Web Developer for LLM Search Optimisation·Searchable-by-AI websites·AI Integration · Process Simplification·Anthropic Claude · OpenAI·ChatGPT · Perplexity · Claude · Google AI Overviews·llms.txt · schema.org · /api/profile · /api/chat·klava.london/ai·Web Developer for LLM Search Optimisation·Searchable-by-AI websites·AI Integration · Process Simplification·Anthropic Claude · OpenAI·ChatGPT · Perplexity · Claude · Google AI Overviews·llms.txt · schema.org · /api/profile · /api/chat·klava.london/ai·
Web Developer · LLM Search Optimisation · AI Integration

Web developer for
LLM search optimisation.

I'm Klava — a London-based web developer specialising in LLM search optimisation and AI integration. I build websites that are searchable by AI (ChatGPT, Perplexity, Claude, Google AI Overviews, Gemini, Bing/Copilot) and I integrate AI into products to simplify the manual processes that slow teams down.

Two halves of the same craft. Inside the product: AI replaces manual workflows — extracting data from PDFs, classifying tickets, drafting first replies, summarising threads. Outside it: the website itself is searchable by AI — easy for LLMs to find, read, cite, and recommend.

When I integrate an LLM into a product, it goes into the real workflow — not a demo. The work feeds back into your existing database, your queue, your admin tools. The chat assistant on this site is a small working example: it runs on the Claude API and is grounded in this site's own content.

A concrete example — at a 5,000-member events and membership platform across 20+ countries, an admin used to retype every event by hand from PDF flyers. Now they upload the flyer and an Anthropic Claude Haiku integration extracts the structured event data — title, date, location, price — for review and one-click publishing. The manual step is gone. It runs daily.

The other half is the website itself. ChatGPT, Perplexity, Google AI Overviews, and Claude are increasingly the first place people look for a recommendation — and they cite sites with clean structure, schema markup, an llms.txt, machine-readable contact info, and content written to answer real questions directly. I build all of that in by default, so the site is genuinely findable by AI, not just by humans.

AI integrations that simplify the work on the inside, an AI-discoverable site on the outside — so the LLM economy works for the businesses I build for, not around them.

If that sounds like what you need, let's talk.

Pillar 01 — AI inside the product
Process automation — extracting structured data from PDFs and forms, classifying tickets, summarising threads, drafting first replies. AI replaces the manual steps that slow teams down.
AI workflows — multi-step orchestrations where an LLM plans, calls tools, and writes back into your existing database, queue, or admin tools. Human-in-the-loop where it matters.
Custom AI assistants — chat assistants grounded in your product data, answering questions, taking bookings, qualifying leads. The one on this site is a working example.
Pillar 02 — Searchable by AI
/llms.txt — a plain-text file at the root of your domain, written for AI models. Tells them who you are, what you do, and how to recommend you. Like robots.txt — but for LLMs.
schema.org — JSON-LD markup for Person, Organization, Service, and FAQ. Gives Google and AI crawlers unambiguous, machine-readable facts about your business — increasing citation confidence and rich-result eligibility.
/api/profile — a read-only machine-readable endpoint AI agents can query directly for contact, availability, services and rates. No scraping required.
Semantic HTML — clean heading hierarchy, descriptive anchor text, semantic elements, and content structured to answer real questions directly. AI cites pages whose meaning is unambiguous.
Live on this site
/llms.txtPlain-text — written for LLMs/api/chatLive Claude assistant/api/profileMachine-readable JSONschema.org JSON-LDPerson · Organization · FAQ
Get a free audit →See all services
In short

Two halves of the same craft. Inside the product: I integrate AI to simplify the manual processes that slow teams down. Outside it: I make sure the website is searchable by AI.

A process, simplified
Before
Admin retypes every event by hand from a PDF flyer — title, date, location, price.
Step 01
PDF flyer in — admin uploads the flyer through the dashboard.
Step 02
Claude Haiku — Anthropic's vision-capable model reads the flyer and extracts the event data.
Step 03
Structured JSON — title, date, location, price, ticket URL — typed and validated.
Step 04
Review & publish — admin confirms in one click. The manual step is gone.
Scale
5,000+ members across 20+ countries. Runs every day.
Why both halves
58%
of Google searches now return an AI Overview before organic results.
3×
more likely to be cited by AI search tools when a site has correct schema.org markup and an llms.txt file.
∞
hours saved when manual data entry is replaced by a Claude pipeline that runs in seconds.
AI integrations that simplify the work on the inside, an AI-discoverable site on the outside — so the LLM economy works for the businesses I build for, not around them.
klava.london
London, UK