[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"site-settings":3,"home-content":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.",{"services":12,"caseStudies":100,"posts":182},[13,30,44,58,72,86],{"id":14,"slug":15,"title":16,"tagline":17,"summary":18,"body":19,"icon":20,"features":21,"sort_order":26,"published":27,"created_at":28,"updated_at":29},"00000000-0000-4000-8000-000000000101","ai-automation","AI Automation","Automation that pays for itself.","We remove the manual work eating your team's day — replies, follow-ups, data entry, reporting — with automation that is monitored, measured, and yours.","## The problem\n\nSomewhere in your business, a person is copying information from one screen into another. Another is answering the same enquiry for the fortieth time this week. Another spends every Friday assembling the same report. None of them were hired to do that — and every hour of it is an hour not spent on customers.\n\n## What we do\n\nWe find the manual work that costs you the most and replace it with automation that runs quietly in the background: enquiries answered in seconds, documents read and filed, reports that assemble themselves. Where a decision needs human judgment, the system routes it to a person — automation should remove busywork, not oversight.\n\nEverything we ship is monitored and measured. You'll know exactly how many hours it saves, because we count them.\n\n## What you get\n\n- The repetitive work handled — accurately, around the clock\n- A clear before\u002Fafter measure: hours saved, response times, error rates\n- Systems your team can see into, not a black box\n- Full ownership — the automation is yours, not rented from us\n\n## How it starts\n\nTell us the task your team would be happiest to never do again. We'll map it, quote a fixed price, and tell you honestly whether it's worth automating.","Bot",[22,23,24,25],"Enquiry & follow-up automation (email, WhatsApp, web)","Document and data-entry automation","Automated reporting — daily, not monthly","Human-in-the-loop approvals where judgment matters",1,true,"2026-07-16T07:53:25.514661+00:00","2026-07-16T20:45:35.564284+00:00",{"id":31,"slug":32,"title":33,"tagline":34,"summary":35,"body":36,"icon":37,"features":38,"sort_order":43,"published":27,"created_at":28,"updated_at":29},"00000000-0000-4000-8000-000000000102","websites-and-apps","Websites & Web Apps","Built to win customers, not just look good.","Fast, modern websites and web applications that turn visitors into customers — built by engineers, not a template farm, and ready to grow with you.","## The problem\n\nMost business websites are brochures: they look fine, load slowly, and do nothing. Meanwhile your customers want to enquire, book, order, and pay — and if your site can't do that, they find one that can.\n\n## What we do\n\nWe build websites and web applications as working infrastructure: fast enough to rank on Google, clear enough to convert, and wired into the rest of your business — your enquiries flow into your CRM, your bookings into your calendar, your orders into your fulfilment.\n\nBecause we're engineers first, the same team can take you from a marketing site to a full customer portal without starting over.\n\n## What you get\n\n- A site that loads fast, ranks well, and converts visitors\n- Integrations with the tools you already run\n- A content admin you can actually use — no developer needed for edits\n- Clean handover: code, hosting, and documentation are yours\n\n## How it starts\n\nSend us your current site (or the idea for one). We'll reply with a plain-English review and a fixed quote within one business day.","LayoutTemplate",[39,40,41,42],"Marketing websites that rank and convert","Custom web applications & customer portals","E-commerce & booking systems","Performance, SEO & analytics built in",2,{"id":45,"slug":46,"title":47,"tagline":48,"summary":49,"body":50,"icon":51,"features":52,"sort_order":57,"published":27,"created_at":28,"updated_at":29},"00000000-0000-4000-8000-000000000103","progressive-web-apps","The PWA Advantage","An app on every phone — without the app-store bill.","Progressive Web Apps give your customers an app-like experience on any phone — installable, offline-capable, push-enabled — without the cost of separate iOS and Android builds.","## The problem\n\n\"We need an app\" usually means two expensive builds (iOS + Android), two review processes, and an ongoing maintenance bill most SMEs never budgeted for. Most businesses don't need an app store — they need their service on the customer's home screen.