Today
Before the first call, sales spends a few minutes searching the web and then dials. On the phone the prospect mentions a quote your company sent years ago that nobody remembers. It sits in the old system, the inquiry in the mailbox of a colleague who left long ago and the trade fair contact in a spreadsheet. So the first contact starts with a bad impression instead of the customer's problem.
An example
A sales engineer at Wallner+Hardt Sensortechnik wants to call a packaging machine maker with two plants that counts as a new prospect. The dossier shows that, according to its job ads, the company is looking for two control engineers with IO-Link experience, that its new cartoning machine is marketed with faster format changes and that the decision makers will be the head of electrical design and the purchasing manager. In the legacy system the agent finds a quote for 80 pressure sensors WS IO-Link from six years ago, lost on lead time, and in the archived sales mailbox an inquiry about the M12 connector pin assignment. She opens the call with the old quote and today's lead time.
Your data, wherever it lives
What your firm already knows about a prospect is scattered today: old quotes in the ERP or a legacy system, trade fair contacts in the CRM or spreadsheets, inquiries in archived mailboxes; the rest is on their website and in public sources. demi reads, understands and links it, with your rights. In minutes the AI builds the dossier that would otherwise take you an hour of searching, and you decide how to open the conversation.
Where the data lives today
- Web & portals
- CRM
- ERP
- E-mails
- Legacy systems
- Folders & drives
How demi solves it
Three layers in this order: connect the data first, then the rights, then the AI.
- 1 · ConnectData Layer
Data sources in this case: websites, CRM, ERP, e-mail, legacy systems and file shares. demi replaces nothing and links public information on the company with everything your firm already knows about it: old quotes in the ERP or a legacy system, trade fair contacts in the CRM, inquiries in archived mailboxes, documents in folders. demi recognizes the company even under an old spelling, a former name or as an acquired plant.
- 2 · PermitPermission Layer
The dossier contains only what you may see in the source systems; earlier prices and margins appear only for roles allowed to see them. People appear only in their business role, from public sources or your own business contacts. demi reads archived mailboxes only if they are released for sales.
- 3 · ActIntelligence Layer
The agent researches the company, its plants, products and news, derives likely problems and names fitting products from your range. It matches the company against the CRM, ERP and legacy systems, even with a different spelling, and finds earlier contacts. Assumptions are marked as assumptions; facts carry their source.
How it runs
- 1
You name the company or pick the lead in the CRM.
- 2
demi gathers public information: plants, products, news, job ads and decision makers.
- 3
The agent searches the CRM, ERP, legacy systems, file shares and archived mailboxes for earlier contacts, including under old company names.
- 4
You get the dossier on one page: company, likely problems, fitting products, decision makers and history, all with sources.
- 5
You decide how to open and what to offer; after the call demi updates the CRM once you approve.
What changes
No first contact without its history
Conversations that start with the customer's problem
Old quotes and contacts become useful again
What does it bring you?
Check it with your own numbers
Every starting value is an assumption you can change. The calculation sits right below, step by step.
Your numbers
Result
+144 hfreed per year
Assumptions and calculation
demi puts together company, decision makers and earlier contacts with your firm; you lead the call.
45 min → 27 min per case
How we calculate
40 prospect dossiers × 45 min × 40% × 1.0 (manual) × 12 months = 8,640 min = 144 h
Value per year, before demi costs
Freed per year+144 h
Assumption: labor cost of $48.62 per hour in US manufacturing in June 2026 (BLS), plus workplace, IT and overhead.
= Value per year, before demi costs
+$9,360
gained per year
144 h ÷ 1,760 h per role = 0.1 full-time roles
An estimate, not a promise. The starting values are assumptions for an industrial company with 150 to 500 people.
Combine with more cases and get the packageQuestions about this use case
Does demi find earlier contacts under a different company name?
Yes. The agent matches names, addresses, register data, domains and phone numbers, including old spellings, a change of name or an acquired plant. If a match is uncertain, it shows it as a possible match and you confirm it.
How does demi know the decision makers at a prospect?
From public sources such as the website, press releases and trade articles, and from your own contacts in the CRM and mailboxes. People appear only in their business role. Whatever is not backed up is listed as an open question in the dossier.
What if our old ERP was switched off long ago?
Then the export or database of the old system helps; it usually still exists somewhere. demi reads such data too and links it to today's customers. We work out with you how the old data is connected.
How current is the public information in the dossier?
demi researches afresh when it builds the dossier and gives source and date for every fact. The agent marks older news as old, so you do not start the call with something outdated.
