AmyAI does the work.
You stay in control.
Many teams start with AI tools and home-built apps that nobody controls. Amy starts with your processes: together you map who does what, which rules apply and where a person decides. Then Amy automates the routine in your team’s everyday work – using only the AI models you approve. Every step stays traceable.
- Local and European AI models
- Connect your own database
- Built in the EU, GDPR by design
From quote to order
Illustrative example- Quote received
Lena submitted the document.
- Amy checks the details
Items captured. Budget available.
- Jonas decidesJonas approved
Orders over €2,500 need approval.
- Place the orderOrder PO-089 placed
Waiting for approval.
Amy recorded the order in the purchasing system.
A human decision releases the next step.
The rules for this process
- AI model
- Allowed under the deployment’s model policy
- Access
- Read the quote, check the budget, place the order after approval
- Human decision
- Jonas approves orders over €2,500.
- Connection
- The existing purchasing system, through its configured API
What happened so far
- Quote submittedLena · 14 items, €4,800
- Checks completedAmy · the budget covers it
- Approval requestedJonas · required by the amount limit
- Order approvedJonas · decision recorded
- Order placedAmy · PO-089 in the purchasing system
Approved by Jonas. Order PO-089 placed. Both steps are recorded in History.
Companies we work with
- IT-Kompass
- Daredo
Stop depending on what only a few people know.
Amy turns experience into clear processes.
You tell Amy how the work runs today – in your own words, no forms, no drawing tool. Amy asks until every step, every exception and every decision is clear. What only a few people knew is now visible to everyone.
It becomes a model your whole team can read.
Amy maps who does what, what each step needs and which system is involved. Your team reviews the model and changes it in conversation until it’s right. Only then is anything automated – exactly what you approved.
-
Explain it. Amy draws it.
The person who knows the work can explain it without drawing a diagram. Amy connects the people, steps and rules in trees and charts the team can review.
-
Find the missing decisions
Amy checks how the parts connect, helping you spot gaps, conflicting rules and unclear handoffs. Work through the exceptions before handing the task to AI.
-
Own the model. Evolve it together.
Your company owns this living model in the open AIM standard. Review it with the people who know the work, use it to guide AI, and evolve it as your business changes.
Who has access?
Which AI? Whose decision?
These questions belong in every AI rollout from the start. You set the boundaries, and Amy checks every action against them before it changes anything.
“Which AI is our team using?”
Provider and model are always visible. You allow or block models, local ones included.
“Who can see and do what?”
Everyone gets exactly the apps and processes of their role. Those who build the model are kept apart from those who use it day to day.
“Will AI just decide on its own?”
No. Where your rule requires approval, Amy prepares the decision and waits. Data changes outside the model are rejected.
“Can we see activity and cost?”
Every step is in the history. Model calls, usage and estimated cost are visible per person and model.
One process at a time. In the end, your whole organization.
Departments, processes, software and projects connect in one model. When a rule changes, Amy shows which processes are affected. So you automate step by step without losing the overview.
Explore example modelsYour AI. Your data.
Keep your process knowledge, operational data and files under your own control. You decide where AI runs and where your data lives.
You choose the AI models.
Models in German and European data centers, or local open-weight models on your own infrastructure, connected through vLLM, Ollama or an OpenAI-compatible API. You decide which providers your team may use.
Your own database.
Connect your own PostgreSQL database for app and process data, and your S3-compatible storage for documents, attachments and exports.
Built in the EU.
Built and operated in the EU by Juice d.o.o., hosted in Frankfurt. GDPR by design and European legal standards from day one.
Works with
- Claude
- Gemini
- OpenAI
- Ollama
- vLLM
- PostgreSQL
- S3
- MCP
- BPMN 2.0
Where shall we begin?
Pick a process your team knows well. Amy maps it with you. Automate when you’re ready.
Tell Amy how your team works→