107 lines
5.7 KiB
Markdown
107 lines
5.7 KiB
Markdown
---
|
|
title: "Apps + AI Development"
|
|
description: "Run your business on open-source apps, then build AI on top of them — notebooks, version control, CI/CD, digital twins, and a live index of your business, all private."
|
|
sections:
|
|
- type: hero
|
|
compact: true
|
|
eyebrow: "Solutions · Apps + AI Development"
|
|
title: "Your Business Apps and Your AI Workbench, on One Private Platform."
|
|
subhead: "Run your business on open-source apps, then build AI on top of them — with notebooks, version control, CI/CD, and safe test environments already connected to your own data."
|
|
fit: { core: "yes", library: "yes", sandbox: "no", controls: "yes" }
|
|
ctas:
|
|
- label: "Start 7-Day Free Trial"
|
|
url: "/start-now/"
|
|
style: primary
|
|
- label: "Book a Demo"
|
|
url: "https://calcom.federated.computer/david/60-min-meeting"
|
|
style: ghost
|
|
|
|
- type: text
|
|
bordered: true
|
|
kicker: "Who This Is For"
|
|
headline: "You Have Ideas for AI, and Data You Won't Hand Over"
|
|
body: |
|
|
You want the savings and privacy of open-source business apps. You also have developers, analysts, or a technical founder who want to build with AI: a support-triage model, a sales assistant that knows your CRM, automations that save the team hours a week.
|
|
|
|
The hard part usually isn't the model. It's getting clean, current access to your own data without copying it into a third-party cloud, and having a safe way to test what you build. This path gives you both: the Software Library for running the business, and Data & Controls for building on it.
|
|
|
|
- type: features
|
|
bordered: true
|
|
tinted: true
|
|
kicker: "Your AI Toolkit"
|
|
headline: "Everything You Need to Build, Already Wired to Your Data"
|
|
items:
|
|
- label: "MCP in every app"
|
|
body: "Claude, ChatGPT, or a private local model can read and act inside your apps through scoped connections — no custom integration code."
|
|
- label: "The Organizational Brain"
|
|
body: "A live, searchable index of your files, forum threads, and support tickets, so anything you build starts with full context."
|
|
- label: "Jupyter notebooks"
|
|
body: "A safe place to explore your own data and prototype ideas with local AI."
|
|
- label: "Gitea + CI/CD"
|
|
body: "Every change, human- or AI-written, is tracked, tested, and deployed automatically."
|
|
- label: "Digital twin environments"
|
|
body: "An exact, safe copy of your live systems for testing risky changes with zero danger to real data."
|
|
- label: "Grafana & Prometheus"
|
|
body: "Real-time monitoring that catches problems, including automations stuck in a loop, before they get expensive."
|
|
- label: "Federated learning"
|
|
body: "Train models locally on your own data. Only encrypted learnings are ever shared, and only if you choose to take part."
|
|
|
|
- type: steps
|
|
bordered: true
|
|
kicker: "How Work Flows"
|
|
headline: "From Idea to Shipped, Without Your Data Leaving Home"
|
|
items:
|
|
- title: "Explore"
|
|
body: "Open a Jupyter notebook and ask questions of your real data through the Organizational Brain."
|
|
- title: "Build"
|
|
body: "Turn the prototype into code. Commit it to Gitea, where every change is tracked."
|
|
- title: "Test"
|
|
body: "CI/CD runs it against a digital twin of your systems, not the real thing."
|
|
- title: "Ship and watch"
|
|
body: "Deploy automatically, then monitor it in Grafana so you know it's behaving."
|
|
|
|
- type: callout
|
|
bordered: true
|
|
tinted: true
|
|
kicker: "In Practice"
|
|
headline: "A Support Assistant, Built In-House"
|
|
text: "A developer prototypes a reply assistant in a notebook, using past FreeScout tickets and the policy pages in Discourse. It goes into Gitea, gets tested against a digital twin, and ships. Now every new ticket arrives with a drafted answer and links to the right documents — and no ticket ever left the company's own install."
|
|
|
|
- type: text
|
|
bordered: true
|
|
kicker: "Where Agents Run"
|
|
headline: "Run What You Build Wherever You Like — Until You Want It Here"
|
|
body: |
|
|
On this path, the AI you build runs where you choose: your own machines, your existing infrastructure, or your model provider of choice. When you're ready to run a whole team of agents next to your data, add the Agent Sandbox to the same install.
|
|
ctas:
|
|
- label: "See the Full Stack →"
|
|
url: "/solutions/full-stack/"
|
|
style: text
|
|
|
|
- type: faq
|
|
bordered: true
|
|
kicker: "Questions"
|
|
headline: "Common Questions About This Path"
|
|
items:
|
|
- q: "Which AI models can I use?"
|
|
a: "The built-in connectors work with Claude, ChatGPT, or a private local model. You choose, and you can change your mind."
|
|
- q: "Will my data be used to train anyone's model?"
|
|
a: "No. Your install is single-tenant and we can't see your data once you change your admin password. Federated learning is opt-in, and even then only encrypted model updates leave your servers — never raw data."
|
|
- q: "Do I need a data team to get value from this?"
|
|
a: "No, but it helps to have at least one person comfortable writing code or working in notebooks. If you'd rather not build, the Open-Source Apps path may fit better for now."
|
|
- q: "Do I need the Agent Sandbox?"
|
|
a: "Not to build. You need it when you want to run many agents at once on Federated's infrastructure, next to your data."
|
|
|
|
- type: final-cta
|
|
dark: true
|
|
headline: "Build AI on your business, not on someone else's cloud."
|
|
body: "Try the apps and the full AI development toolkit free for 7 days."
|
|
ctas:
|
|
- label: "Start 7-Day Free Trial"
|
|
url: "/start-now/"
|
|
style: primary
|
|
- label: "Compare All Four Paths"
|
|
url: "/solutions/#compare"
|
|
style: ghost
|
|
---
|