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 ↓
- 01Call30 minutes with an engineer, free
- 02PrototypeA working system on your process and data, free
- 03ImplementationTarget and fixed price in the contract; 50% at signing
- 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
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.
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 and did not use it named concerns about data protection and privacy.
Source: Eurostat, Use of artificial intelligence in enterprises (2025) ↗
52.5%
According to Eurostat (2025), 52.5% of EU companies that considered AI and did not use it named a lack of clarity about the legal consequences.
Source: Eurostat, Use of artificial intelligence in enterprises (2025) ↗
49%
According to the European Commission (2026), 49% of EU SMEs and mid-caps name legal uncertainty as a barrier to using AI.
Source: European Commission, Flash Eurobarometer 578 (2026) ↗
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.
- 01Packthe documents of one meeting in an agreed place
- 02Introductionthe topic, the main point and who proposes it
- 03Statusa proposal, information or a recorded decision
- 04Checkthe secretary reads the introduction next to the document
- 05Versionafter a document changes, the description is refreshed
What local AI for board materials costs and when it pays back
- 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.
- 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.
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 →