\n\n## What we do\n\nWe build Progressive Web Apps: one codebase that behaves like a native app on every device. Your customers install it straight from the browser, get push notifications, and can keep using it with a weak connection. You get one build to maintain instead of three.\n\nFor retail ordering, bookings, member portals, and field tools, a PWA delivers 90% of the native-app experience at a fraction of the cost — and updates instantly, with no store approval queue.\n\n## What you get\n\n- An installable, app-like experience on every phone\n- One codebase — one build, one bill, one place to improve\n- Push notifications, offline mode, home-screen presence\n- Honest advice for the cases where you genuinely do need native\n\n## How it starts\n\nTell us what you wish your customers could do from their phone. We'll tell you whether a PWA fits — and what it would cost, fixed.","Smartphone",[53,54,55,56],"One build for every device — iOS, Android, desktop","Installable from the browser, no app store required","Offline capability & push notifications","A fraction of the cost of native development",3,{"id":59,"slug":60,"title":61,"tagline":62,"summary":63,"body":64,"icon":65,"features":66,"sort_order":71,"published":27,"created_at":28,"updated_at":29},"00000000-0000-4000-8000-000000000104","systems-integration","Systems Integration & APIs","Make your tools act like one system.","We connect the tools your business already runs — CRM, accounting, spreadsheets, WhatsApp, legacy software — so data flows once, correctly, everywhere.","## The problem\n\nYour CRM doesn't talk to your accounting software. Orders live in one tool, customers in another, and the truth lives in a spreadsheet someone updates by hand every Monday. Every gap between systems is filled by a person retyping data — slowly, and sometimes wrongly.\n\n## What we do\n\nWe build the connective tissue: integrations that move data between your tools automatically, APIs that let your systems be extended instead of replaced, and modern interfaces wrapped around legacy software you're not ready to retire.\n\nThe goal is simple: enter information once, and let it appear everywhere it's needed.\n\n## What you get\n\n- Your tools connected — no more re-keying between systems\n- One source of truth for customers, orders, and money\n- Legacy systems modernized without a risky rewrite\n- Documentation your next developer will thank you for\n\n## How it starts\n\nAn integration review: we map your tools and the manual bridges between them, then hand you a sequenced plan — worst leak first.","Cable",[67,68,69,70],"CRM, accounting & operations tool integration","API design & development","Legacy system modernization","Spreadsheet rescue — one source of truth",4,{"id":73,"slug":74,"title":75,"tagline":76,"summary":77,"body":78,"icon":79,"features":80,"sort_order":85,"published":27,"created_at":28,"updated_at":29},"00000000-0000-4000-8000-000000000105","data-and-analytics","Data & Analytics","Decisions from dashboards, not gut feel.","From scattered spreadsheets to live dashboards: we build the data foundation that shows you — daily — what's selling, what's stuck, and what's slipping.","## The problem\n\nEvery important question — what sold best last month, which branch is behind, which customers are about to leave — takes days and a spreadsheet export to answer. And when two reports disagree, nobody knows which one to trust.\n\n## What we do\n\nWe pull the data out of your operational tools into one governed place, define every metric once, and put live dashboards in front of the people who need them. Sales by branch, stock by location, cash position, response times — visible every morning, not at month-end.\n\nClean, connected data has a second benefit: it's the foundation every AI initiative needs. Companies that sort their data first get automation that actually works.