Luscent vs building it in-house
A firm with a data team can build its own way to read Client communications, and some should. This page sets out what that build has to include, what Luscent already does, and how to tell which fits your firm.
Either way, the question at the end is the same: can you show what the firm knew, and when?
The short answer
Should we build this ourselves?
You can. A firm that builds it takes on the connections to mail, calendar and CRM, the reading of communications, the scoring, a rules engine for suitability, the evidence trail and the AI governance around all of it, and keeps each of them current as the rules change. Luscent is that system already, hosted in the EU, with a free ninety-day pilot that starts on synthetic data, so the two can be compared on evidence rather than on a slide.
ConnectionsMail, calendar and CRM, scoped by the firm
Your team builds itLiveReading the communicationsLanguage models hosted in the EU, by EU providers
Your team builds itLiveA score per relationshipHealth Score from 0 to 100, each change traced to its source
Your team builds itLiveSuitability rulesMiFID II, GDPR, the EU AI Act, CVM and ANBIMA
Your team builds itLiveMore jurisdictionsSwiss, UK and German rules
Your team builds itRoadmapThe evidence trailWritten as the work happens, exchanges attached, retained seven years
Your team builds itLiveNamed approvalA person approves before anything reaches a Client
Your team builds itLiveA record for firms without a CRMThe Luscent CRM, included at no extra cost
Your team builds itIn buildBuilding it, or starting from Luscent
01What you start with
A blank architecture: models to choose, a pipeline from mail, calendar and CRM, and somewhere to keep what it finds.
A product in production: Signals, Health Scores and suitability evidence linked to its source messages, with Microsoft 365 and Salesforce connected.
02Suitability rules
Written and kept current by your own team, for each jurisdiction you serve.
A deterministic rules engine covering MiFID II, GDPR, the EU AI Act and Brazilian CVM and ANBIMA rules. Swiss, UK and German rules are on the roadmap.
03Where it runs
Wherever the firm hosts it. Residency, model providers and sub-processors are yours to choose and document.
In the EU: client data on Scaleway in Paris, data and AI services on Hetzner in Germany, inference hosted in the EU by EU providers only.
04AI governance
Your own EU AI Act position, model documentation and human oversight, written and maintained in-house.
A documented Article 50 position, available on request, and a named person who approves before anything reaches a Client.
05The evidence trail
Designed, built and retained by your team, and explained by them to a reviewer.
Written as the work happens, with the exchanges attached, and retained seven years.
06Your data
Stays wherever your build keeps it.
Not used to train or fine-tune models. Deleted or returned on termination, as the data processing agreement sets out.
07Who decides
Your Relationship Managers.
Still your Relationship Managers. Luscent decides nothing for the firm.
08How you evaluate it
A business case, a build, and a first version to judge.
A ninety-day pilot, free, with three to five Relationship Managers, starting on synthetic data.
When building fits, and when it does not
Building it in-house fits when
- You have a data and AI team with room beyond its current roadmap
- Your communications estate is unusual enough that no product will fit it
- You want to own the model choice and every line of the evidence design
Luscent fits when
- The evidence question needs an answer before an internal build would ship
- Your team should spend its time on Clients, not on maintaining a rules engine
- You want to judge it on your own book first, without production data
Three questions to answer before you decide
- 01
Can you show what the firm knew, and when?
Start with where your firm stands today. Eight questions place it on a four-level ladder.
Take the readiness check - 02
Would the build pass your own vendor review?
Put the same ten questions to an internal build that you would put to any vendor reading RM communications.
Read the ten questions - 03
What would ninety days on your own book show?
Run the pilot with three to five Relationship Managers, success metrics agreed before day one, and decide on what it shows.
How the pilot works
What buyers ask before they decide
Do we have to move any data into Luscent?
No. Luscent reads Microsoft 365 and Salesforce where the data already sits, through connections the firm authorises and scopes. Nothing is migrated.
Does Luscent use our data to train models?
No. Luscent does not use client data to train or fine-tune models.
What happens to our data if we stop?
Under an agreement, Client data is kept for its term and deleted or returned on termination, as the data processing agreement sets out, and backups age out of a 30-day recovery window. Data exports are standard and source-code escrow is available.
How do we compare the two fairly?
Run the pilot: ninety days, free, three to five Relationship Managers, starting on synthetic data, with success metrics agreed before day one. Then put the same ten vendor questions from the white paper to your internal build.
Judge it on your own book before you build
Ninety days, free, three to five Relationship Managers. Synthetic data first, EU only.