QUESTIONS
WE GET ASKED

It reads your documents and returns structured output. You feed it a blueprint, a freight invoice, a customs package, a set of daily site reports — and it extracts the relevant data, cross-references it against other documents or internal rules, and flags issues. The output is a formatted report your team can act on directly. It doesn't replace your project management system or TMS — it handles the document intelligence layer your team is currently doing manually.

Custom-built for your operation. Every system starts from a discovery session where we map the specific document types you work with — your blueprints, your freight invoices, your customs formats. The model is fine-tuned on your actual documents, not trained on generic data. A residential GC and an industrial contractor get different builds. A freight broker and a 3PL get different builds. There's no template being reskinned — it's built around what you actually do.

PDFs (including scanned), spreadsheets (Excel, CSV), Word documents, and plain text. For construction: blueprints, RFI logs, scope of work documents, daily site reports, subcontractor agreements. For logistics: freight invoices, bills of lading, customs packages (commercial invoice, packing list, certificates of origin, CMR), rate confirmations, carrier statements. If you have document types that aren't listed — send us one in the free assessment and we'll tell you exactly what the system can extract from it.

It doesn't replace your ERP, TMS, or project management system. It doesn't connect to live data feeds or carrier APIs in real time. It doesn't answer open-ended questions or function as a general-purpose chatbot. It processes documents you feed it and returns structured findings. It's a document intelligence layer — not an all-in-one platform. If you're looking for a full operations suite, this isn't it.

You receive the full source code, all model weights, the full system documentation, and a handover session with your team. You are not buying a licence to use software we retain. You own the build outright — the same way you own any other piece of equipment or software asset your company acquires. If Marapone shut down tomorrow, your system would keep running exactly as it does today. You can modify it, extend it, or have another developer work on it. There are no usage restrictions post-purchase.

Because a subscription model requires us to keep the system running in our infrastructure — which means your data routes through our servers, you're dependent on us staying in business, and you're paying indefinitely for something you never fully own. We build it, install it on your hardware, and hand it over. There's no reason to keep billing you after that. The retainer support option exists if your workflow changes or you want new modules — but that's your choice to make, not a recurring line item.

Four tiers: Starter ($1,500 CAD), Pilot ($4,900 CAD), Full Build ($9,500 CAD), and Plus ($15,000 CAD). Starter covers one workflow module. Pilot covers two modules for operations with more document complexity. Full Build is the complete four-module suite. Plus adds server or air-gapped deployment, extended team onboarding, and priority support. Full details, including what's included in each tier, are on the Pricing page.

No mandatory ongoing costs. The system runs on your hardware with no external dependencies — no API keys, no cloud subscription, no usage fees. If you want ongoing support — new modules, updates when your document formats change, or a new document type enters your operation — retainer support is available at $499 CAD/month (cancel any time) or $3,500 CAD/year. Most clients go three to six months before engaging the retainer, if they use it at all.

Nowhere. The system runs entirely on your hardware. Documents are processed locally — no data leaves your premises during operation. There are no external API calls made when the system is processing your documents. Your blueprints, freight invoices, customs documents, and client data stay exactly where they are. This is one of the core reasons clients in construction and logistics choose this model — these industries deal with sensitive project data, client contracts, and regulatory documents that shouldn't be routed through third-party servers.

No. Once the system is installed and handed over, we have no access to your machine, your network, or the documents you run through the system. There's no telemetry, no usage reporting, no backdoor. The system operates entirely offline. If you bring us in for retainer support, that's a separate engagement where you explicitly grant access for a specific scope of work.

The document you send is used to run the assessment and generate your report. It's held securely during that process and deleted after the report is delivered. We don't retain client documents, use them for model training beyond the assessment, or share them with third parties. If you're concerned about sensitivity, we can discuss anonymizing or redacting the document before you send it — the system can still produce meaningful results from a partially redacted document in most cases.

