Skip to content

Blog · Published · Updated

AI in automotive: service request intake

Short answer

AI in a car workshop orders a client's request before it reaches the service adviser: the description of the symptom, the conditions the client gives and the information still to collect. It does not diagnose the fault or judge whether the vehicle is safe to drive. The workshop sets the rules for requests that concern safety.

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

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

Automotive and AI: statistics 2026

2.3 mo.

payback of €3,000 at 800 requests a month: €1,861 of work today, €563 with checking and the model. Scenario.

Figures checked: 22 October 2026

A request ready for the adviser
  • The symptom in the client's words
  • When and in what conditions it occurs
  • Information to fill in during the conversation
  • Safety-related requests handled by the workshop's rules

A symptom is no name of a damaged part

In a fictional request, the client writes: „sometimes I hear a knocking after pulling away, then it stops”. A draft that names a specific part and the cost of replacing it adds a diagnosis that nobody has confirmed. The adviser needs the original description and questions about the circumstances.

A possible note says that, according to the client, the symptom appears after pulling away and does not always come back. Further details are missing. It is material for a conversation, with no repair instructions. The workshop sets the rules for handling requests that concern safety. A language model does not decide them.

A form can remove some of the gaps

First check the current form and the workshop's management system. Fields for the case identifier, the vehicle details and the contact can cut retyping. AI makes more sense where the client describes the situation in free text or sends several messages.

The result should point back to those messages. During a correction, keep a record of who changed the description and why. If the client sends a new detail, do not create a second request automatically only because the message came through another channel. The rule for merging cases has to be agreed with the team.

What should the first trial show?

Prepare a fictional request with an incomplete description, a follow-up to the same case and a similar description about another vehicle. The adviser checks the correct assignment, that the client's words were kept and the questions that need a further conversation. A confident-sounding diagnosis that is not in the material is a serious error.

Assess the review time separately. If the ordered note means rereading all the messages, fix the references or narrow the scope. This is a proposed acceptance trial; we present no rollout in a workshop and no result of a model test.

The next stage of the adviser's work is described in the AI offer for workshops: preparing material for a quote and linking the client's answer to the right version of the estimate. It is a proposed administrative scope, with no diagnosis of the vehicle.

When should you order an automation?

With a few requests a day, a template and the adviser's way of working may be enough. Connecting the mailbox with the workshop system is worth considering when the same material is retyped again and again and the assignment rules are already known.

Syntalith can build request handling automation. The service price levels are on the pricing page. The first scope can be limited to preparing a note for approval. Connecting to the workshop software and saving changes require the available interfaces to be confirmed. Searching manuals is a further, separate topic, described in the post on a knowledge base for multi-brand service. For the first call, a description of the path of a request from the client to the adviser is enough.

What it costs

Scenario: 800 requests a month
Today
800 requests × 4 min = 53.3 h (€1,861)
With the system, a person checks the result in 30% of the time
€558
Model, 1 call per case, Claude Sonnet 5.5
€5
Cost of one case
€2.33 today, €0.70 with the system
Saving
€1,298 a month

Payback of €3,000

2.3 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: 2,000 input tokens and 300 output tokens per call at Anthropic's rates, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

What we measure in the trial
  • The time from receiving a case to the result, before and after the change
  • Cases the application passed to a person
  • Corrections by the person checking
  • The cost of the model and maintenance at the target volume

Where to start

In the free review we choose one process and count the volume and the team's working time, and within 2 working days you receive a written summary with a price. We build the automation as part of AI automations, from €3,000 net.

Worked example · Scenario

How we count the payback: service requests

We run the same count for your workshop in the free review.

€2,327

a month for preparing 200 first repair estimates

Payback: 1.5 mo.

20 minutes for a first repair estimate 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: reading the enquiry in our quoting system (about €0.0008) plus pricing the lines (Claude Sonnet 5.5, about 4,000 + 1,500 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026. The extra margin is a scenario: we assume 1 in 20 estimates sent the same day ends in an order that a slow reply loses today, with a margin of €92. In the review we count it on your sales process.

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.

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

Questions

  • How does AI help with service request intake?

    It orders the client's description into the symptom, the conditions in which it occurs and the gaps to fill, so the adviser has material for the conversation before the visit.

  • Can AI diagnose a car fault from the request?

    No. A symptom is no name of a damaged part, and the workshop assesses the fault and the safety of the vehicle.

  • How much does it cost?

    At Syntalith, AI apps, automations and agents start from €3,000 net. At 800 requests a month and 4 minutes each, the payback is 2.3 months.

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.

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.