Skip to content
SSyntalith
PLEN
Book a review

Blog · Published · Updated

AI in customer service: return, complaint or cancellation?

Short answer

AI in customer service first identifies the type of case: withdrawal from the contract, a complaint, or a cancellation on the terms of the offer. The word „refund” is not enough. The deadlines and the reply depend on the type, and the first test runs with no automatic refusals. At Syntalith the automation costs from €3,000 net, and with 800 requests a month at 6 minutes each it pays back in 1.6 months.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000
Book a free process review (30 min)

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Customer service and AI: statistics 2026

1.6 mo.

payback of a €3,000 automation at 800 requests a month: €2,792 of work today, €857 with checking and the model. Scenario.

Figures checked: 22 October 2026

The same refund, three different cases

One online shop customer wants to send a product back because they changed their mind. Another reports a defect. A hotel guest wants to cancel a future stay. Each writes „please refund me”, and each case has different rules. UOKiK, the Polish consumer authority, describes the 14-day withdrawal period for online purchases and the exceptions to that right, among them accommodation services for a set date.

No right of withdrawal does not close a complaint. The European Consumer Centre in Poland describes a complaint about accommodation that does not match the offer. A guest writes that they got a different room from the one booked and asks for part of the price back. The bot replies „non-refundable booking”. That is a classification error: this is a complaint, and the cancellation terms do not settle it.

Type of requestThe question that sorts itWhat not to assume
Withdrawalwhat type of contract it is and which dates matterthat every contract gives the same right
Complaintwhat does not match the contract or the offerthat the cancellation terms settle it
Cancellationwhich terms apply to this offerthat no free cancellation closes other claims
What goes on the case card
  • The customer's request in their own words
  • The type of contract established and the linked order or booking
  • The version of the terms that applied to this transaction
  • A message with several requests split into separate cases

The offer page available today may differ from the terms of the service bought. When the company has not kept the right version, that is a gap to clarify, and the model does not present today's terms as the ones that applied on the day of purchase.

What AI handling of returns and complaints costs and when it pays back

Scenario: 800 requests a month
Today
800 requests × 6 min = 80 h (€2,792)
With the system, a person checks the output in 30% of the time
€838
Model, 2 calls per case, Claude Sonnet 5.5
€19
Cost of one case
€3.49 today, €1.07 with the system
Saving
€1,935 a month

Payback of €3,000

1.6 months

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 4,000 input tokens and 500 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.

The count covers the work around each case: searching, reading, writing and handing over. What remains is the time to check the result, 30% of today's work in the scenario. Before the quote we measure both times on 20 to 100 cases the team has already handled, in a free test that takes 5 working days.

Run the first test with no automatic refusals

Start by assigning a category and the material for assessment, with no refusals sent. Add to the test set messages where the customer does not know the name of the right, combines several requests or writes about a date that differs from the one in the system. Measure the number of changed categories, corrected drafts and the time of the whole case. A shorter time to first reply saves nothing if the customer has to write a second time. The person responsible for customer service approves the deadline rules and reply templates with a lawyer.

What to choose in customer service

  • A few dozen requests a month

    templates for the three types of case

    no build

  • A shop with a returns module

    the platform's features and team training

    from €1,150

  • Hundreds of requests, a shop and services, several contract types

    an automation of classification and drafts

    from €3,000

Where to start

The first scope covers classification and drafts for one channel, with no automatic refusals. We build this kind of system as part of our AI automations. For the free process review, a description of one case from the last few weeks and the tools it went through is enough. You do not need to send confidential documents, and you receive a written plan within 2 working days.

Worked example · Scenario

How we count the payback: AI in customer service

We run the same count for your requests in the free process review.

€5,817

a month for answering 2,000 customer emails

Payback: 0.6 mo.

5 minutes to read an email and write a reply and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: Claude Sonnet 5.5, about 3,000 + 600 tokens per message with a draft reply, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

Start with the process that takes the most time each week.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 21, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

Private AI models →

Source: OpenAI, training on data from private accounts ↗ · OpenAI, who sees conversations ↗ · Anthropic, changes for private accounts (August 2025) ↗ · OpenAI, data in API ↗ · AWS Bedrock, EU profile ↗

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI implementation

Start with the process that takes the most time each week.

The engineer chooses one process with you and calculates how much it costs today. Then we build a free prototype on 20-100 cases that your team has already handled. We write down the goal and the fixed price in the contract.

See AI implementation →
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000
Book a free process review (30 min)

or call+48 888 78 48 78WhatsAppMon–Fri 9:00–17:00 CET

Questions

  • How does AI tell a return from a complaint?

    It asks about the type of contract, the reason and what the customer expects, and compares them with the order or booking. The word „refund” is not enough, because it can mean withdrawal, a complaint or a cancellation.

  • Does a non-refundable booking rule out a complaint?

    No. According to the European Consumer Centre in Poland, a guest can complain about accommodation that does not match the offer. Cancellation terms cover giving up the stay, and a complaint covers how the service was delivered.

  • How much does such an automation cost?

    At Syntalith from €3,000 net. With 800 requests a month at 6 minutes each, the payback is 1.6 months. We agree integrations and maintenance before the quote, and the model costs €19 a month.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Write
contact@syntalith.ai
Call
+48 888 78 48 78
WhatsApp
write on WhatsApp

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
You buy accounts directly from OpenAI or Anthropic and receive an invoice from them. We do not add anything to the license.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.