\n\n## What you get\n\n- Live dashboards your leadership actually opens\n- One agreed definition of revenue, margin, and every metric that matters\n- Reports that assemble themselves — reclaim those Friday afternoons\n- A data foundation ready for AI when you are\n\n## How it starts\n\nBring us the three questions you most wish you could answer instantly. We'll show you the dashboard that answers them — and quote it, fixed.","Database",[81,82,83,84],"Live business dashboards","Data pipelines from your operational tools","One definition of every metric that matters","AI-ready data foundations",5,{"id":87,"slug":88,"title":89,"tagline":90,"summary":91,"body":92,"icon":93,"features":94,"sort_order":99,"published":27,"created_at":28,"updated_at":29},"00000000-0000-4000-8000-000000000106","consulting","Consulting & Strategy","One partner from idea to infrastructure.","Senior technical judgment when you need it: technology roadmaps, build-vs-buy decisions, AI readiness, and architecture review — from engineers who build for a living.","## The problem\n\nTechnology decisions are cheap to make and expensive to unmake. The wrong platform, the wrong vendor, or building the wrong thing first can cost a growing business years. Most SMEs don't need a full-time CTO — they need senior judgment at the moments that matter.\n\n## What we do\n\nWe act as your technical partner: reviewing decisions before you commit, evaluating vendors without commission bias, assessing whether your business is ready for the AI projects on its wish list, and building roadmaps that respect both your ambition and your budget.\n\nWe're practitioners, not analysts. Every recommendation is one we'd be willing to build ourselves — and often we do.\n\n## What you get\n\n- Straight answers, with reasoning you can interrogate\n- A roadmap sequenced by return, not by trend\n- Vendor and quote reviews from people who know what things should cost\n- An on-call technical brain for the big decisions\n\n## How it starts\n\nA working session on your hardest current technology question. If we can't add clarity, you don't pay.","Compass",[95,96,97,98],"Technology roadmaps sized to your budget","Build-vs-buy & vendor evaluation","AI readiness assessment","Fractional CTO for growing businesses",6,[101,131,158],{"id":102,"slug":103,"title":104,"client":105,"industry":106,"summary":107,"body":108,"results":109,"stack":122,"cover_image":128,"sort_order":26,"published":27,"created_at":129,"updated_at":130},"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.",[110,113,116,119],{"label":111,"value":112},"First response time","4 h → 30 s",{"label":114,"value":115},"Viewings booked","+38%",{"label":117,"value":118},"Enquiries missed","0",{"label":120,"value":121},"Delivery","5 weeks",[123,124,125,126,127],"WhatsApp Business API","Claude API","Supabase","n8n","Google Calendar","\u002Fimages\u002Fcase-enquiries.webp","2026-07-16T07:53:25.75398+00:00","2026-07-16T20:45:36.157743+00:00",{"id":132,"slug":133,"title":134,"client":135,"industry":136,"summary":137,"body":138,"results":139,"stack":152,"cover_image":157,"sort_order":43,"published":27,"created_at":129,"updated_at":130},"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.",[140,143,146,149],{"label":141,"value":142},"Repeat orders","+52%",{"label":144,"value":145},"Home-screen installs","12,000+",{"label":147,"value":148},"vs. native build cost","≈ 40%",{"label":150,"value":151},"Order time (repeat)","\u003C 60 s",[153,154,125,155,156],"Nuxt","PWA","Paystack","Push API","\u002Fimages\u002Fcase-retail-pwa.webp",{"id":159,"slug":160,"title":161,"client":162,"industry":163,"summary":164,"body":165,"results":166,"stack":179,"cover_image":181,"sort_order":57,"published":27,"created_at":129,"updated_at":130},"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.",[167,170,173,176],{"label":168,"value":169},"No-shows","−41%",{"label":171,"value":172},"Staff hours reclaimed \u002F week","26",{"label":174,"value":175},"Reporting cadence","monthly → daily",{"label":177,"value":178},"Patient wait to book","0 (self-serve)",[153,125,123,126,180],"Metabase","\u002Fimages\u002Fcase-clinic.webp",[183,197,209],{"id":184,"slug":185,"title":186,"excerpt":187,"body":188,"cover_image":189,"tags":190,"published":27,"published_at":194,"created_at":195,"updated_at":196},"00000000-0000-4000-8000-000000000303","build-vs-buy-ai-2026","Build vs. Buy in 2026: A Decision Framework for AI Tooling","The AI vendor landscape reinvents itself every quarter, which makes \"just buy something\" as risky as \"build everything.\" A four-question framework for deciding without regret.","Two years ago the safe advice was \"buy — the vendors will out-iterate you.