Blog · Published · Updated
How to choose AI for a doctor's work with text
Short answer
Choosing AI for a doctor starts with the task. Drafting an organisational instruction and supporting a clinical decision need different evidence and assessment. This guide covers administrative text: what the user assesses, which errors change the meaning and why the first exercise needs no patient data.
- net for implementation for a team of up to 10 people, paid once
- from €1,150
- from start to work of the entire team
- 2 weeks
- after this time, we measure the effect on the same tasks
- 30 days
- conversation with an engineer and a written plan within 2 business days
- €0
We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓
Author: Syntalith · 3 min read
Statistics
Healthcare text and AI: statistics 2026
0.9 mo.
payback of a €1,150 training day for 10 people saving 1 hour a week each: €1,511 of time recovered against €178 of licences a month. Scenario.
40%
According to a study published in Science (2023), ChatGPT cut the time 453 professionals spent on writing tasks by 40%.
Source: Noy and Zhang, Science (2023) ↗
48.8%
According to Eurostat (2025), 48.8% of EU companies that considered AI but did not use it named concerns about data protection and privacy.
52.5%
According to Eurostat (2025), 52.5% of EU companies that considered AI but did not use it named a lack of clarity about the legal consequences.
32.7%
According to Eurostat (2025), 32.7% of people aged 16 to 74 in the EU used generative AI tools in the previous 3 months.
Figures checked: 22 October 2026
- A missed condition or exception
- A changed number, date or unit
- Information added from outside the source
- A confident tone over uncertain content
Decide what the user is to assess
A sample task could be shortening an approved organisational instruction for staff. The author checks whether the draft kept the order of steps, the conditions and the contact person. A fictional text with no patient history is enough for the first trial.
Suppose that in such a text changing an appointment requires confirmation by the front desk. A draft saying „you can change the appointment yourself” removes the condition. The error can appear in a fluent, short sentence. So judge whether each point matches the source first, and readability only after that.
Caution also applies to convincing text
WHO describes the risk of false, incomplete and biased answers from generative AI, and of users trusting automation too much. It recommends defining tasks and involving the people the tool affects. WHO guidance, checked on 9 October 2026.
So a comparison of two products should use the same materials and the same expected result. Do not judge answers by their confident tone or by a vendor's promise that the tool „understands medicine”. A clinical use needs its own assessment of the intended purpose and the evidence required.
Record the errors that change the meaning
| Part of the text | What to check |
|---|---|
| The condition for a step | Whether the summary kept it |
| The person responsible | Whether the model added a different role |
| A date or an order | Whether the result matches the source |
| Missing information | Whether it stayed visible |
For each correction, note the reason. Editing time is part of the cost of use. If a draft means rebuilding the whole instruction, fast generation matters little. This is a proposed assessment; we have not run a product comparison.
Once you have chosen the task, the plan for a first AI trial in a medical clinic helps. It describes responsibility for sources and the data flow before the tool is shared with staff.
Patient data is not needed for the first exercise
Before real documents are used, the clinic has to assess the purpose, the scope of the data, the tool's terms and access. The EDPB names health data as a special category that needs extra protection. EDPB guide, checked on 9 October 2026. Removing a name alone does not settle whether the person can no longer be identified.
Syntalith can agree team training that covers preparing the material, assessing the draft and improving the prompt. The process review at Syntalith is free, automations, apps and agents start from €3,000 net, and team training from €1,150 net a day (pricing). The clinic brings knowledge of its workflow and approves the tool and the materials. The service does not include clinical validation or certification of a medical device.
If the problem is finding the current instruction, the scope of a knowledge base for clinic administration is closer. Start the conversation with a text that staff regularly correct, and with who can approve its content.
What it costs
- Time saved
- 10 people × 1 h a week × 4.33 = 43.3 h
- Value of that time
- €1,511
- Licences
- $200 (€178)
- Left after licences
- €1,333 a month
Payback of a €1,150 training day
0.9 months
The hours saved are the scenario's assumption, which we check by timing tasks before the training and after 30 days. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Claude Team seats at $20 per person a month, at the ECB rate of 1.1205 USD per euro on 22 October 2026.
