Skip to content

Blog · Published · Updated

Local AI for preparing board materials

Short answer

A local AI assistant prepares a short introduction to each document in the meeting pack for the company secretary, with a link to the source. It must keep the difference between a proposal for discussion and a recorded decision. At Syntalith an app on a local model costs from €3,000 net plus GPU hardware. With 240 documents in packs a month at 15 minutes each, it pays back in 2.2 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
model on your server or in the cloud in the EU
quoted after the review
same work in application with EU cloud model
from €3,000
task, data and equipment analysis
€0

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

Board materials and AI: statistics 2026

2.2 mo.

payback of a €3,000 local app at 240 documents in packs a month: €2,094 of work today, €738 with checking and a GPU server. Scenario.

Figures checked: 22 October 2026

A proposal is not yet a decision

The meeting pack contains a document proposing to replace an internal reporting tool. The author gives the reason: employees enter the same data by hand twice. No decision to replace it has been recorded yet.

A good introduction reads: „The document proposes replacing the reporting tool because the same data is entered by hand twice. The materials record no decision to replace it.” A link to the document sits next to it. The sentence „The board approved replacing the tool” would change the meaning. A board member then knows which question to open the document with, and does not start reading in the belief that the matter is settled. The assistant does not add savings the author did not state.

A guide to the pack
  1. 01Packthe documents of one meeting in an agreed place
  2. 02Introductionthe topic, the main point and who proposes it
  3. 03Statusa proposal, information or a recorded decision
  4. 04Checkthe secretary reads the introduction next to the document
  5. 05Versionafter a document changes, the description is refreshed

What local AI for board materials costs and when it pays back

Scenario: 240 documents in packs a month
Today
240 documents in packs × 15 min = 60 h × €34.90 = €2,094
With the app, an employee checks the output in 25% of the time
€524
Hetzner GEX45 GPU server
€214
Saving
€1,357 a month

Payback of €3,000

2.2 months

The volume, the time and the checking share are the scenario's assumptions, which we measure in the trial. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Price of the GEX45 with 24 GB of GPU memory from Hetzner's website on 22 October 2026, without the one-off setup fee of €209.

The count covers the time spent searching, reading and compiling the material. What stays is the time to check the output against the source, 25% of today's work in the scenario. We measure both times in a trial on 20 to 100 cases the team has already handled. The scenario assumes 240 documents a month: the packs for the management board, the supervisory board and committees in one company. According to a study in Science (2023) of 453 professionals, ChatGPT cut the time spent on writing tasks by 40% (Science).

What runs locally and what needs agreeing

The model runs on a named computer or server in the company. The app takes documents from an agreed place and saves draft introductions where the secretary can check them. The Ollama documentation describes a local mode with cloud features switched off. That is a property of the program that runs the model, and access to documents and where results are saved across the whole app need agreeing separately. For the secretary, what matters is who opens the pack and who sees the draft before it is checked.

What to agree with IT beyond the model
  • Where the app takes documents from and where it saves results
  • What stays in logs, backups and the history of questions
  • Who has access to questions, answers and summaries
  • Who updates the model, the app and the set of documents

Does your current board portal already help

If the authors supply short, consistent summaries, an ordered list of materials with links is enough. Before you build, check the features of your board portal. BoardPro describes its AI assistant, which answers questions about stored materials with references to sources and respects permissions. The feature has to be switched on, needs the right plan and also draws on the model's general knowledge. A local app is a separate option when the company wants to prepare introductions on its own infrastructure.

A list, the portal or local AI
  • Authors write consistent summaries

    a list of materials with links

    no AI

  • The portal has an assistant and the cloud is allowed

    the portal feature on the right plan

    the portal licence

  • The materials stay in the company

    a local app for introductions

    from €3,000 plus hardware

Where to start

To begin, the pack for one meeting and a person who knows what the materials mean are enough. Searching the archive of several bodies over several years is a bigger scope. We roll out local models as part of private LLMs, and we build the view for working with sources as an AI app. For the free process review, a description of one case and the places where the material sits is enough. Confidential files stay in the company, and you get a written plan within 2 working days.

Worked example · Scenario

How we count the payback: materials for the board

We run the same count for your packs in the free process 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 →

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 ↗

A model on your server or in the cloud in the EU, proven on your tasks.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 25, 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 →

Private AI models

A model on your server or in the cloud in the EU, proven on your tasks.

We select the model and equipment for the task, run it and measure the quality using your examples before you buy anything. The data stays in the company or in the cloud in the EU. We price implementation, hardware or hosting and support separately after analysis.

View private AI models →
model on your server or in the cloud in the EU
quoted after the review
same work in application with EU cloud model
from €3,000
task, data and equipment analysis
€0

Questions

  • Can AI prepare summaries for the board?

    It can prepare introductions for the secretary to check. Each one links to the document and keeps the difference between a proposal and a decision.

  • May board materials go into a cloud chat?

    That depends on company rules. According to Eurostat (2025), 48.8% of EU companies that considered AI and did not use it named data protection concerns, so a local environment is often a requirement for board materials.

  • How much does such an app on a local model cost?

    At Syntalith from €3,000 net plus GPU hardware, for example a Hetzner GEX45 server with 24 GB at €214 a month. With 240 documents in packs a month, the payback is 2.2 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
When we roll out ChatGPT, Claude or Copilot, you buy the licences directly from OpenAI, Anthropic or Microsoft and they invoice you. We add nothing to the licence.
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.