[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"site-settings":3,"case-studies-list":11},{"contact_email":4,"socials":5,"seo_default_description":10},"hello@doxacore.com",{"medium":6,"facebook":7,"linkedin":8,"instagram":9},"https:\u002F\u002Fmedium.com\u002F@doxacore","https:\u002F\u002Ffacebook.com\u002Fdoxacore","https:\u002F\u002Flinkedin.com\u002Fcompany\u002Fdoxacore","https:\u002F\u002Finstagram.com\u002Fdoxacore","Doxacore Solutions builds the digital infrastructure that removes manual work and wins customers — websites, apps, PWAs, and AI automation with enterprise-grade engineering at a pace SMEs can move at.",[12,44,72],{"id":13,"slug":14,"title":15,"client":16,"industry":17,"summary":18,"body":19,"results":20,"stack":33,"cover_image":39,"sort_order":40,"published":41,"created_at":42,"updated_at":43},"00000000-0000-4000-8000-000000000201","real-estate-enquiry-automation","Answering every enquiry in seconds — without hiring","Real-estate agency (12 agents)","Real Estate","Enquiries from the website, WhatsApp, and property portals were going cold for hours. Now every one gets an accurate, instant reply — and agents walk into pre-booked viewings.","## The situation\n\nA twelve-agent real-estate firm was drowning in its own success: enquiries arrived around the clock from the website, WhatsApp, and three property portals, but agents could only reply between viewings. Average first response: four hours. In a market where buyers message five agencies at once, four hours is a lost customer.\n\n## What we built\n\nAn enquiry engine that answers instantly on every channel. It identifies the property, answers questions about price, size, and availability from the live listings database, qualifies the buyer with two or three natural questions, and books a viewing straight into the right agent's calendar. Anything unusual — negotiations, complaints, unclear requests — is handed to a human with full context.\n\n## The engineering that mattered\n\n- **Grounded answers only**: the assistant can only state facts from the listings database — if it doesn't know, it says a human will follow up, and one does.\n- **Channel-native**: the same brain answers web chat, WhatsApp, and portal emails, so no channel is a second-class citizen.\n- **Agent handover with context**: humans join with the full conversation and buyer profile in front of them — no \"as I said before\" moments.\n\n## The outcome\n\nEvery enquiry now gets a useful answer in under a minute, around the clock. Viewings booked rose 38% in the first quarter, and the owner's favorite number: enquiries that got no reply at all went from \"we honestly don't know\" to zero.",[21,24,27,30],{"label":22,"value":23},"First response time","4 h → 30 s",{"label":25,"value":26},"Viewings booked","+38%",{"label":28,"value":29},"Enquiries missed","0",{"label":31,"value":32},"Delivery","5 weeks",[34,35,36,37,38],"WhatsApp Business API","Claude API","Supabase","n8n","Google Calendar","\u002Fimages\u002Fcase-enquiries.webp",1,true,"2026-07-16T07:53:25.75398+00:00","2026-07-16T20:45:36.157743+00:00",{"id":45,"slug":46,"title":47,"client":48,"industry":49,"summary":50,"body":51,"results":52,"stack":65,"cover_image":70,"sort_order":71,"published":41,"created_at":42,"updated_at":43},"00000000-0000-4000-8000-000000000202","retail-pwa","A storefront that sells like an app — without the app-store bill","Multi-branch retailer","Retail & FMCG","Customers wanted an app; the native quotes were brutal. A Progressive Web App delivered the home-screen presence, push offers, and repeat-order flow — at a fraction of the cost.","## The situation\n\nA retailer with several branches wanted what its customers kept asking for: \"do you have an app?\" The quotes for native iOS + Android development were more than a year of marketing budget — before maintenance.\n\n## What we built\n\nA Progressive Web App: one build that installs from the browser onto any phone, remembers the customer's usual order, takes payment, and sends push notifications for offers and order updates. It works on the shop's slowest customer Wi-Fi and keeps the catalogue browsable offline.\n\n## The engineering that mattered\n\n- **The repeat-order flow is the product**: two taps from home screen to \"order placed\" for a returning customer — that's where the +52% came from.\n- **Performance as a feature**: sub-2-second loads on mid-range Android phones, because that's what customers actually carry.\n- **One codebase**: every improvement ships to all platforms instantly — no app-store review queue, no version fragmentation.\n\n## The outcome\n\nTwelve thousand customers put the store on their home screen in the first months. Repeat orders — the metric the owner cared about — rose by half. Total cost, including the first year of improvements: roughly 40% of the *lower* native quote.",[53,56,59,62],{"label":54,"value":55},"Repeat orders","+52%",{"label":57,"value":58},"Home-screen installs","12,000+",{"label":60,"value":61},"vs. native build cost","≈ 40%",{"label":63,"value":64},"Order time (repeat)","\u003C 60 s",[66,67,36,68,69],"Nuxt","PWA","Paystack","Push API","\u002Fimages\u002Fcase-retail-pwa.webp",2,{"id":73,"slug":74,"title":75,"client":76,"industry":77,"summary":78,"body":79,"results":80,"stack":93,"cover_image":95,"sort_order":96,"published":41,"created_at":42,"updated_at":43},"00000000-0000-4000-8000-000000000203","clinic-automation","Clinic admin on autopilot","Pharmacy & clinic group (3 sites)","Healthcare","Front-desk staff spent their days on the phone chasing appointments and their evenings compiling reports. Automated scheduling, reminders, and daily reporting gave them both back.","## The situation\n\nThree clinic sites, one shared phone line's worth of chaos: patients calling to book, staff calling to remind, no-shows costing consultation slots, and site managers compiling numbers by hand at month-end.\n\n## What we built\n\nSelf-serve booking that patients actually use (web + WhatsApp), automated reminder sequences that let patients confirm or rebook with one tap, a waitlist that automatically fills cancelled slots, and dashboards that give each site manager today's numbers every morning.\n\n## The engineering that mattered\n\n- **Reminders that converse**: a reminder a patient can *reply* to (\"running late\", \"need to move it\") beats a one-way SMS — that interaction is where the no-show reduction lives.\n- **Waitlist backfill**: a cancelled slot triggers offers to waitlisted patients in order — recovered slots are pure regained revenue.\n- **Privacy by design**: patient data stays in the clinic's own database with role-based access; the automation layer sees only what it needs.\n\n## The outcome\n\nNo-shows fell by 41%. The front desk stopped being a call center — 26 staff-hours a week moved from phone tag to patient care. And leadership now sees occupancy and revenue daily, per site, without anyone compiling anything.",[81,84,87,90],{"label":82,"value":83},"No-shows","−41%",{"label":85,"value":86},"Staff hours reclaimed \u002F week","26",{"label":88,"value":89},"Reporting cadence","monthly → daily",{"label":91,"value":92},"Patient wait to book","0 (self-serve)",[66,36,34,37,94],"Metabase","\u002Fimages\u002Fcase-clinic.webp",3]