Questions and answers.About the platform, pricing and more.

Pick a task that runs many times a day under clear rules, with data you already have. We help you choose in a short workshop or in the AI Bootcamp.

The people who know the process, someone from IT for access and operations, and whoever owns your AI roadmap. For a first app, a small team is enough.

We agree on the effect with you beforehand, such as response time, error rate or workload. Operaide reports runs and usage per app, so you can follow adoption.

Every new app reuses what is already set up: sign-in, connections, AI models and rules. Domain experts build the simple ones themselves, developers take on the larger ones.

One is enough to start, if it solves a real problem. The platform pays off more with every further use case, because each one reuses the setup, the rules and the IT approval of the first.

A first version of a simple app runs within hours, a complete one within days, depending on the systems you connect. In the AI Bootcamp your teams build their first apps with us in five days and roll them out.

Domain experts build no-code in the App Builder, and developers extend the apps in code in Operaide Studio. IT keeps control of AI models, data and access. If you like, our engineers build the first version with you, for example in the AI Bootcamp.

Run Operaide on your infrastructure: one container on a Linux server or VM, connected to your identity provider and the AI models you choose. IT approves the platform once, not every app, so new processes build on it without a new IT project each time.

A few hours to describe the process and show examples, then short sessions to test the first version with real cases. Your team keeps doing its daily work.

Operaide takes on the routine: sorting, typing, searching. Your team keeps the decisions and gets time for the work that needs people, like customers, exceptions and quality.

Yes. Domain experts start no-code in the App Builder. When an app needs more, developers continue in Operaide Studio on the same app, as TypeScript code in Git.

You can build an agent with any agent framework. What takes months is everything around it: sign-in, roles, credentials, tracing, deployment and operations. Operaide brings all of that, so your team writes only the business logic and the first app runs in days. The apps stay plain TypeScript in your Git, on your own infrastructure.

Linux on x86 or ARM with Docker: 2 CPU cores and 4 GB RAM to start with, more for many users or self-hosted AI models. Operaide runs as one container on-premises, in your VPC or in any cloud.

Commercial, European and self-hosted AI models: OpenAI, Anthropic, Mistral, Azure, Google, Amazon Bedrock, OpenRouter and more, or open-source models via Ollama or LM Studio. Your administrators configure them, and every step of an app can use its own AI model, chosen for its task.

Yes. There is no connector catalogue to wait for: each connection is built for your system through REST or MCP, including ERP, CRM, EDI, portals, older and in-house systems. Connections are set up once in the platform, and your apps read and write through them with the access rights you set, without secrets in the code.

Every run is traced step by step, every AI call is recorded, and Audits record an EU AI Act assessment for each app, signed off by an authorised manager.

Enterprise is one annual licence: a base package sized to your company plus an execution package for what your apps run. Users, apps and tenants are unlimited. We put together an offer after the first conversation. You can start with one use case or an AI Bootcamp, and the Community Edition is free.

One container to install, then sign-on and the first connections to set up. How long it takes depends on your network, firewalls and reverse proxy. Our engineers help along the way.

Yes. Operaide scales with your workloads and can run with redundancy in your infrastructure. We plan the setup with your IT.

Support matched to your needs, with response targets in your contract. If you need more, you can add a larger support package at any time.

Yes. The Community Edition is free to use for developing and evaluating AI agents and automations. You run it on your own machine or server.

We're opening the Community Edition in stages so we can support every developer properly. Apply with a few details and we'll get back to you.

Yes. Both editions are the same platform. Apps you build with the Community Edition run on Enterprise without changes.

No. You connect your own AI providers, such as OpenAI, Anthropic, Azure or Mistral, or run open-source AI models yourself. Token costs go directly to your provider, and Operaide reports usage per app.

Always on infrastructure you choose: on-premises, in your VPC or in a European cloud, as one container inside your network and under your security controls. For each step of an app you choose the AI model, fully local if needed.

