Blog · Published · Updated
Local AI for confidential client projects
Short answer
On a project under an NDA, a local AI model compares versions of the client's documents on a named workstation, with nothing sent to an outside service. You still agree where the chat history goes, how a colleague takes over and what happens at closure. At Syntalith an app on a local model costs from €3,000 net plus GPU hardware. With 200 document comparisons a month at 30 minutes each, it pays back in 1.2 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
Confidential data and AI: statistics 2026
1.2 mo.
payback of a €3,000 local app at 200 document comparisons a month: €3,490 of work today, €1,087 with checking and a GPU server. Scenario.
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) ↗
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) ↗
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) ↗
84%
According to the European Commission (2025), 84% of Europeans think AI at work needs careful management to protect privacy and ensure transparency.
Source: European Commission, AI and the future of work (2025) ↗
Figures checked: 22 October 2026
A revised brief and one comparison
A consultancy and its client agreed to work with the client's documents only on a designated workstation, and the restriction also covers any material derived from them. The client sends a revised brief with added interviews, and the consultant works out what changes for the team. The assistant prepares a comparison that shows the added interviews and links to the passages in both versions. The consultant checks that the summary keeps the workshop and the report, and adds a question to discuss with the client.
The consultant finishes their part, and a colleague will lead the conversation with the client. They cannot send her the file on any laptop: she needs agreed access to the workstation or the workspace. A good handover covers a checked list of changes, both versions and the open question, which the colleague can open without replaying the conversation with the model.
- 01Documentsversions of the brief only on the designated workstation
- 02Comparisonchanges with links to both versions
- 03Checkthe consultant approves the list of changes
- 04Handoverthe colleague gets access to the same place
- 05Closurethe material and conversations go to the person responsible
What local AI for confidential projects costs and when it pays back
- Today
- 200 document comparisons × 30 min = 100 h × €34.90 = €3,490
- With the app, an employee checks the output in 25% of the time
- €873
- Hardware in the company, counted in the scenario as renting a GEX45 server
- €214
- Saving
- €2,404 a month
Payback of €3,000
1.2 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. We price hardware in your own server room after the review.
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.
What runs locally and what needs agreeing
A model on the designated computer analyses documents without sending the task to an outside service. LM Studio describes local work with documents and an offline mode, and the app's privacy policy states that messages, chat history and documents are stored locally. The chat history helps the author return to their reasoning, and it also stores project content, so the person responsible for the environment includes it in access rules and in the closure.
- 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
When an ordinary document comparison is enough
If the change in the brief is short and visible, an ordinary comparison in the editor is enough. An assistant is worth testing when the changes are scattered and the consultant has to work out what they mean for the project scope. Each client has a separate workspace: an earlier brief stays in the previous client's collection and conversations are kept apart, so a new answer never draws on another client's material. Searching an archive for earlier research is covered in the article on private AI for R&D documentation.
A short, visible change
comparison in the editor
no AI
Scattered changes, one workstation
a local assistant with a separate place per project
from €3,000 plus hardware
The team hands comparisons to one another
an app with projects and access control
€3,000 to €7,000
Where to start
When choosing, we go through the whole task with the person who prepares the comparison and the person who takes it over. The first scope covers one project and one workstation. 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: a local model on confidential documents
We run the same count for your projects in the free process review.
€4,363
a month for the work on 500 questions
EU cloud version payback: 0.8 mo.
Our assumptions are 15 minutes to find a passage in case files and templates, and checking in 15% of the old time. €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 in the EU cloud version, at the ECB rate of 1.1205 USD per euro on 22 October 2026. We count the payback for an app with a model in the EU cloud (from €3,000 net). We price the model on your server after a call, and the cost of people's work stays the same.
See the full calculation →
