Zammad

Fewer tickets and faster answers in Zammad

A chatbot answers repeat questions on your website. New tickets get the right Group and priority. Agents see a summary at a glance. Everything runs on your own servers, with the AI model already set up.

  • Chatbot for your website
  • Right Group on arrival
  • Summary in every ticket
  • Runs on your servers
Constanze Krishnaratne

Your host

Constanze Krishnaratne

CEO

Your benefits

What OTAI does for your Zammad team

Your agents keep working in Zammad. OTAI takes over the repetitive part.

Fewer repeat tickets

A chatbot on your website answers simple questions at any hour, with the facts you enter in OTAI Studio.

No sorting by hand

New tickets get the right Group, priority, and tags when they arrive.

Agents get to the point faster

A short summary shows what a ticket is about without reading the whole thread.

Your data stays with you

OTAI runs on your own servers. Ticket text does not leave your network.

ROI estimate

What you can save

Example monthly savings for Zammad teams, net of the OTAI subscription. Open the full calculation to see how the numbers add up.

Small team · 50 tickets/day · 3 Groups

≈ €2,700–€3,000

estimated monthly savings

Mid-size · 200 tickets/day · 10 Groups

≈ €12,600–€13,300

estimated monthly savings

High volume · 750 tickets/day · 40 Groups

≈ €57,000–€58,500

estimated monthly savings

Show the full calculation

What manual routing costs you every month

Four hidden costs — easy to miss, expensive when they stack up.

L1 triage labor

2–4 h/day per L1

Agents read and sort before specialist work starts.

Misrouting & bounce

2× handle time

Wrong Group → tickets ping-pong between teams.

Customer wait time

SLA risk

Hours before the right team sees the ticket.

Repetitive cognitive load

Minutes per ticket

Reading threads, copying fields, re-prioritizing.

Before / after in real life

Concrete situations — not just spreadsheet math.

Lisa

Customer

Without OTAI

Hours waiting for a reply

A password reset lands in the general inbox — Lisa waits most of the day.

4+ hours
With OTAI

Answer in minutes via chatbot

The public chatbot resolves common requests instantly — no ticket needed.

~2 min

Marco

L1 agent

Without OTAI

Sorts every ticket by hand

Sorts 80+ tickets/day by hand — specialist teams still wait hours.

45 min avg. to right team
With OTAI

Routing on arrival

Classification sets Group and priority before Marco even opens the ticket.

Instant

Sandra

Specialist

Without OTAI

Reads long threads herself

Scrolls through 15 emails just to understand the current status.

8–12 min/ticket
With OTAI

Summary on the ticket

Problem, status, and next steps are written back on the ticket.

~30 sec
Pack: Free Cloud Trial

Too low volume

Many routing targets, minimal tickets — Full On-Prem is not yet worth it.

5 tickets/day · 30 Groups

Manual routing€450
With OTAI (total)≈ €200
OTAI subscription (range)€0 (trial)
Remaining handling cost€200

Estimated monthly savings

≈ −€250

per month (net of subscription range)

Agent time saved
≈ 6 h/month
Value of that time
≈ €130 worth

Where the savings come from

  • Group classification

    Direct routing to the right team without L1 triage hops. Main lever for fast handling.

    Faster first handling / shorter cycle

    ≈ €180
  • Priority & other attributes

    Correct priority cuts sorting effort.

    Faster first handling / shorter cycle

    ≈ €40
  • Ticket summaries

    Saves agent reading time, with minor impact on overall cycle time.

    Agent time (not cycle time)

    ≈ €30
  • Answer drafts

    Soon

    Minimal effect at low ticket volumes.

    Not shipped yet — illustrative only

    —
  • Customer chatbot

    Premium · Soon

    Premium pack — stops ticket creation. Needs higher volume.

    Not shipped yet — illustrative only

    —

Subscription costs outweigh savings at 5 tickets/day. The math flips at higher volume.

