Blog · Published · Updated
What does this company metric mean?
Short answer
A knowledge base next to your reports answers what a metric means in a specific report: it gives the company definition, an edge case and a link to the glossary before the team starts interpreting the numbers. At Syntalith an AI app on company documents costs from €3,000 net. At 300 metric questions a month with 12 minutes of searching each, it pays back in 1.7 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
1.7 mo.
payback of a €3,000 app at 300 metric questions a month: €2,094 of searching today, €319 with the app. Scenario.
42%
According to the European Commission (2026), 42% of EU SMEs and mid-caps already use AI or algorithmic management, mostly in a limited and experimental way.
Source: European Commission, Flash Eurobarometer 578 (2026) ↗
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) ↗
49%
According to Anthropic (2024), combining contextual embeddings with BM25 search cut failed retrievals by 49%, and by 67% with reranking.
48%
According to the European Commission (2026), 48% of EU SMEs and mid-caps name a lack of expertise as a barrier to AI.
Source: European Commission, Flash Eurobarometer 578 (2026) ↗
Figures checked: 22 October 2026
Find the definition before discussing performance
At a meeting someone asks about active customers. One person thinks of companies with a current contract, another of those that ordered recently. In the service report, „active customer” means a company with at least one completed order in the reporting period, and the glossary and the report description explain the period and the exclusions. A new manager asks whether a company with an open, uncompleted order counts as active.
Analyst
how it is calculated
Knows how the report is prepared and what is excluded.
Business owner
purpose of the metric
Knows which decision the definition serves.
Report owner
missing explanations
Completes the glossary when the source does not settle a question.
The assistant does not fetch a specific customer's data to explain a term, and it does not build a missing definition from several similar reports. The general meaning of a term on the internet does not explain how the company counts its result. A definition is easier to use when it says where it is used and who will clear up any doubt.
What a metrics knowledge base costs and when it pays back
- Today
- 300 metric questions × 12 min = 60 h (€2,094)
- With the system, a person checks the output in 15% of the time
- €314
- Model, 1 call per case, Claude Sonnet 5.5
- €4.59
- Cost of one case
- €6.98 today, €1.06 with the system
- Saving
- €1,775 a month
Payback of €3,000
1.7 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. According to the European Commission (2026), 42% of EU SMEs and mid-caps already use AI, mostly in a limited and experimental way. A shared definition of a metric is a condition for measuring what that use brings.
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.
Use the data catalogue you already have
The Microsoft Purview glossary explains the terms used in data governance, and a company glossary can be a good enough start. Do not move a maintained glossary to a new tool just to add a chat. First check whether an explanation next to the metric solves the problem.
A link or explanation next to the metric
a glossary in the report
no new app
A maintained data catalogue
the catalogue as the team's source
configuration
Questions join several definitions and descriptions in different places
an AI app next to the report
from €3,000
What to review before expanding the scope
Choose a report where conversations regularly stall on the meaning of terms. With its owner we go through the readers' questions and prepare edge cases, such as an open order against a completed one, which the analyst and the owner check before release. The app shows the source of the explanation without copying report data, and the reporting system keeps calculating the numbers. The scope 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 →