\" One year ago it flipped: capable models plus thin glue code made building shockingly cheap. Today the honest answer is *it depends*, which is useless without a framework. Here's ours.\n\n## Question 1: Is this a differentiator or a utility?\n\nIf the capability touches how you win customers — pricing intelligence, your support experience, your core operations — bias toward **building**, because you want it to fit your process exactly and improve on your schedule. If it's a utility everyone needs the same way (meeting transcription, generic writing help), **buy** it and move on.\n\n## Question 2: Where does the data live, and where must it stay?\n\nThe moment customer or regulated data is involved, vendor evaluation becomes data-flow evaluation. Ask precisely: what's retained, where it's processed, what's used for training, what your deletion rights are. If a vendor can't answer in writing, that's your answer. Building keeps data in your perimeter — often the deciding factor in healthcare, finance, and legal.\n\n## Question 3: What does year two cost?\n\nBuying has visible subscription costs and invisible ones: per-seat growth, usage overages, the integration work the demo didn't show, and switching costs when the vendor pivots, gets acquired, or 10x-es pricing. Building has visible development cost and the invisible one: maintenance, forever. Model both at 24 months, not at the demo.\n\n## Question 4: Can you ride the platform curve?\n\nThe strongest 2026-era argument for building: what took a vendor team to build in 2024 is now a week of work on top of frontier model APIs. Capabilities keep migrating into the platforms themselves. If the thing you'd buy is mostly \"a nice UI on a model call,\" building buys you the platform's improvement curve for free.\n\n## The hybrid that usually wins\n\nIn practice, most of our clients land on: **buy** commodity capabilities, **build** the thin layer where AI touches their differentiated data and workflows, and keep that layer small enough to rewrite in a quarter. In a landscape that shifts this fast, the winning architecture is the one you can change your mind about.\n\n## A rule of thumb\n\nIf you can't write the job description for the tool in one sentence, you're not ready to build *or* buy — go back and run an automation audit first.","\u002Fimages\u002Fpost-buildbuy.webp",[191,192,193],"Strategy","AI Adoption","Leadership","2026-07-08T09:00:00+00:00","2026-07-16T07:53:26.039085+00:00","2026-07-16T20:45:36.61241+00:00",{"id":198,"slug":199,"title":200,"excerpt":201,"body":202,"cover_image":203,"tags":204,"published":27,"published_at":208,"created_at":195,"updated_at":196},"00000000-0000-4000-8000-000000000302","ai-agents-in-production","AI Agents in Production: What Actually Breaks (and How to Engineer Around It)","The gap between an impressive agent demo and a dependable agent system is engineering, not prompting. The five failure modes we see most — and the patterns that prevent them.","Anyone can build an agent demo in an afternoon. The demos are genuinely impressive — which is exactly the problem, because they create expectations the production system has to survive. After shipping agent systems into real businesses, these are the failure modes we plan for on day one.\n\n## Failure mode 1: The confident wrong answer\n\nLLMs fail fluently. In production, a wrong answer delivered with confidence costs more than an honest \"I don't know.\"\n\n**The pattern**: grounding + refusal. Retrieval supplies the facts; the agent is instructed — and *measured* — on refusing when retrieval comes back thin. Track your refusal rate. An agent that never refuses is an agent you can't trust.\n\n## Failure mode 2: Silent drift\n\nModels get updated. Your data changes. A prompt that worked in March degrades quietly by June, and nobody notices until a customer does.\n\n**The pattern**: evaluation harnesses. Keep a versioned suite of real cases with expected outcomes and run it on every change — model, prompt, retrieval index. Treat it exactly like a test suite, because that's what it is.\n\n## Failure mode 3: The permissions blank check\n\nAn agent with broad tool access will eventually do something you didn't intend. Not because it's malicious — because instructions are ambiguous and inputs are adversarial.