Pack: Entry

Small team

A lean support team handling a steady daily ticket stream.

50 tickets/day · 3 Groups

Manual routing€4,800
With OTAI (total)≈ €1,800–€2,100
OTAI subscription (range)≈ €500–€800
Remaining handling cost€1,300

Estimated monthly savings

≈ €2,700–€3,000

per month (net of subscription range)

Agent time saved
≈ 40 h/month
Value of that time
≈ €900 worth

Where the savings come from

  • Group classification

    No L1→L2 hopping: The right team starts on intake. Primary savings driver.

    Faster first handling / shorter cycle

    ≈ €2,200
  • Priority & other attributes

    Proper fields reduce mis-prioritization and re-sorting.

    Faster first handling / shorter cycle

    ≈ €400
  • Ticket summaries

    Cuts reading time per ticket for agents.

    Agent time (not cycle time)

    ≈ €350
  • Answer drafts

    Soon

    Review a draft (~30–90s) instead of typing — useful on ~25% of tickets.

    Not shipped yet — illustrative only

    ≈ €250
  • Customer chatbot

    Premium · Soon

    Premium pack only: Prevents simple requests from becoming tickets.

    Not shipped yet — illustrative only

    —

Tickets land with the right team hours earlier — SLAs are easily met.

Pack: Standard

Mid-size

Growing helpdesk routing across multiple specialized teams.

200 tickets/day · 10 Groups

Manual routing€18,500
With OTAI (total)≈ €5,200–€5,900
OTAI subscription (range)≈ €800–€1,500
Remaining handling cost€4,400

Estimated monthly savings

≈ €12,600–€13,300

per month (net of subscription range)

Agent time saved
≈ 160 h/month
Value of that time
≈ €3,500 worth

Where the savings come from

  • Group classification

    Straight to the right team without manual triage — dominant savings lever.

    Faster first handling / shorter cycle

    ≈ €9,500
  • Priority & other attributes

    Proper priority from intake shortens time to meaningful work.

    Faster first handling / shorter cycle

    ≈ €1,800
  • Ticket summaries

    Saves agent reading time across all tickets.

    Agent time (not cycle time)

    ≈ €1,200
  • Answer drafts

    Soon

    Less typing on routine queries (coming soon).

    Not shipped yet — illustrative only

    ≈ €900
  • Customer chatbot

    Premium · Soon

    Premium: Deflects ticket creation. Not included in Standard.

    Not shipped yet — illustrative only

    —

Resolved up to a day faster — Group classification drives most savings.

Pack: Premium

High volume

Heavy ticket load across many targets with complex initial routing.

750 tickets/day · 40 Groups

Manual routing€72,000
With OTAI (total)≈ €13,500–€15,000+
OTAI subscription (range)≈ €1,500–€3,000+
Remaining handling cost€12,000

Estimated monthly savings

≈ €57,000–€58,500

per month (net of subscription range)

Agent time saved
≈ 620 h/month
Value of that time
≈ €14,000 worth

Where the savings come from

  • Group classification

    Eliminates L1 bottlenecks with immediate team assignment.

    Faster first handling / shorter cycle

    ≈ €38,000
  • Priority & other attributes

    Proper priority shortens wait time before work begins.

    Faster first handling / shorter cycle

    ≈ €6,500
  • Ticket summaries

    Saves significant agent reading hours.

    Agent time (not cycle time)

    ≈ €4,000
  • Answer drafts

    Soon

    Review drafts instead of typing — applies to ~25% of tickets (coming soon).

    Not shipped yet — illustrative only

    ≈ €3,500
  • Customer chatbot

    Premium · Soon

    Premium: Deflects common requests so tickets are never created.

    Fewer tickets created

    ≈ €8,000

Direct team routing on intake plus Premium chatbot ticket deflection.