Yes. Start with one use case, as a proof of value in an AI Bootcamp or as a first project. We plan it with you.

An app that runs on your real process and data and shows its value in daily work. Not a concept, a mock-up or a prototype that ends in a drawer.

Domain experts who know the processes, developers who will build and run the apps, and the person who owns your use case list. Someone from IT joins for access and operations.

Both. We recommend on-site for the build week, because the fastest results come from working side by side.

A shortlist of processes you want to automate, access to the systems involved, and the people who know them. We help you choose the use cases beforehand.

On your infrastructure or in an environment we provide for the week. The apps you build move to your installation for the trial.

A go or no-go decision, without risk. Your team has used the apps in daily work, so you decide on facts. With a go, the apps move into production with Enterprise, and nothing you built is lost.

It depends on team size and setup. We send you an offer after a first conversation.

Yes. You decide which providers are configured. With self-hosted AI models via Ollama or LM Studio, no model call leaves your network.

Only if you decide so. Operaide runs on your own infrastructure, and for each step of an app you choose the AI model: a local model on your own hardware for data that must not leave, or a frontier model in your cloud tenant. An app can also use a local model to remove personal data before anything reaches a cloud model. Every run is traced, so you can see which data went where.

No. Operaide also runs air-gapped, as captive AI without any internet connection: with self-hosted AI models, and the aggregated usage metrics sent as a file instead of over a connection. In connected setups, Operaide sends these metrics to the Operaide audit service once a day.

New versions are released as Docker images. You pull them from the registry and decide when to install them. Signed images, so you can verify each one before installing, are available on request. In air-gapped networks, you bring the image in like any other software.

Nobody, unless you grant access. Operaide runs on your infrastructure under your administration.

Your apps are TypeScript code in your own repository, and your data sits in standard databases you can export. Nothing is locked in a vendor cloud.

Yes. We provide architecture and compliance documentation, including an orientation against the BSI AIC4 criteria, on request.

You can build an agent with any agent framework. What takes months is everything around it: sign-in, roles, credentials, tracing, deployment and operations. Operaide brings all of that, so your team writes only the business logic and the first app runs in days. The apps stay plain TypeScript in your Git, on your own infrastructure.

Commercial, European and self-hosted AI models: OpenAI, Anthropic, Mistral, Azure, Google, Amazon Bedrock, OpenRouter and more, or open-source models via Ollama or LM Studio. Your administrators configure them, and every step of an app can use its own AI model, chosen for its task.

Enough to read and review code. AI coding agents write much of it, but someone on the team should be able to judge what they produce. Familiarity with Zod helps.

Claude Code and Codex are set up in Operaide Studio, and Operaide Code is our own terminal agent. Other assistants work too: the Reaktor framework reference is public in our docs.

Yes. Download an app template, work in your own editor and deploy with the same commands. Operaide Code runs on macOS, Linux and Windows with your own AI provider keys.

Apps run in a sandbox with a fixed set of modules, including axios, zod, the Vercel AI SDK, pdf-lib and the MCP SDK, plus any published operaide-* library. This keeps apps secure and predictable across tenants.

Yes. We show you what AI can do in your processes, look at where it brings the most value and pick the first use cases with you. No strategy project needed.

You do. The apps are TypeScript code in your own Git, with their documentation. Nothing runs in a cloud of ours, and your team can change everything we built.

No. We hand over code, documentation and know-how, and enablement trains your team to build and run apps on its own. Support from our engineers stays available if you want it.

It depends on the process and the systems involved. A first app usually runs within days, a larger application with several systems within weeks. We plan it with you in the first workshop.

Both. Workshops and the bootcamp work best in your offices, the weeks in between usually run remote.

It depends on the scope and the support you need. We put together one offer for platform and services after the first conversation.

Support matched to your needs, with response targets in your contract. If you need more, you can add a larger support package at any time.