Claude Code wrote a good part of Jose Quevedo’s portfolio code, but Quevedo says the consequential decisions remained his: what to build, what to measure, and which suggested changes to reject. His September 21, 2026 account is a single-project case study—not proof that AI coding produces the same results for other developers.
What Quevedo built—and what the account can show
Quevedo reports rebuilding his portfolio with TypeScript, React 19, Next.js 16 using the App Router, Tailwind CSS 4, and Framer Motion, then deploying it on Vercel with his own domain. Those are the tools and versions he names in his September 21, 2026 article; they are not an independent audit of the live site. Read Quevedo’s account on DEV Community.
![Claude AI for Beginners Bible: [5 in 1] The Ultimate Guide to Automate Your Work, Save Hours Every Week, and Use AI for Real-World Results](https://m.media-amazon.com/images/I/415+fSJacsL._SL160_.jpg)
As an Amazon Associate I earn from qualifying purchases.
His central distinction is between producing code and owning the decisions around it. As he puts it, “The AI wrote a good part of the code. Every decision that mattered was mine.” The article does not compare Claude Code with another tool or establish that AI-written code is inherently better or worse. It shows how one developer describes directing, reviewing, and evaluating a particular rebuild.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Which decisions did he keep in human hands?
Keep the design focused
Quevedo chose a clean design without extra widgets, reasoning that simplicity would read as more professional. This was a design judgment for his portfolio, not a universal rule that every portfolio should look alike.
#1 Best Overall
Audit before adding features
He asked for a review of SEO, accessibility, and performance before building more features, then worked through issues by priority. That sequence makes the review part of the development process rather than a final polish step.
Make accessibility concrete
Among the changes he describes were a pause control for auto-rotating carousels, setting hidden slides to inert, and sizing touch targets for phones. These are reported decisions; the article does not independently verify the implementation.
Handle SEO page by page
Quevedo says he added per-page canonical and social metadata, a sitemap, and one h1 in the hero, and verified the site in Google Search Console. These are the SEO steps he reports, not an independent confirmation of search performance.
Recommended Free Tools
Keep or revert changes based on evidence
He tried a CSS-only change intended to make the hero faster. According to his account, it produced no meaningful Lighthouse gain, so he reverted it. The useful principle is not that CSS changes cannot help; it is that a proposed optimization should earn its place through measurement.
What scores did he report?
Quevedo reports the following Lighthouse scores for the production site. The article does not give test conditions or an independently reproducible run, so these figures describe his reported results only.
| Reported test | Performance | Accessibility | Best practices | SEO |
|---|---|---|---|---|
| Desktop | 99 | 100 | 100 | 100 |
| Mobile | 89 | 100 | 100 | 100 |
These numbers are not evidence that Claude Code caused the results, nor a guarantee of what another project will score. The source gives no test conditions or independent reproduction.
Rank #4
How to apply the case study to your own project
Quevedo’s advice for someone starting out is to set goals and constraints before prompting, use the assistant for audits as well as code, read changes before shipping, and measure before and after. In practical terms, that means deciding what the portfolio must communicate and which constraints matter, then treating generated work as a proposal to inspect rather than an automatic acceptance.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →- Clarity: Does the design make the work and its purpose easy to find?
- Accessibility: Have interactions such as carousels, hidden content, and touch controls been considered?
- SEO basics: Are page metadata and site-discovery essentials handled for the actual pages?
- Measured performance: Did the change improve a measured result under comparable conditions?
- Human review: Can you explain and stand behind each change you ship?
Quevedo’s short formulation is: “The AI can suggest a change. Only measuring tells you if it worked.” His account ends with a question worth asking when reviewing any portfolio: “What is the first thing you check when you open someone else’s portfolio?”
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
