Christian Schmitt

Advanced Circula Website Relaunch & Complete Redesign 👀 The Challenge ✅ Massive Migration & Redesign: Migrate over 250 pages from Sanity to Webflow while completely overhauling the website design without affecting SEO. ✅ CMS & Pagebuilding: Build a robust flexible CMS System, also let the Circula Team generate Landingpages with prebuild Components in Minutes instead of Weeks ✅ Multi-language Implementation: Build a robust multi-language system that delivers tailored content for each language. ✅ Custom Interactions: Develop a highly customized design featuring interactive GSAP animations and advanced JavaScript functionalities. ✅ Scalability & Accessibility: Create a scalable, component-based system that supports future growth and meets high accessibility standards. ✅ Team Limitations: Execute the entire project—migration and redesign—with only three freelancers. Circula is among the EU’s Top 80 fastest-growing companies in the FT 1000 Freelancer: • Luca Gonzalez Sonst • Simon Ziri • Christian S. Special Thanks to Circula & External Partners: • Roman Leicht & Nikolai Skatchkov (CEO Circula) • Sergey Bekrin (Engineering Manager) • Etienne Echinard (VP Marketing) • Jacqueline 'Jacqui' T. (Website Lead) • Juliane Mainoo (Product Marketing) • Benjamin Hartung (Design Lead) • Anna Lischke (SEO) • Kieran Ward (Growth & Marketing) • Moritz Zimmermann (Performance Marketing) and all other people who were involved in this :)

Bist du dabei? Die Webflow Conf 2026, gefeiert in München. Am 02. September holen wir die Webflow Conf nach München. Tagsüber Vorträge zur Zukunft der Webentwicklung. Abends die Keynote live aus Boston. 40 Plätze für Leute aus der DACH-Community, die Webflow im Alltag nutzen. Jetzt dabei sein dripl.ink/hx9Xs

@cursor_ai can we have a native GA4 and GSC Connection please? 😇

You can also now create automations without any attached repos, like a daily Slack digest agent that prioritizes unread threads and DMs for your response. Find more templates in our marketplace: cursor.com/marketplace

You can now create and manage automations in the same workspace as your agents. Automations are now available in the Agents Window. For the next 7 days, all agent runs for newly created automations are 50% off.

“Webflow AEO has been a huge force multiplier. The recommendations are specific to my actual site and pages, which means I can quickly spot gaps like missing schema markup or broken links that materially impact our AI visibility, then execute them instantly.” - Chris Singleton, Senior Manager - Website and Organic Growth, Smartly Today, Webflow AEO is available to all Enterprise customers, bringing measurement, on-brand recommendations, and agentic execution together in a closed loop. Own your visibility in AI search, at scale. No AEO expertise required. No handoffs or stitching together multiple tools. All natively in the platform where work gets done, and where your brand context lives. Learn more about Webflow AEO here: wfl.io/4tLXQ7Y

@leerob it is spawning motion html elements in random places. Like in this: x.com/darryl__yeo/st…

Where could we improve Composer 2.5? We're working on the next model and would love your feedback. Lots of work to do (our CursorBench evals below) in the coming weeks!

@ericzakariasson @thesebastiansas @leerob Omg I had the same 🤔

@thesebastiansas @leerob mind sharing a request id? will forward to the team

Composer 2.5 is great, but the reason it keeps trying to use `motion` tag is beyond me 🤔 It first makes the change using `motion`, then it corrects itself and changes it back to `div` @leerob @ericzakariasson

Composer 2.5 is now the most-chosen model in Cursor. We're giving everyone 10x usage for the rest of the day. Enjoy!

🚢🚢🚢 Use @webflow component props in custom code webflow.com/updates/use-co…

@Lukebonnici1 Yes it is running for me all day 👌🏼

Anyone still using Cursor out there? I do, and Composer 2.5 slaps.

@kavirkaycee If you think the prices are too high you have to optimize your bandwidths

I’m glad I migrated a business website out of Webflow and into Next js These price increases are crazy

@aseem_bathla @marvinblach Check the jobs they are searching for :)

@schmittdev @marvinblach Why do you think so?

New Webflow Pricing, what are we thinking?