How a ticket reaches the right team

Without OTAIHours of waiting before work begins
  1. Ticket arrives
  2. L1Reads & triages manually
  3. Moved to a Group
  4. L2/L3Bounced if misrouted
  5. Right team starts
With OTAIInstant routing — no triage backlog
  1. Ticket arrives
  2. AIClassifies target + priority
  3. L1/L2/L3Assigned directly to the right team
  4. Team starts immediately

More ways OTAI saves cost

Group classification drives cycle-time savings. Other features save agent time or deflect tickets.

Ticket summaries

Summarizes long email threads instantly. Reduces agent reading time.

From Entry · available now

Typical savingLess read time per ticket
Coming soon

Answer drafts for agents

Review and send drafts instead of typing. Speeds up responses.

Depends on pack

Typical savingFaster replies, less typing
Coming soon

Customer chatbot

Answers common questions directly to deflect ticket creation.

Premium pack only

Typical savingFewer tickets created

Illustrative examples for European support teams. Subscription figures are ranges (Full On-Prem from ~€500/month depending on agents + pack) — not a fixed price list. Manual costs cover triage, wait time, and misrouting. Chatbot and answer drafts are coming soon.

Features

Every feature in Zammad

Every feature, what it gives you, and how it looks.

A chatbot for your website

Zammad AI has no chatbot. Zammad Chat only connects a customer to your agents and sends no automatic answer. OTAI adds a chatbot to your website. It answers with the facts you enter in OTAI Studio.

Your benefit: Customers get an answer to simple questions at any hour, without waiting for an agent.

OTAI Studio: public chatbot with the code to add it to a website

Model already running

On-prem Zammad AI needs Ollama installed and a model downloaded and loaded. OTAI ships with the model already running on your GPU.

Your benefit: You start with on-prem AI right away. There is no separate model project.

OTAI Studio dashboard right after setup

All AI settings in OTAI Studio

One screen shows which AI agents run, on which tickets, and what they write back.

Your benefit: Your team changes the setup itself. No code and no config files.

OTAI Studio: list of active AI agents

Set the Zammad Group

OTAI reads each new ticket and sets the right Group. It uses your Group names and the descriptions you add in Studio. No ticket history is needed.

Your benefit: Tickets reach the right team without anyone sorting them by hand.

OTAI Studio: values and descriptions the AI uses to pick the team

Priority and tags

OTAI sets the priority from what the customer writes and adds matching tags.

Your benefit: Urgent tickets stand out at once, and tags stay consistent for reports.

OTAI Studio: priority agent with its values

Fill your own fields

OTAI fills your Zammad object attributes, such as department or product, with values from your list.

Your benefit: Triggers and reports work with clean values instead of empty fields.

OTAI Studio: agent that fills a custom field

Ticket summary

OTAI writes a short summary of the ticket into a Zammad object attribute.

Your benefit: Agents see what a ticket is about without reading the whole thread.

OTAI Studio: ticket summary agent

Screenshots show OTAI Studio connected to Znuny. With Zammad you use the same Studio.

Comparison

Why OTAI and not just Zammad AI?

Zammad 7 brings its own AI features for agents. Here is where OTAI goes further.

Answers for customers

Zammad AI: No chatbot. Zammad Chat connects a visitor to an agent and sends no automatic answer.

Open Ticket AI: A chatbot on your website answers simple questions on its own.

AI model

Zammad AI: You bring the model. On your own servers, you install Ollama and load a model yourself.

Open Ticket AI: The model comes with OTAI and is already running.

Where ticket text goes

Zammad AI: With a hosted provider such as OpenAI, ticket text is sent to that provider.

Open Ticket AI: Ticket text stays on your servers.

Switching it on

Zammad AI: Each AI agent runs only when a trigger, macro, or scheduler job calls it.

Open Ticket AI: Switch it on in OTAI Studio, and it works on every new ticket.

Updates and support

Zammad AI: If you run the model yourself, you keep it running and up to date.

Open Ticket AI: Model updates and support are part of OTAI.

