Skip to content
CV
WorkzAIn8 min read01 · Overview

Product Design Case Study · AI assistant · Human-in-the-loop

An AI assistant that brings the context.

zAIn is the AI assistant in zvoove One. It reads operational data straight from the ERP and answers in natural language. I designed the vision, the UX concept and the whole chat experience.

zvoove · staffing software · 2025 – 2026 · 8 min read

Role in the project
Concept & experiencezvoove Germany
Team
PM, AI lead, production engineeringPM: scope and phase model · AI lead: RAG and technology
Responsibility
Vision to chat UINorth star, UX concept, prompting, confirmation and reflection cards, messaging
As of September 2026
Live since 10 Aug 2026+3

As of September 2026

  • Live

    Since 10 Aug 2026: GA v1 for existing and new cloud customers

  • Read-only

    106 of 154 endpoints released, writing only on test and staging data

  • Test round

    16 customers, August 2026

  • Open

    Productive write access: legal review open

and 3 more states
As of September 2026
Live+3

As of September 2026

  • Live

    Since 10 Aug 2026: GA v1 for existing and new cloud customers

  • Read-only

    106 of 154 endpoints released, writing only on test and staging data

  • Test round

    16 customers, August 2026

  • Open

    Productive write access: legal review open

At first, an agent answered by percentage. zAIn is not a chat window waiting for questions but an assistant with context and clear limits. What was designed was the behaviour, not just the interface.

zAIn

At a glance

  • 16 customers

    in the August 2026 test round

    16 customersin the August 2026 test roundGA v1 since 10 Aug 2026 for existing and new cloud customers
  • 106 of 154

    endpoints released, read-only

    106 of 154endpoints released, read-onlyWriting only on test and staging data
  • 5 decisions

    from early agent to an assistant with context

    5 decisionsfrom early agent to an assistant with contextThe five decisions from “At a glance”
  1. Problem

    The first agent answered by percentage

    An early chat above the old Launchpad: confidence decided which tier answered.

  2. Intervention

    The behaviour is designed, not just the surface

    Chat experience, the three-layer pattern and a handbook of rules for AI behaviour.

  3. Outcome

    Live since August 2026, read-only and bounded

    106 of 154 endpoints released for reading, writing only on test and staging data.

Role in the project
Concept & experiencezvoove Germany
Team
PM, AI lead, production engineeringPM: scope and phase model · AI lead: RAG and technology
Responsibility
Vision to chat UINorth star, UX concept, prompting, confirmation and reflection cards, messaging
02 · From agent to navigator

The first agent answered by percentage.

zAIn was first called zvoove Assistant. The PM lead, the tech lead and I had the idea independently of each other; we got it started together. I set up the initiative team, connected the design to UnityUI, built the first proof and connected the knowledge base via MCP, tested internally first, including as an assistant for customer support.

Before the launchpad there was an early “zvoove Agent”: a chat window over the old launchpad, with a greeting, quick actions and a visible confidence level.

Early prototype of the zvoove Agent with quick actions and a confidence badge
Early prototype: the “zvoove Agent” in the old launchpad, with answer level and confidence (“L1 · 75%”).

Behind it sat a level model: confidence decided which level answers, from a direct answer to a handover to support.

Answer levels and routing · early agent
  1. L0

    System and context

    Entry, orientation, setting expectations.

    greeting, quick replies
  2. L1

    Known knowledge

    Answers known topics directly.

    confidence ≥ 0.8
  3. L2

    Clarification

    Resolves ambiguous input with a follow-up question.

    confidence 0.5–0.8
  4. L3

    Generative

    AI-generated help with a disclaimer when confidence is low.

    confidence 0.2–0.5
  5. L4

    Handover

    Handover to support or a human for unknown topics or repeated failures.

    < 0.2 or 2–3 failures

Two things came of it later: the percentage left the interface in favour of interpretable uncertainty, and the chat got clearly separated jobs next to notifications and structured UI. The flagship case covers both.

