O'Reilly Media
- 9798341634756
AskNex reference artwork. The publisher's cover appears only under an approved rights record.
by Addy Osmani
A practitioner's guide to AI-assisted development that separates the fast first draft from the engineering that makes software correct, maintainable and safe.
The clearest account of why AI-generated code that works is not the same as software you can ship.
AskNex explains and applies the ideas in this book in its own words. Nothing on this page is quoted from the book, and the page does not stand in for it: the argument, the evidence and the voice are the author's, and reading the original remains the deeper path.
The core idea
AI gets you most of the way quickly; the last stretch of edge cases, integration and correctness is still engineering. Treat generated code as untrusted input, keep design decisions human, and never merge what you cannot explain.
The ideas
2 mental models, in the order they build on each other.
- 01
The 70% problem
The first draft arrives fast; the remaining work is where the difficulty always was.
- 02
Untrusted contribution
Read, test and review generated code as you would a stranger's pull request.
What the book argues
AskNex's own paraphrases of the positions this book takes, as they are held in the knowledge graph. Not quotations, and not the whole book.
The model gets you most of the way quickly; the last stretch of edge cases, integration and correctness is still engineering.
Never merge code you cannot explain; generated code you do not understand is debt you will pay for later.
Treat generated code as an untrusted contribution: read it, test it and review it as you would a stranger's pull request.
Use the model for boilerplate, exploration and explanation; keep architecture and trade-offs human.
Software quality and review
Correctness, maintainability and safety of software, which a fast first draft does not supply.
AI-assisted software engineering
Specifying, steering and verifying code produced by a model, rather than typing it.
Human judgement with AI
Keeping the expertise that lets you evaluate what a model produces, instead of outsourcing the judgement.
Working with AI
Using a fast, fallible model as a collaborator whose strengths are uneven and must be mapped.
Career capital
Rare and valuable skills bought with sustained effort, then spent on autonomy.
Where it argues with other sources
Most summaries flatten this. AskNex keeps it, because the disagreement usually decides what applies to you.
Osmani qualified by Kim & Yegge
The model gets you most of the way quickly; the last stretch of edge cases, integration and correctness is still engineering.
The scarce engineering skill becomes specifying, steering and verifying; engineers who delegate well multiply their throughput.
The leverage is real, and so is the last stretch: delegate the draft, keep the engineering judgement, and budget time for the part the model cannot finish.
What actually matters
- Experienced engineers gain the most because they can spot bad output; beginners must build fundamentals, not skip them.
- Use the model for boilerplate, exploration and explanation; keep architecture and trade-offs human.
Where it applies
Practical moves the book supports. Each one is a place to start, not a rule.
- Explain before merge
Write one paragraph on what a generated change does and why. If you cannot, do not merge it.
- Test the draft
Add the tests you would demand of a contributor before accepting the code.
Questions worth asking
Could I debug this generated code at 2 a.m.?
Which fundamentals am I letting the tool do for me?
Problems this book speaks to
Recurring situations where this book is one of the sources AskNex draws on. Each opens a public orientation page.
What are you trying to figure out right now?
AskNex will answer your situation using the ideas in Beyond Vibe Coding alongside every other source that applies — including the ones that argue against it.