Sources: Zammad AI providers · Zammad AI agents · Zammad Chat

Quick Start

Common Zammad Setups

What a typical rollout looks like. We map your Groups in Studio; Runtime classifies new tickets and writes group, priority, and tags back to Zammad.

IT Helpdesk

  • Ticket: “VPN to the office is down”
  • Writes Group: Network
  • Sets Priority: 3 and tags: outage, vpn
  • Same pattern for hardware, software, and access tickets

Customer Service

  • Ticket: “I was charged twice on my invoice”
  • Writes Group: Billing
  • Sets Priority: 2 and tags: invoice, duplicate-charge
  • Same pattern for returns, shipping, and product questions

Municipal Services

  • Ticket: “Pothole on Main Street near the school”
  • Writes Group: Infrastructure
  • Sets Priority: 3 and tags: roads, public-works
  • Same pattern for permits, registrations, and public safety
How it works

Go live with Zammad

Connect the helpdesk, describe your setup in Studio, classify tickets zero-shot, run Full On-Prem.

01

Skip the model setup

02

Connect Zammad

03

Set it in Studio

04

Run on your GPU

  1. 01

    Skip the model setup

    The model is already running. You do not install Ollama or load a model.

  2. 02

    Connect Zammad

    Connect with an API token. Your groups come from Zammad.

  3. 03

    Set it in Studio

    Turn on the group, the priority, the chatbot, and summaries. No separate model step.

  4. 04

    Run on your GPU

    The same kind of GPU you would buy for Zammad. Results are written back into the ticket.

On-Prem Classification

Classify Ticket Fields on Your Infrastructure

Full On-Prem AI runs inside your network to set queues, groups, priorities, and custom fields securely.

Full On-Prem Path

Your Infrastructure (On-Prem)
GPU required
OTAI Studio

On-prem configuration and control in your environment

Zammad

New tickets arrive for AI processing

OTAI Runtime + Connector

Local classification on your GPU — air-gap ready

Tickets Enriched by AI

Routing, priority, and custom fields updated automatically

No ticket data leaves your network. Everything runs on your infrastructure.

AI Capabilities

Fields AI Can Improve in Zammad

Group

Group Assignment

Priority

Priority Classification

State

Status Prediction

Tag

Auto-Tagging

Object Attribute

Custom Field Population

Requirements

Zammad 6.0+ (self-hosted or managed)
Docker / Docker Compose for OTAI Runtime
API access with admin token
2 CPU cores, 4 GB RAM minimum
GPU with 24 GB+ VRAM for Full On-Prem production
Start with the Free Cloud Trial if GPU hardware is not yet available
Pricing

Editions

Free Cloud Trial to evaluate. Full On-Prem quotes based on agents and tier.

Free Cloud Trial

One month · full features

Free
  • One month
  • Full features on a sample ticket system and OTAI Studio
  • Rate limit and a total usage cap
  • No GPU on your side
One month

Full On-Prem

On request · agent-based software

From ~€500 / month
  • Studio and Runtime on your infrastructure
  • Chatbot, classification, summaries, and AI workflows
  • Flexible agent licensing: Entry, Standard, or Premium
  • Includes updates, security patches, and support
  • Run on existing hardware or partner hardware
View Product
FAQ

Frequently Asked Questions

Questions about using OTAI with Zammad.

Zammad's own AI needs a provider. On-prem, that means you install Ollama and load a model. Zammad's install notes say a production model server is a complex stack, and the bundled Ollama add-on is for testing.

OTAI arrives with the model running. You connect Zammad and set your groups in OTAI Studio.

You still buy a GPU. Zammad on-prem needs one too. The difference is that you do not build the model server yourself.

OTAI also brings a chatbot for your website. Zammad AI has none: Zammad Chat connects a visitor to an agent and sends no automatic answer.

OTAI then sets the group, the priority, and other fields, and it writes a short ticket summary.

Ready to automate classification
for Zammad?

Automate ticket classification on-premise using your existing Group setup.

Constanze Krishnaratne

Your host

Constanze Krishnaratne

CEO