The PM and I prioritised which cases zAIn had to handle first in around 20 qualitative interviews. In July 2026, customer tests at the innovation roundtable followed.

zAIn: this could become a powerful tool.

Customer at the innovation roundtable, July 2026 · translated from German
03 · Chat experience

Every answer gets a form that fits it.

I designed the complete chat UI and UX: the thinking state, the messages and display patterns for the whole range of answers, from rich text through tables and cards to images and video.

Answer formsExamples · synthetic data

Text

zAInOrders · Cologne
  1. How many orders are open in Cologne right now?A
  2. There are 12 orders open in Cologne, 3 of them start this week.
Write a message …

Table

zAInDispatch
  1. Who is available as a forklift driver next week?A
  2. Three employees match the request:

    Available · forklift licence

    J. WeberForklift licencefrom Mon
    A. YilmazForklift licencefrom Tue
    M. NowakForklift licencefrom Wed
Write a message …

Card

zAInAssignments
  1. Show me Jonas Weber’s current assignment.A
  2. Here is the assignment:

    Assignment · Jonas Weber

    Customer
    Nordhafen Logistik GmbH
    Period
    15–30 Sep 2026
    Shift
    Early, 6 am–2 pm
    Status
    confirmed

    Open in the ERP

Write a message …

Video

zAInHelp
  1. How do I create a new customer?A
  2. There is a short video from the zvoove Academy for that:

    Create a new customer2:40

Write a message …

On top came confirmation and reflection cards, the prompting and the messaging script: how zAIn speaks and how it offers next steps.

Assistant in the context of a product view with suggested next steps
Assistant in context: zAIn recognises where someone works and suggests fitting next steps.
Notification center handing a case to zAIn
Handover from the notification center, live: the case arrives at the assistant as a prepared prompt.

When zAIn is meant to act, the three-layer pattern separates what it understood, what it intends to do and what came out. Briefly in the flagship case, in depth in the UWX case.

Three-layer pattern
  1. Message

    Understand

    What zAIn understood becomes visible before it plans anything.

  2. Intent

    Plan

    The steps are shown before they run; for write actions, approval sits here.

    approval
  3. Result

    Result

    The result stays attached to the case and traceable.

04 · Rules, not gut feeling

A handbook makes AI behaviour testable.

So that product, design, engineering and AI build the same behaviour, I set up the AI Assistant Handbook, an internal playbook (as of February 2026).

Four layers
  1. System

    Hard limits no one overrides.

  2. AI logic

    How zAIn reasons and decides.

  3. Interaction

    Tone and structure of the conversation.

  4. UI

    The visible presentation.

Higher layers constrain lower ones: if the system blocks a request, the UI shows no “try anyway” button.

Every behaviour is written as a rule card: trigger, rule, rationale, example. If a dataset holds more than 500 items, for instance, it is not rendered in full. On top come patterns for recurring situations, such as ambiguity: two or three clear readings as a choice, more than three as a follow-up question. And a catalogue of edge cases, each mapped to its layers.

Rule cardPattern · ambiguity
Trigger

An input allows more than one reading.

Rule

Two or three clear readings as a choice, more than three as a follow-up question.

Example

Two readings, so a choice.

  1. Show me the open orders for Müller.A
  2. Do you mean one of these customers?
    Müller LogistikMüller Bau
AI Assistant Handbook, page “How to Use This Handbook”
One handbook for every role: what product, design, engineering, AI and management need from it.
AI Assistant Handbook, page “Edge Cases & Exceptions”
Edge cases mapped to the layers, such as conflicting filters or permission boundaries.

I built the AI Assistant Handbook on my own in Figma Make in February 2026; it became the AI Product Playbook.

Learning

A handbook for AI behaviour is a design system for decisions. It is meant to save the discussion that would otherwise start over in every feature.

05 · Limits

What zAIn cannot do is designed.

