Blog · Published · Updated
How to choose AI for Excel? Comparing tasks
Short answer
You choose AI for Excel by what has to stay in the file: help writing a formula, a one-off analysis of a workbook or a regular report. For the first two, a tool the employee already has is enough, while a repeated workflow also needs checks on the sources and data refresh.
- 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
Spreadsheets and AI: statistics 2026
0.7 mo.
payback of a €1,150 training day for 8 people saving 1.5 hours a week each: €1,813 of time recovered against €143 of licences a month. Scenario.
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.
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) ↗
31.1%
According to Eurostat (2025), 31.1% of EU companies that use AI apply it to business administration or management.
20.0%
According to Eurostat (2025), 20.0% of EU companies with at least 10 employees used AI.
Source: Eurostat, 20% of EU enterprises use AI technologies (2025) ↗
Figures checked: 22 October 2026
A formula or one analysis
an AI assistant the employee already has
a licence
Comparing files by keys
Power Query with no model
no extra tool
A weekly report from several sources
an automation with checks on the sources
from €3,000
A formula must keep working after the data changes
Prepare a copy of the sheet and the expected result for a few known rows. Check the case of an empty cell, a new record and a value stored as the wrong type. A formula that is correct for the first example can stop working once the table grows.
Ask for the assumptions to be explained. If the solution skips empty values, decide whether that is what the report needs. Missing information and a zero mean different things. The person using the sheet should know where they will see missing data.
Comparing files may need no model at all
Microsoft describes merging tables in Power Query on one or more columns. The data types and the order of the selected columns matter. When the task comes down to an agreed join on an identifier, try this feature before you buy an extra tool. Microsoft documentation, checked on 9 October 2026.
In a fictional example, the orders table has one row for Z-01, and the descriptions table has two matching entries. After merging and expanding the data, the amount can appear twice. Before summing, settle the expected relationship between the tables. A neat AI comment does not fix such a basis for the calculation.
Assess the output file too
| Task | What to check after the tool has worked |
|---|---|
| A proposed formula | The result, and the behaviour after a row is added |
| A workbook analysis | The source of each number and how gaps are handled |
| Preparing a report | Whether the refresh repeats reliably, and duplicate checks |
| Saving the changed file | Formulas, layout and whether it can be edited further |
Do not compare only the answers in the chat. Open the result and check whether a colleague can carry on with the work. Record the checking time and the corrections that had to be made by hand. This guide describes a proposed trial, with no ranking of current models.
From choosing a tool to the team's work
If you have already chosen help inside the application, see how to start with AI in Excel. When material is pasted into a chat, settle separately the permitted scope of data and how results are stored.
Syntalith can prepare training for work on spreadsheets. Syntalith prices: an automation, app or agent from €3,000 net, training from €1,150 net a day (pricing). The team practises assessing formulas and conclusions on agreed materials. Pulling data regularly from other systems is a separate scope. For the call, a description of the report and of a situation where a result that looked right turned out wrong is enough.
What it costs
- Time saved
- 8 people × 1.5 h a week × 4.33 = 52.0 h
- Value of that time
- €1,813
- Licences
- $160 (€143)
- Left after licences
- €1,670 a month
Payback of a €1,150 training day
0.7 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: work in Excel
We run the same count for your team in the free review.
€1,815
a month for 12 h a week of report preparation
Payback: 1.9 mo.
The hours for each firm size 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. We measured the model cost in our report system: a commentary with a check of the figures costs about €0.0002, converted at the NBP rate of 21 October 2026 and the ECB rate of 1.1205 USD per euro on 22 October 2026.
See the full calculation →Questions
Which AI should you choose for Excel?
For formulas and one-off analyses, a tool the employee already has is enough. A weekly report needs a workflow with checks on the sources and data refresh.
Does comparing files need AI?
Often it does not. Merging queries in Power Query compares files by keys with no model. AI helps with describing differences and unclear columns.
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 8 people and 1.5 hours a week each, the payback is 0.7 months.