\n\n**The pattern**: least-privilege tools. Each tool exposes the narrowest possible action, destructive operations require human confirmation, and every call is logged with its full context. Design the tool surface like you'd design an API for an intern on their first day.\n\n## Failure mode 4: Cost creep\n\nToken costs look trivial in the demo and compound brutally at scale — especially with agentic loops that can burn ten model calls answering one question.\n\n**The pattern**: budgets and caching. Per-request token budgets, response caching for repeated questions, small models for routing and classification, big models only where quality is measured to need them.\n\n## Failure mode 5: The un-debuggable incident\n\nSomething went wrong yesterday at 4 p.m. Without traces, you're reconstructing a crime scene from memory.\n\n**The pattern**: full observability from day one. Every request stores its inputs, retrieved context, tool calls, outputs, latency, and cost. When (not if) an incident happens, you replay it in minutes.\n\n## The theme\n\nNone of this is exotic. It's the same discipline software engineering learned decades ago — tests, least privilege, observability, budgets — applied to a component that happens to be probabilistic. Teams that treat agents as software succeed. Teams that treat them as magic write postmortems.","\u002Fimages\u002Fpost-agents.webp",[205,206,207],"AI Agents","Engineering","LLMs","2026-06-24T09:00:00+00:00",{"id":210,"slug":211,"title":212,"excerpt":213,"body":214,"cover_image":215,"tags":216,"published":27,"published_at":219,"created_at":195,"updated_at":196},"00000000-0000-4000-8000-000000000301","automation-audit-guide","The Automation Audit: Finding the 20% of Work That Eats 80% of Your Week","Before you buy any AI tool, map where your hours actually go. A practical, week-long method for finding automation candidates with real ROI — no consultants required.","Most automation initiatives start backwards: a tool gets chosen, then everyone hunts for problems it might solve. The results are predictable — shelfware, cynicism, and a team that flinches at the word \"AI.\"\n\nThe fix is boring and effective: audit first, automate second. Here's the method we use with clients, compressed so you can run it yourself in a week.\n\n## What is an automation audit?\n\nAn automation audit is a structured inventory of the repetitive work in your business, scored by time cost, error cost, and automation difficulty. The output is a ranked list of automation candidates with honest ROI estimates — not a vendor pitch.\n\n## Step 1: Capture the work (days 1–3)\n\nDon't send a survey; nobody remembers their week accurately. Instead, ask each team member to keep a simple interruption log for three days: every time they switch to a repetitive task, one line — what, why, how long.\n\nYou're looking for three patterns:\n\n- **Couriering**: moving data between systems that don't talk (exports, re-keying, copy-paste).\n- **Formatting**: reshaping information for an audience (status reports, client updates, board decks).\n- **Chasing**: reminding humans to do things (approvals, sign-offs, missing documents).\n\n## Step 2: Score the candidates (day 4)\n\nFor each recurring task, estimate: hours per month, error impact when done wrong, and how rule-based it is. A task that's high-hours, high-error-cost, and mostly rule-based is a tier-one candidate. High-judgment tasks score lower — they need human-in-the-loop designs, not full automation.\n\n## Step 3: Estimate honestly (day 5)\n\nA useful rule of thumb: an automation that saves H hours per month is worth building if you can ship it for less than 6–9 months of those hours at loaded cost — because maintenance is never zero. If a candidate only pays back in year three, park it.\n\n## What good candidates look like\n\nThe best first automation is usually not the biggest one. It's the one that is visible, measurable, and low-drama: invoice intake, report assembly, CRM hygiene, onboarding checklists. Ship one of those, measure the hours, and let the result build the appetite for the harder wins.\n\n## The one-question version\n\nIf you do nothing else, ask each person on your team: *\"What's the task you'd be embarrassed to explain to an engineer?\"* The answers are your audit.","\u002Fimages\u002Fpost-audit.webp",[16,217,218],"Operations","Playbook","2026-06-10T09:00:00+00:00"]