At GA, zAIn reads only: 106 of the 154 classified endpoints are released, and write actions run on test and staging data only. The legal review for productive writes into the ERP is still open (as of September 2026).

Three deliberate limits
  1. Refuse honestly instead of hallucinating

    v1 deliberately refuses analyses across the whole tenant, because without a search index the answers would be unchecked.

  2. Sensitive data technically out of reach

    Salaries, invoices, bank details and reasons for sickness are out of reach in v1, not just hidden. For this I built the three-layer pattern to GDPR rules.

  3. Visibility over convenience

    Queries across branches without an explicit visibility check were stopped in the test round.

Declining honestlyExample · synthetic data
zAInReports
  1. Which customer had the most assignment hours last quarter?A
  2. I cannot answer that reliably in this version yet: reports across the whole tenant need a search index that does not exist yet.
  3. I can show you the assignment hours for a single customer.
    Choose a customer
Write a message …

The limits follow the autonomy boundary: read before prepare before change.

06 · After launch

Measured honestly after launch.

After go-live, the team and I analysed the conversations of the first weeks: recorded prompts, thumbs ratings and free-text feedback. We classified every prompt by whether zAIn answered, asked back or blocked.

07 · Outcome

What is live and what stays open

Go-live, GA v1existing and new cloud customers
10 Aug 2026
Endpoints released for readingof 154 classified
106
First test roundAugust 2026
16 customers

What stays open

  1. Write actions in the real system

    Productive writes need the legal sign-off and the human gate in operation.

  2. Analyses across the whole tenant

    Need a search index before zAIn may answer them.

  3. The fixable mechanics

    The next iterations follow from the post-launch analysis.

fin (for now)

CV · Maximilian Dahl
In plain words

What do you actually do, Max?

My parents and family have nothing to do with tech or my profession. They told me they did not understand my website. This is for them. And for anyone who would like an explanation without the jargon.

I make software easier to work with.

When someone spends ages searching for a button or has to enter the same information three times, I want to know why. I watch how people work, talk to them and design a better way through the task. Then we try it together.

My title is Principal Designer. That means I also make decisions about how whole products fit together and help the team build on them. I still design and write code myself.

Here is a simple example.

At zvoove, I designed an assistant called zAIn. This simplified example shows the idea:

  1. Someone asks

    “How much holiday do I have left?”

  2. The assistant looks it up

    It finds the information and explains the answer.

  3. The person decides

    If they want to book time off, they review the details before anything is sent.

My job is to work out what people need to see, how the answer should be explained and when the program needs their approval.

A design system is a bit like LEGO.

Imagine every team inventing its own bricks. Nothing fits. With a shared kit, the pieces connect, even when people build different things.

Shared pieces. Different things you can build.
Book time offReview an invoice

In software, those pieces are things like buttons, input fields and messages, plus rules for how they work together. I built this kind of kit at Container xChange. It is called Compass.

What has come out of my work?

One starting point
At zvoove, I designed the shared starting point for several programs and tried it out in code. It became Launchpad, which has been live since August 2026.
Built, too
I built the visible part of the notification centre myself. A backend engineer built the part behind it, and we shipped it together.
A team that can build on the work
At Container xChange, I grew the design team from 4 to 14 together with Niclas. Compass gave designers and developers a shared kit to work with.

What am I particularly good at?

I look beyond the screen in front of me. When several teams run into the same problem, I look for a solution they can share. That is how Compass came about.

And I like making an idea tangible early. I can build a working version myself, put it in front of someone and find out where it falls short. I would rather learn that from using it than from a long discussion about a picture.

What would I like to do next?

I want to help decide what a product should become, support a team and keep building myself. I am looking for a role as a Principal Designer, Team Lead or AI Product Builder, in a team that builds with artificial intelligence.

In plain words: I want to take responsibility for the whole thing, without giving up the part I enjoy most — trying things out and making them work.