ChatGPT and similar tools are general-purpose assistants. They're not trained on your documents, they don't understand your specific workflows, and every document you feed them leaves your premises and goes through a third-party server. What we build is a private, fine-tuned system that runs entirely on your hardware, trained on your actual documents, and returns structured output for your specific use case — not a generic answer to a prompt. It's not a chatbot. It's an AI that does one thing extremely well for your operation, with no external data exposure.

No system catches everything — and we won't claim otherwise. What the system does is dramatically reduce what slips through compared to manual review, and do it consistently, without getting tired or distracted. The system is built as a first-pass intelligence layer, not a replacement for human judgment. Your team still reviews the output and makes the final call. The goal is that by the time something reaches your desk, the AI has already eliminated 90%+ of the noise and surfaced what actually needs attention. The free assessment lets you evaluate the accuracy directly on your own documents before committing to anything.

Because you own the source code, you're not locked into us. You can have any developer work on it. If you want us to handle updates — new modules, changes when your document formats evolve, or adding a new workflow — retainer support is available at $499 CAD/month or $3,500 CAD/year. Most clients don't need this for the first six months; the system is built to run stably on the document types it was trained on. When you need it, it's there. When you don't, you're paying nothing.

No. If you don't have hardware capable of running a local AI system, we handle it. For Starter and Pilot builds, we can source, configure, and ship a dedicated machine pre-loaded with your build for a flat $1,000 CAD hardware add-on — the machine is yours to keep. For Professional builds requiring multi-GPU systems, we locate parts, assemble, and configure the rig — hardware cost is covered in the project deposit. We'll spec the hardware requirements after the free assessment so there are no surprises.

One to three weeks from signed scope to system handover, depending on the tier and complexity. Starter builds typically run one week. Pilot builds run one to two weeks. Professional builds run two to three weeks. The timeline starts after the scoping call and written specification are agreed on — the assessment and scoping phase before that runs separately and typically takes three to five business days total.

Yes — that's the point. We don't hand over something your IT team needs to figure out. The handover session walks your team through exactly how to use the system: where to put documents, how to read the output reports, and what to do if something looks off. We also provide written documentation. The system is designed to be operated by whoever currently handles your document workflow — not by a developer. Most clients are running independently within the first day.

We create custom content for your company — posts, captions, reels, and videos. Both long form and short form. Everything is written and scripted around your brand, your voice, and the platforms where your audience actually spends time. You get the content ready to publish. What you do with it is up to you.

Primarily the modern social platforms — Instagram, TikTok, YouTube, LinkedIn. Short-form content like Reels and Shorts is where most attention lives now, and that's where the strategy is built around. We don't focus on old-school approaches like mass email campaigns or SEO blog writing — those methods have been largely replaced by short-form video and social content, and that's what actually moves the needle today.

We handle the content — scripts, direction notes, captions, and strategy. Filming and editing are on your end. The scripts and direction notes we provide are written to be easy to execute, even if you're recording on a phone. Most clients find that doing the filming themselves keeps the content more authentic anyway — which is exactly what performs best on short-form platforms.

That's what the free 24-hour assessment is for. Send us one real document from your operation — a blueprint, an invoice, a customs package, whatever is most relevant. We run it through a test system and return a real report: your data, actual findings, no demo output. You'll see exactly what the system extracts and flags from your own document before any conversation about a build. If it doesn't produce something useful, there's nothing to talk about — and you've spent nothing finding that out.

We're based in Canada and Italy, and most of our clients are in those markets — but the work is not geographically restricted. We've scoped builds remotely and can ship hardware internationally when needed. If you're outside our primary markets, reach out and we'll assess fit directly. The free assessment works regardless of location.

We intentionally keep our active build count small — typically two to three projects at a time. We're a boutique operation, not a software factory. This isn't a limitation we're trying to scale past — it's how we ensure every build gets the attention it requires. If our pipeline is full when you reach out, we'll tell you directly and give you an honest timeline.

The free 24-hour assessment. Go to the contact page, fill out the form, and attach one document from your operation. We'll run it through a test system and get a real report back to you within 24 hours. No sales call, no pitch deck, no commitment. If the report is useful, we talk. If it's not, you've spent nothing.