How do you drive Webflow from Claude Code?

That changes the shape of the work. Before, an agent could tell you what to change. Now it can make the change in the project, and you review it in the Designer like any other edit.

What it is good at

Repetitive structural work. Porting a component pattern across pages, renaming and consolidating classes, applying a spacing scale that was decided once and then drifted. This is the work that is too boring to do carefully and too consequential to do carelessly.

CMS modelling at scale. Creating collections, fields and references from a schema you wrote down. By hand that is forty minutes of clicking.

Auditing. Reading every page's structure and reporting what disagrees with the standard. This is where I get the most value, because it turns a vague sense that the site has drifted into a list.

What it cannot touch

Webflow publishes a current limitations list, and it's worth reading before you plan around the tool. As of August 2026 the ones that bite:

• Interactions are out. IX3 stays a manual job. Motion stays hand-built, which is fine by me, because motion is a judgement call per project.
• Fonts are partial. Uploaded font files only. Remotely hosted Google and Adobe fonts are excluded.

Plan for those up front.

The thing that makes it work

Everything the agent does comes from a standard I wrote down. Every decision it applies was made in advance.

Naming, structure, spacing, motion timings, CMS patterns, handover rules: all of it lives in versioned markdown that every project starts from. That file is the product. The agent is a fast, tireless, literal-minded implementer of it, and it's only as good as the thing it's implementing.

Which is why "AI built the site" is the wrong description of this. Nobody says a compiler wrote the program. The interesting question is whether the standard is any good, and that's a question about the person who wrote it.

Where I keep the judgement

Three things never go to the agent, on any project:

• Information architecture. What gets a URL, what a collection represents, how things relate. Get this wrong and everything downstream is fast work in the wrong direction.
• Anything a client will be judged on by their own audience. Copy, hierarchy, the argument the page makes.
• The decision to change working behaviour. An agent mid-task will happily "fix" something that was deliberate. The rule on my projects is that at a fork it verifies, defers, or asks. The fork gets surfaced before anything in the project changes.

That last one is the failure mode I have hit, and I have the commit history to prove it.

Whether it's worth setting up

If you build one Webflow site a year, no. The setup cost is real and the payoff is in repetition across projects.

If you build continuously, the compounding is in the standard. Every project that starts from the same written rules is faster than the last, and the tool is just what makes following them cheap. I'd still be writing the standard if the tooling vanished tomorrow. I'd just be applying it by hand.