- The time of the task before the training and after 30 days
- The corrections made by the person checking the result
- Tasks where a participant still needs help
- Licences and tools cleared for work
Where to start
We run the workshop as part of team training, from €1,150 net a day. For the free review, a description of one task the team does every week and the tools it uses is enough. You receive the written training programme within 2 working days.
„I already use AI.”
Your people too. Just no rules.
From our conversations with companies
5 na 10 employees paste sensitive data into private AI accounts: contracts, invoices, customer data.
In ESET survey (2026)
1 na 10 admits this in the survey.
Customer data pasted into a private AI account without an data processing agreement is a violation of the GDPR.
Don't worry, we won't tell anyone :)
What do we see in companies that "already use"
- Only ChatGPT or Claude accounts, without plugins, skills, integrations and MCP servers with company tools.
- Company programs are not connected to AI. People still click through systems and Excel, and enter chat data manually.
- Lack of company standards: everyone writes instructions in their own way, no one shares what works.
- No rules for personal data, GDPR and company secrets.
- No limits and no visibility: no one knows who uses AI, how much and for what.
62% Polish employees use AI at work · 27% companies have written rules for working with AI.
Source: ESET and DAGMA, Cyberportrait of Polish business 2026 (March 2026, 1,026 people) ↗
ChatGPT or Claude space review
Accounts, permissions, rules for working with data and 5 tasks set for the team. 1 day.
€450 net
Company accounts, rules of working with data and team training in 2 weeks, from €1,150 net.View implementation for the team →
„Is my data safe?”
Yes. You choose where they go: from your company account to the model on your server.
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.
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.
02API with zero retention (ZDR)
The provider processes the request and does not save anything. It requires his consent, we prepare the application together.
03Processing in the EU
Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.
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 Your examples
- 2 tuning
- 3 test on new cases
- 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 →
Price
Three packages. You know the price right away.
Team of up to 10 people
from €1,150
net, paid once · 2 weeks
Company, from 11 to 40 people
from €2,300
net, paid once · 3–4 weeks
Organization, over 40 people
from €4,600
net, paid once · 6–8 weeks
- The same packages once you have licenses. To start, an inspection of the space in 1 day is enough: €450 net.
- You buy Claude Team licenses directly from Anthropic, without our markup: USD 20 per person per month for annual payment or USD 25 for monthly payment, from 2 to 150 people.
From conversation to measurement
01 · 30 min
Free process review€0
An engineer picks 3 to 5 of your team's tasks with you. Written plan within 2 working days.
02 · 2 weeks
Rolloutfrom €1,150
Accounts and roles, rules for working with data, training on your team's tasks. You buy licences directly from the provider.
03 · after 30 days
Measurementincluded
We compare task times before and after. We name in writing the tasks worth handing to a system.
or call+48 888 78 48 78WhatsAppMon–Fri 9:00–17:00 CET
Worked example · Scenario
How we count the payback: text work in a clinic
We run the same count for your clinic in the free review.
€3,490
a month for handling 1,500 confirmations and appointment changes by hand
Payback: 1 mo.
4 minutes per confirmation, reminder or rescheduling 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 2,000 + 300 tokens per change, at the ECB rate of 1.1205 USD per euro on 22 October 2026. Recovered visits are a scenario: we assume 1 in 30 handled changes frees a slot early, the front desk fills it from the waiting list and a visit is worth €34. In the review we count it on your price list.
See the full calculation →Questions
How do you choose AI for a doctor's work with text?
On an administrative task, for example drafting an instruction, with an assessment of the errors that change the meaning. Clinical decision support is a separate assessment with different evidence.
Do you need patient data to test AI?
No. The first exercise uses a fictional instruction, and using medical records needs a legal and technical assessment with the data protection officer.
How much does this training cost?
At Syntalith, from €1,150 net for a workshop day for the team. Claude Team seats cost $20 per person a month. With 10 people and 1 hour a week each, the payback is 0.9 months.
