Blog · Published · Updated
AI for researchers: literature notes with sources
Short answer
A researcher can use AI to order literature notes, compare methods and list questions for further reading. Every conclusion needs a check in the source: whether the publication exists and whether it supports the claim are two separate checks. At Syntalith team training costs from €1,150 net a day. With 6 people and 1 hour saved a week each, it pays back in 1.4 months after licence costs.
- 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
Research and AI: statistics 2026
1.4 mo.
payback of €1,150 training with 6 people saving 1 hour a week each: €907 of time given back, €107 of licences a month. Scenario.
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.
9.4%
According to Eurostat (2025), 9.4% of people aged 16 to 74 in the EU used generative AI tools for formal education.
25.1%
According to a Harvard Business School study (2023) of 758 consultants, tasks within the model's capabilities went 25.1% faster with AI.
11 of 13
According to the NoLiMa study (2025), at 32,000 tokens of context 11 of 13 models fall below half of the accuracy they have with a short context.
Figures checked: 22 October 2026
AI literature notes: whether a publication exists, and what supports the claim
The model gives a reference to an article that sounds credible. The first check is whether the publication exists: Crossref offers a metadata search by DOI, bibliographic description or part of the title. Crossref mainly collects metadata supplied by publishers and does not read the full text, so a record it finds does not confirm the claim. The second check is opening the publication and finding the passage that supports the claim.
The practice text describes 40 participants from one lab who finished a task faster with a tool under the conditions studied. The sentence „the tool improves the productivity of all researchers” goes beyond that result. The note keeps the scope of the group, the type of task and the absence of data on other conditions.
| Note field | What to record |
|---|---|
| Question | which question from your work the material answers |
| Source | title, identifier, version and the part of the text available |
| Finding | what the authors observed or proposed |
| Basis | page, section, table or a short passage |
| Limitation | sample, conditions and caveats |
| Own conclusion | interpretation kept apart from the finding |
- Does the publication exist: a Crossref record by DOI or title
- Does the passage support the claim: page, section or table in the full text
- Does the scope of the result match the claim: sample, conditions, task
Also record whether you work with the full text, an abstract or someone else's summary, and which version is the basis: a preprint, the article or a correction. Confidential reviews and unpublished results stay outside the tool without the institution's consent.
What AI training for researchers costs and when it pays back
- Time saved
- 6 people × 1 h a week × 4.33 = 26.0 h
- Value of that time
- €907
- Licences
- $120 (€107)
- Left after licences
- €800 a month
Payback of €1,150 training
1.4 months
The hours saved are the scenario's assumption, which we check by timing the 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 licences at $20 a person a month, at the ECB rate of 1.1205 USD per euro on 22 October 2026.
We measure the hours in the scenario before the training and after 30 days, on the same tasks of the team. If after a month checking texts written with AI takes as long as writing from scratch, we change the exercises or the scope of the tool.
In a research team, the hour a week comes mainly from notes for a literature review and comparisons of methods before writing. The risk is a reference that exists and does not support the claim. So in the exercise we also count the claims a second person had to correct after checking the source.
What the team should practise
In the workshop we work on describing the source, keeping the result apart from the interpretation and improving a note after a second person's comments. After the first round, a colleague checks a few notes without knowing the conversation with AI and records which sources they found and which findings they had to correct. Sample fictional document exercises are available in our training materials (in Polish).
Individuals, a few articles a month
good instructions and Crossref
no build
A team working on shared literature
training in notes and source checks
from €1,150
A large document collection with permissions
a search with a quote from the source
from €3,000
Where to start
For the first exercise, choose a few materials the team has access to and is allowed to use in the chosen tool. We run the workshop as part of our team training. For the free process 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: AI in education
We run the same count for your team in the free process review.
€2,327
a month for searching the school's documents for answers to 400 questions
Payback: 1.5 mo.
10 minutes to find a procedure or material 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 6,000 + 500 tokens per answer from the documents, at the ECB rate of 1.1205 USD per euro on 22 October 2026.
See the full calculation →Questions
How can a researcher use AI with the literature?
To order notes, compare methods and list questions for further reading. Each conclusion is checked in the source: whether the publication exists and whether the passage supports the claim.
Does Crossref confirm what an article says?
No. Crossref helps establish that a publication exists and which record a reference leads to. You check the basis of a claim in the full text.
How much does such training cost?
At Syntalith from €1,150 net for a day's workshop for the team. Claude Team licences cost $20 a person a month. With 6 people and 1 hour a week, the payback is 1.4 months.
