Lead-Generation Websites for Service Businesses
Conversion-focused websites for service businesses that need to explain complex offers clearly, earn trust, and turn qualified visits into enquiries.
Explore the solution →AUZ Case Study · AI Automation
Vivi is the intelligent assistant Auztec built for Vision Touch Ltd’s website. It understands natural-language, typo-tolerant questions, recognises 140+ Greater London areas and postcodes, answers from the site’s own content, and qualifies enquiries through a guided flow — all without a mandatory paid AI service, with a one-switch upgrade to Cloudflare Workers AI.
AuztecVivi
AI Automation
A construction firm’s website visitors ask wide-ranging questions — services, areas, timelines, quotes — often with typos and local place names. The brief called for an assistant that could answer instantly and offline-capably, qualify real leads, and run at near-zero cost on serverless hosting, with a clean upgrade path to a hosted LLM when the business wanted it.
We engineered a small conversational engine that scores keywords over a knowledge base built from the site’s own content, with bounded fuzzy matching and light stemming for typo tolerance, plus conversation context that remembers the current service and area. An optional server-side AI layer (Cloudflare Workers AI or any OpenAI-compatible provider) is consulted only for low-confidence questions, and a rule-based fallback handles human handover, lead capture, and email drafting.
The engineering and design work behind the product.
Bounded Levenshtein fuzzy matching and light stemming resolve “rennovation”, “kitchin”, “illford”, and more.
Recognises all Greater London districts plus postcode-prefix detection (IG1, HA1, SE15 …).
Remembers the current service and area, so follow-up questions and a plain “yes” continue the right thread.
A nine-step flow captures the enquiry with project type and location pre-filled, then drafts an email.
A retrieval fallback fuzzy-searches the whole knowledge base before ever saying “I’m not sure”.
No server-side conversation storage, input caps, rate limiting, and grounded prompts — no prices, no promises, no invented facts.
Understands natural-language, typo-tolerant questions
Recognises 140+ Greater London areas plus postcode prefixes
Nine-step lead-qualification flow with pre-filled project type and location
Answers grounded in the site’s own knowledge base — no mandatory paid AI
37 automated intent checks in the test suite
One-switch upgrade path to Cloudflare Workers AI
See how the principles behind this project apply to other business problems.
Conversion-focused websites for service businesses that need to explain complex offers clearly, earn trust, and turn qualified visits into enquiries.
Explore the solution →Knowledge-grounded assistants that answer recurring questions, guide visitors, qualify enquiries, and hand sensitive cases to people.
Explore the solution →A practical architecture for combining predictable intent handling, verified knowledge, optional generative AI, and safe human escalation.
Read the insight →A maintainable approach to service architecture, technical SEO, media performance, enquiry capture, and serverless deployment.
Read the insight →Tell us what you're building. We'll help you turn it into a scalable digital product.