FAQ
The questions we hear most from Vancouver Island businesses considering AI engineering and custom software.
Straight answers
23 questionsIf yours is not here, email hello@entoura.studio.
AI infrastructure: document and data intelligence, workflow automation, retrieval grounded in your own data, intake classification, compliance monitoring, and structured outputs. Specific jobs with citations, not a general-purpose chatbot.
Rarely. Most builds use frontier model APIs (Anthropic, OpenAI, Google) chosen per task for capability, latency, cost, and residency. When a use case demands it, we fine-tune or self-host. Model choice is an engineering decision, not a default.
That is decided in writing during the Blueprint, which defines what reaches a model, what stays local, what gets logged, and where inference runs. Canadian-hosted infrastructure is the default.
Defined behaviour: fallbacks, confidence thresholds, human review queues, and graceful degradation. The system is built to handle model errors as a normal operational condition, not an exception.
For individual drafting, summarizing, and learning, yes, and you should. A subscription is a general-purpose tool a person opens and prompts. It has no standing connection to your systems, no memory of how your business runs, and it only acts when someone drives it. That is a productivity tool for a person, not an AI system for a business. When you need AI embedded in a workflow, governed, and reliable enough to depend on, you have outgrown the subscription.
When the work needs to run inside your software, not at a keyboard. APIs let you embed models in the tools you already use, choose the model per task (Claude, GPT-class, Gemini, or open-source), set data-retention terms in writing, and pay per token at volume instead of stacking $20–100/month seats across a team. That is the path from "everyone has a login" to a system the business runs on. The Blueprint defines whether you are there yet.
Yes. Entoura structures every build for client-side control: business-owned accounts, clear access, documentation, and repositories. Some details depend on third-party platforms (Apple, Google, Stripe, hosting providers), which we account for during planning.
A working system in production: AI infrastructure, the application it runs inside, a documented code repository, hosting access, and a handoff call. A running system, not a pitch deck.
Yes. The codebase uses React, TypeScript, and standard infrastructure. Any competent team can pick it up. The documentation is written specifically for this scenario.
Most first releases ship in 4–8 weeks. A more complex multi-platform build runs 8–14 weeks. The work is scoped before it is quoted, so the timeline is specific to your project, not a guess.
Every build is custom, so there is no menu price on the website. It starts with Entoura.Blueprint™, a paid planning engagement that produces a fixed build quote before any code. The Blueprint page has the engagement fee; the build number comes out of that plan. Managed services are monthly and scoped to your system.
New work gets named, scoped, and priced before it enters the build, so nothing arrives as a surprise. If something changes direction, the scope document gets adjusted together, so you always know what you are paying for.
Yes. Product design, interface design, and brand-informed layouts are part of the build process. Design and engineering happen together in one team, with no wireframes handed to a separate group.
No. AI accelerates how we build and powers what we deliver. But the product is real code, reviewed by a human engineer, deployed to real infrastructure, and built to survive year three.
For AI infrastructure: frontier model APIs chosen per task, vector databases, structured extraction pipelines, evaluation frameworks. For applications: React, Next.js, TypeScript, Expo (mobile), Supabase, Stripe, and Vercel. All hosted in Canada where possible.
Yes. Cross-platform mobile applications are built using React Native and Expo, deployed to the App Store and Google Play. Mobile and web can share a codebase when it makes sense.
Usually. If it has an API, export, webhook, CSV, or database path, we can likely connect it. Common integrations include accounting platforms, CRMs, scheduling tools, payment processors, and email platforms. If something cannot connect, we say so early.
Vancouver Island is home base, but the work is not geographically restricted. The studio serves clients across BC and beyond. The local accountability of knowing where the studio is and having direct access to the team is part of the value regardless of where you are.
The team that scopes your AI infrastructure and application is the same team that builds and maintains it. One team throughout, with no handoffs between sales and delivery.
Direct communication, typically Slack, email, or video calls. Weekly working previews so you see progress as it happens. You work straight with the team doing the work, with no project managers sitting in between.
Three options: run it yourself, keep us on managed services, or hand it to another team. Everything is structured for continuity either way, with documentation and access planning designed for a clean transition.
Yes. Managed services cover AI model monitoring, continuous improvements, bug fixes, and support. Cancel anytime. There is no lock-in period.
On a retainer, the fix is on us. If not, the codebase and infrastructure are documented well enough for any team to diagnose and resolve issues. Observability is built in from the start: error tracking, logging, and alerts are part of the standard delivery.
The first conversation is free and takes 25 minutes. If building is not the right answer, we say so.
Discover Your AI OpportunitiesAI Opportunity Assessment
Confirm your call
You’re booked.
Confirmation sent. Carter will see you then.
By chatting you agree to our privacy terms. Handled in Canada.
I couldn’t reach the calendar just now. Here’s a direct booking link.
Still here. Ready whenever you are.
Try: "What is the Blueprint?", "How does AI Engineering work?", "What does a build cost?"