🚢🚢🚢Set a default preview role for each @webflow site webflow.com/updates/defaul…

Announcing the Artificial Analysis Coding Agent Index! Our new coding agent benchmarks measure how combinations of agent harnesses and models perform on 3 leading benchmarks, token usage, cost and more When developers use AI to code they’re choosing a model, but also pairing it with a specific harness. It makes sense to benchmark that combination to understand and compare performance. The Artificial Analysis Coding Agent Index includes 3 leading benchmarks that represent a broad spectrum of coding agent use: ➤ SWE-Bench-Pro-Hard-AA, 150 realistic coding tasks that frontier models struggle with, sampled from Scale AI’s SWE-Bench Pro ➤ Terminal-Bench v2, 84 agentic terminal tasks from the Laude Institute and that range from system administration and cryptography to machine learning. 5 tasks were filtered due to environment incompatibility ➤ SWE-Atlas-QnA, 124 technical questions developed by Scale AI about how code behaves, root causes of issues, and more, requiring agents to explore codebases and give text answers Analysis of results: ➤ Opus 4.7 and GPT-5.5 lead the Index: Opus 4.7 in Cursor CLI scores 61, followed closely by GPT-5.5 in Codex and Opus 4.7 in Claude Code at 60. GPT-5.5 in Cursor CLI follows at 58. ➤ Open weights models are competitive, but still trail the leaders: GLM-5.1 in Claude Code is the top open-weight result at 53, followed by Kimi K2.6 and DeepSeek V4 Pro in Claude Code at 50. These are strong results, but still meaningfully behind the top proprietary models. ➤ Gemini 3.1 Pro in Gemini CLI underperforms: Gemini 3.1 Pro in Gemini CLI scores 43, well below where Gemini 3.1 Pro sits on our Intelligence Index, highlighting that Gemini’s performance in Gemini CLI remains a relative weak spot for Google’s offering. ➤ Cost per task (API token pricing) varies >30x: Composer 2 in Cursor CLI is cheapest at $0.07/task, followed by DeepSeek V4 Pro in Claude Code at $0.35/task and Kimi K2.6 in Claude Code at $0.76/task. At the high end, GPT-5.5 in Codex costs $2.21/task, while GLM-5.1 in Claude Code costs $2.26/task. For both models this was contributed to by high token usage, and in GPT-5.5’s case by a relatively higher per token cost. ➤ Token usage varies >3x: GLM-5.1 in Claude Code uses the most tokens at 4.8M/task, followed by Kimi K2.6 at 3.7M/task and DeepSeek V4 Pro at 3.5M/task. GPT-5.5 in Codex uses 2.8M tokens/task, substantially more than Opus 4.7 in Claude Code at 1.7M/task. In GLM-5.1’s case, higher token usage, cost and execution time were partly driven by the model entering loops on some tasks. ➤ Cache hit rates remain high but vary materially: Cache hit rates range from 80% to 96% across combinations. Provider routing, harness prompt structure and cache behavior can materially change the economics of running the same model given cached inputs are typically <50% the API price of regular input tokens. ➤ Time per task varies >7x: Opus 4.7 in Claude Code is fastest at ~6 minutes/task, while Kimi K2.6 in Claude Code is slowest at ~40 minutes/task. This is contributed to by differences in average turns per task, token usage and API serving speed. Opus 4.7 had materially lower amount of turns to complete a task than all other models while Kimi K2.6 had the most. ➤ Cursor made real progress with Composer 2: Composer 2 in Cursor CLI scores 48, near the leading open-weight model results, while being the cheapest combination measured at $0.07/task. Cursor has stated Composer 2 is built from Kimi K2.5, showcasing they have made substantial post-training gains. This is just the start. We are planning to add additional agents (both harnesses and models). Let us know what you would like to see added next.

@levelsio @Cloudflare .de is also missing

Request for @Cloudflare to add these remaining TLDs so I can transfer these domains from Namecheap into there and have one less vendor: .bio, .nl, .vc, .cm

What’s up with $NET ?

@Tycreated @clay A huge win for clay 🙌🏼

New news 🎉 I joined @clay I’ll be on the brand team, working across the website experience. More soon!

@ChromiumDev German is destroying your layout, hyphens: auto should do the thing :)

You can simply prompt your agent: "Go to chrome.dev/devtools-store…, emulate Paris as a location, and verify there are stores listed." The agent navigates to the page, clicks "Use my location", inspects the list, and confirms the nearest stores, all without manual intervention.

Test websites exactly how your users experience them → goo.gle/4cFRfW7 Chrome DevTools for agents introduces viewport and user agent emulation, allowing your AI agents to mimic real device conditions seamlessly ⬇️🧵

@marvinblach You wanna build the European version? 😅😅

Github again with issues its starting to become a problem

@SimonHoiberg If you are using still Webflow the Webflow MCP can build this for you 👌🏼

@schmittdev Dope, I'll try this

We got to the point now where image generation models like Nano Banana can output really high quality website graphics like this (and very reliably). I'll soon have my OpenClaw agents automatically create, deploy, and test different landing page versions + create Facebook ads against them. Then use the results to iterate and find new proven angles, discover new customer profiles, etc.