Questions we get asked before a project starts.
Scope, timelines, cost, models, and who owns the code when we are done. If yours is not here, ask us directly.
What services do you offer?
Custom AI applications, AI features inside existing products, conversational agents, intent-driven search, and the ordinary product work around them: interface design, backend, dashboards, CMS. We also do GEO and AIO so your business is represented correctly inside AI answers, not only in search results.
How does your design process work?
A call, then a short paid discovery: what you are trying to do, what data exists, what the AI should and should not decide. You leave that with a scope, a plan, and a cost, usable whether or not you build with us. Design and engineering then run together rather than in sequence.
What industries do you work with?
Recruitment and HR, real estate, SaaS and startups, marketing agencies, education, and hospitality. These are the sectors where we have shipped, broken things, and fixed them in production.
How long does a project take?
A focused MVP typically ships in six to ten weeks, a prototype in days. Platform work with custom integrations runs longer. Data readiness moves the timeline more than anything else.
What does it cost?
Smaller builds start under $10k. Product and platform work runs from $25k upward. We scope in stages, so you can stop, pause, or expand after each one rather than committing to one large number.
Which models and tools do you use?
Anthropic Claude and OpenAI for language work, with Next.js, Supabase, Python, and Vercel around them. Model choice follows the problem. We are not tied to one vendor and will say when the cheaper model is the right answer.
Who owns the code and data, and what happens after launch?
You do. Repositories, prompts, and infrastructure transfer to your accounts at handover, and we never train on your data. Most clients stay on a retained arrangement afterwards for monitoring and iteration, because AI products drift as models and usage change.