Files, docs, examples
About Prostir
Turn what you know into an AI your customers actually use.
Most expertise sits in files, examples, and the same answers you give over and over. You could sell it. You could let it run without you. But the gap between "I know this" and "here is a product people pay for" is full of work nobody warned you about: sign-in, payments, hosting, customer memory.
Prostir is that missing layer. You bring the knowledge. We run the engineering underneath.
Why we built it
Why we built Prostir
The AI part got easy. Anyone can open ChatGPT and get answers in their own voice. The hard part starts after that.
The moment you want to charge for it, or let real customers use it, the questions change. Who signs in. Who paid. What happens when two people use it at once. Where does the knowledge live. Every answer pointed back to the same place: hire a developer, wait three months, spend the budget.
So good ideas stall. They sit in a Notion doc while customers keep asking the same questions. We built Prostir so that the idea is the only part you need to bring.
What it is
What Prostir is, in plain words
Prostir takes your knowledge and turns it into a custom AI agent for your business. It runs where your customers already are: in ChatGPT, in Claude, on your website, or inside your own web dashboard.
- 01 Upload what you know Bring your files, docs, and examples.
- 02 Write the rules in plain English No code — just how it should answer.
- 03 Set a price, or keep it free Charge customers, or keep it free for your team.
- 04 Get one link It works everywhere your customers already are.
Everything a real product needs sits behind that link already:
- Customer accounts
- Payments through Stripe
- Usage limits
- A dashboard of who used what
Already built for you
Who it's for
Who it is for
Prostir is built for people who have the expertise but not an engineering team.
Consultants & coaches
Who answer the same questions every week.
Course creators
Who want a tutor that teaches from their material.
Teams
Who need a private helper that knows their docs and rules.
Anyone with a service to sell
A service worth selling, without spending €15k and a quarter to ship it.
If you can write an email and drag a file, you can launch on Prostir.
Who builds it
Who builds it
Prostir is made by Managed Code, a creative and engineering team that builds products. We have spent years building the kind of infrastructure most products reinvent from scratch: hosted endpoints, knowledge handling, billing, access control.
We turned that work into building blocks so you do not have to. The result is a platform where the hard backend is already solved, tested, and running.
If you want to see exactly what runs under the hood, the next section has it.
Under the hood
For the technically curious
You do not need to read this to use Prostir. If you build software, here is what runs underneath.
Prostir is a .NET platform built by Managed Code. The creator workspace and operator console run on Blazor; the public pages are static Astro. Underneath, typed .NET services on Orleans handle the boundaries between agent, user, session, and operation, with Cosmos for persistence and EF Core for the query model. Aspire orchestrates it locally and in the cloud.
The AI layer uses Microsoft.Extensions.AI for chat clients, embeddings, tool calls, and telemetry. Three Managed Code packages do the heavy lifting: MCPGateway aggregates tools, prompts, and upstream MCP sources; MarkdownLd.Kb builds the Markdown-LD and JSON-LD knowledge artifacts behind search; Storage abstracts files, memory, and runtime artifacts.
Actions stay server-side. The official MCP C# SDK handles protocol, Jint runs sandboxed JavaScript tools, Stateless drives workflow transitions and can-fire checks, and Stripe.net runs billing and payments.
Under the hood
For the technically curious
You do not need to read this to use Prostir. If you build software, here is what runs underneath.
Managed Code
Open-source primitives Prostir uses under published agents.
.NET AI Runtime
The framework and libraries behind tools, workflows, and protocol edges.
Where to start
Read the cases before you pick a build path.
The case studies show how the pieces map to real customer-facing AI agents: a brand-voice assistant, a course tutor, a paid expert, an internal helper. Pick the one closest to your idea and start there.