Blog · Published · Updated
Company Brain for commercial property portfolios
Short answer
An AI knowledge base at a manager of several properties finds the instructions for the right building and prepares a draft reply to the tenant with a contact, so a colleague covering the role does not carry over the rules of their own building. At Syntalith an AI app on company documents costs from €3,000 net. At 500 tenant questions a month with 10 minutes of searching 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
- net per application, fixed price before contract
- from €3,000
- from signing the contract to acceptance
- 4–10 weeks
- free prototype on your documents
- €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
AI knowledge bases: statistics 2026
1.2 mo.
payback of a €3,000 app at 500 tenant questions a month: €2,908 of searching today, €444 with the app. Scenario.
15%
According to Brynjolfsson, Li and Raymond (2025), customer support agents working with AI resolved 15% more issues an hour on average, in a study of 5,172 people.
Source: Brynjolfsson, Li and Raymond, The Quarterly Journal of Economics (2025) ↗
47%
According to the European Commission (2026), customer service is the most common use of AI among EU SMEs and mid-caps that already use it: 47%.
Source: European Commission, Flash Eurobarometer 578 (2026) ↗
24.8%
According to Eurostat (2025), 24.8% of EU enterprises in real estate activities used AI.
49%
According to Anthropic (2024), combining contextual embeddings with BM25 search cut failed retrievals by 49%, and by 67% with reranking.
Figures checked: 22 October 2026
The tenant needs to arrange a delivery
A tenant is planning a delivery of office furniture. The instructions for their building say the loading bay is booked through the manager's office, and suppliers use the service entrance. The colleague covering the role usually looks after a building where reception takes such requests.
- 01BuildingWhen the message does not say which building it concerns, the colleague asks the tenant.
- 02InstructionsThe assistant shows the rules for this property, with a link.
- 03DraftA reply with the right contact.
- 04SlotLoading bay availability is checked in the booking system or with the office.
The colleague covers several addresses, so the reply needs the name of the building and a link to its instructions. The tenant learns how to arrange the delivery without waiting for the regular colleague to return. The building's manager keeps the material current and corrects the contact in the place the team uses. The covering colleague then finds the same information as the regular one and does not phone the absent colleague.
What a property knowledge base costs and when it pays back
- Today
- 500 tenant questions × 10 min = 83.3 h (€2,908)
- With the system, a person checks the output in 15% of the time
- €436
- Model, 1 call per case, Claude Sonnet 5.5
- €7.57
- Cost of one case
- €5.82 today, €0.89 with the system
- Saving
- €2,464 a month
Payback of €3,000
1.2 months
The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 6,000 input tokens and 500 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.
The model is a small item here. The result depends on the time that searching and asking around take today, and on how much of it is left for checking the answer.
Before we quote a build, we run a test on 20 to 100 questions the team has already asked: we compare the app's answer with what an employee found by hand and measure the time from the question to the source. The test takes 5 working days and costs €0.
Check what your current system offers
Open the property record in the tool you use. The property details page in Prism Mobile can show building information, contacts and instructions, and Document Intelligence in Prism AI lets you ask about uploaded documents in your own words. A solution of your own makes sense when instructions sit in several tools and staff still ask colleagues for help despite the features available.
A building record with instructions and contacts
show the team how to reach it
no new app
Questions to documents in the current platform
the vendor's AI feature
vendor licence
Instructions and contacts in several tools
an AI app that joins the sources
from €3,000
Help the covering colleague answer without calling the manager
The first scope is one team's buildings and the documents needed for everyday tenant questions, shared with staff according to their tasks. Building managers name the current material, and the covering colleague judges whether the answer lets them handle the case. When instructions are easy to find but replies run long, training in writing messages for property management is more useful. The scope of the assistant is described on the private ChatGPT for your company page.
Worked example · Scenario
How we count the payback: answers from company documents
We run the same count for your documents in the free analysis.
€3,723
a month for finding answers to 800 questions in documents
Payback: 1 mo.
Our assumptions are 8 minutes to find an answer in documents or ask a colleague, 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 from documents, at the ECB rate of 1.1205 USD per euro on 22 October 2026.
See the full calculation →
