Website design and development, built for AI search
We design and build websites on a modern content management system, written and structured so search engines and AI assistants can read, trust and cite them. Every site is built to be run after launch, by your team or by agentic web management.
AI assistants now answer many of the questions buyers used to type into a search box, and they quote the sites they can read and trust. A site earns that when every fact about you is stated the same way everywhere, each page answers its question first, and the pages arrive as complete HTML that a crawler can read without running scripts.
We build for that from the first wireframe. Pages open with a direct answer, headings follow the questions your buyers ask, and structured data (JSON-LD) describes your company, services and people in a form search engines read.
For a site that AI agents will help run, we recommend a headless content management system, usually Sanity, with a Next.js front end. Content lives as structured records rather than pages, so one record feeds the visible page, the structured data, the sitemap and llms.txt, a plain-text summary of the site written for AI tools. Because they all come from the same record, they cannot drift apart.
We still build on Webflow or WordPress when that suits a team that edits pages by hand and does not plan to share the upkeep with agents.
#01
What your buyers search for, and what AI assistants already say about you.
#02
Design the pages and the content model together, so every fact has one home and one place to change it.
#03
Server-rendered pages, structured data, a sitemap and llms.txt, all generated from the content.
#04
Performance, accessibility and security, plus redirects from every old URL so nothing you have earned is lost.
#05
Hand over a site your team can run, with drafts a person approves before anything goes live.
Your team can run the site directly, or it can run on agentic web management: AI agents draft content and check pages on a schedule, and a person on your team approves every change. Nothing publishes on its own.
Selected work
We moved our own site from Webflow to Sanity and Next.js in September 2026 and built it this way: server-rendered pages, structured data and llms.txt generated from the content, IndexNow to tell search engines when pages change, and a person approving every edit. Website work on the site includes Stanley Security and the Oliver Wyman web design system.
The engagement
Marketing and product leaders whose website now has to be read and quoted by AI assistants, not only ranked by search engines: teams launching a new site, moving off a platform they have outgrown, or rebuilding a site nobody can keep current.
Solutions
After launch, AI agents keep your site and content current, and a person on your team approves everything before it goes live.
Your brand now has to resonate with people and register with machines. We build the operational skills and AI workflows that carry your brand consistently through every touchpoint, from your product and site to social and AI answer engines.
Pixels are commoditized. Brand-fluent, accessible systems aren't. Your team can ship the next screen. Keeping your fiftieth screen on-brand, on-pattern and on-business-logic is a different problem: design system governance, the discipline most internal teams haven't built yet. We've been designing since 2014, and we pair that experience with AI for what AI does well: parallel exploration, deep research and system-wide consistency. You get AI speed plus the discipline AI can't generate on its own.
Agents now build from your design system, and they bring none of your team's context. We engineer and audit systems with machine-readable metadata and explicit anti-patterns, using Figma MCP, Cursor, and Claude, so agents stay on-brand and on-system while your team ships faster.
The fastest teams decide with evidence, not opinions. We instrument products with tools like Pendo and run AI-assisted experimentation, turning real user behavior into a continuous loop of what to build, test, and sharpen next.
Further reading
Answer-engine optimizationBy Lindsey J
Answer engine optimization explained: as AI summaries cut click-through, here is how any product team stays legible, credible, and cited, with a five-question self-assessment.
6 min read
Answer-engine optimizationBy Lindsey J
5 min read
Got questions?
One clear description of who you are, stated the same way everywhere; structured data; answer-first copy; pages a crawler can read without running scripts; and a plain-text summary of the site for AI tools.
Yes. A redesign starts from what your buyers search for and what AI assistants already say about you, then rebuilds the site so both are accurate.
The site is built to run on agentic web management: agents keep it current and your team approves every change. Or your team runs it directly.
We design the products, websites and design systems your customers use and their AI agents act on.
