Relationship manager
- A verdict and the smallest fix before the client sees anything
- No second round on advice that has already gone out
OutcomeAdvice leaves once, cleared.
[00] Use case 01 / 04 · Suitability GateSynthetic data throughout
Every trade checked before the advice leaves.
Before a relationship manager sends a proposed rebalance, Luscent checks each trade against the client's mandate and the strictest jurisdiction that applies, and returns a verdict, a plain reason and, where it blocks, the smallest change that would clear it.
The case, in four factsSuitability Gate
- TriggerA drafted rebalance or proposal, before it is sent
- ChecksThe mandate, product rules and the strictest jurisdiction that applies
- ReturnsA verdict per trade, its rule and the smallest fix
- DecidesThe relationship manager; a second person for knowledge gaps
One finding, one decision at a time.
Findings · resolve top-down
Suitability Gate · REB-2041Mandate v3.2 §6
Mandate renewal reviewOverdue
Cross-border · PROP-0113Not evaluated
| Leg · instrument | Verdict |
|---|---|
| T1European equities fund | Queued |
| T2US equities fund | Queued |
| T3Capital-protected note | Queued |
| T4EM sovereign bond fund | Queued |
| T5EUR money market fund | Queued |
REB-2041, drafted by Anne Keller. Equities at 52,0 % against a 45,0 % target. Five trades, checked against Mandate v3.2 and the strictest jurisdiction that applies. Nothing has been sent.
Run the gate
Step 1 of 6: The work comes to you
[01] The storyToday · the moment · with Luscent
From after the fact to before it.
Before a relationship manager sends a rebalance, Luscent checks each trade against the mandate and the strictest jurisdiction, and names the smallest fix.
- 01 · Today
The advice goes out on Friday. The questions arrive on Monday.
A rebalance is drafted and sent, then checked against a mandate that sits in another system. A breach found after the fact is a remediation, not a correction.
- 02 · The moment
The check moves to the draft.
Before anything is sent, every trade meets the mandate and the strictest rule that applies. Same inputs, same answer, every time.
- 03 · With Luscent
Cleared once, on the record.
The fix is named, the escalation routed and the whole decision written down before the client reads a word of the advice.
[02] Who gets whatFour seats
One workflow,four people who stop chasing it.
Compliance officer
- Every verdict with its rule, every override with its reason
- Escalations routed to you, not discovered by you
OutcomeReview moves from after the fact to before it.
Head of advisory
- One standard applied the same way, whoever drafts the proposal
- Fewer proposals returned after they were sent
OutcomeConsistency without another review layer.
Management
- Suitability evidence a supervisor can replay
- Fewer remediations to explain
OutcomeA defensible record by design.
[03] The business caseSame model as the full estimate
Time back from checking, and a record that already exists.
The Suitability Gate works on the compliance effort around advice: checking before, documenting after. This is the part of the estimate on the pricing page it addresses.
- 01Checks run on the draft, not reconstructed after sending
- 02Overrides and escalations recorded as they happen
- 03One rule set, applied the same way across the desk
- PilotMeasured on your own book in the pilot, against success metrics agreed in writing before anything is connected.
Your firm
Compliance effort addressed
195.840 EUR a year
40 % of the compliance effort addressed
- Hours returned
- 2.304 h a year
- Per relationship manager
- 192 h a year
The working
12 relationship managers × 10 h a week × 48 weeks × 85 EUR an hour × 40 % of the effort addressed. The same model and assumptions as the estimate on the pricing page. Modelled from time-and-motion assumptions, not measured client results.
[04] BoundariesAnd how AI is used here
What it always does,and what it never does.
Always
- Runs on the draft, before anything is sent to the client.
- Names the smallest change that clears a block.
- Routes a knowledge and experience gap to a second person.
- Holds a trade with missing data instead of guessing.
- Records every verdict, override and send.
Never
- Executes a trade. There is no order routing; this is advice.
- Lets a model decide a verdict. Rules decide; the model only words the reason.
- Blocks silently. A block is a hold the relationship manager clears or overrides, on the record.
How AI is used · Reads
Deterministic rules check each trade against the mandate and the strictest jurisdiction. A language model only words the reason.
How AI is used · Decides
The rule gives the verdict. The relationship manager clears or overrides a hold, on the record.
How AI is used · On the record
Every verdict, override and send, with the rule that fired.
The EU AI Act's Article 50 transparency obligations applied on 2 August 2026. Luscent's documented position is available on request. Where AI reads, and who decides
[05] The ruleOur reading, not legal advice
Our reading of MiFID II (Directive 2014/65/EU), Article 25(2)
“When providing investment advice or portfolio management the investment firm shall obtain the necessary information ... so as to enable the investment firm to recommend to the client or potential client the investment services and financial instruments that are suitable for him ...”
Suitability is decided per recommendation, against what the firm knows about the client. A gate on the draft, before it is sent, is where that obligation is cheapest to meet and easiest to prove.
Our reading, not legal advice. The rules engine applies the firm's own configuration of these rules, and the relationship manager decides.
[06] QuestionsAsked before signature
Questions.
Does the Suitability Gate execute trades?
No. It evaluates a draft recommendation before it is sent. There is no order routing and no connection to a custodian; what leaves is advice, signed by the relationship manager.
Can a relationship manager override a block?
Yes. A block is a workflow hold, not a system veto. The relationship manager can clear it with the suggested fix or override it with a reason, and the override is written to the Audit Trail. A knowledge and experience gap is different: that leg waits for the second person's sign-off.
[07] The same LoopRecord · Understand · Explain · Decide · Prove
Three more triggers,one way of working.
Use case 02 · Comms to Compliance
An email changes the client. The advice waits.
When a client email says their circumstances changed, Luscent reads the change, holds the advice that relied on the old picture, and opens a reassessment.
See it run →Use case 03 · Cross-BorderTwo rulebooks. One household. One defensible answer.
A household booked in Luxembourg and São Paulo sits under MiFID II and CVM at once. Luscent evaluates one action under both and shows a path to proceed.
See it run →Use case 04 · Relationship DriftRelationships rarely end loudly. They drift.
When a client relationship slips, Luscent shows it in the Health Score, links the messages behind it and lists the next conversation for the relationship manager.
See it run →The pilotCohort open
Find out before you move a single client record.
Ninety days, at no cost, with three to five relationship managers, starting on invented clients. Success metrics are agreed in writing before anything is connected, so at the end there is a decision rather than an impression.
The terms
- Length
- 90 days
- Cost
- Nothing
- Seats
- 3 to 5 relationship managers
- Data
- Synthetic first
- Client data
- Stays in the EU
- Writes back
- Nothing
- DAY 0Metrics agreed, in writing
- ConnectWeek 1 to 4
- WEEK 4The book, ranked
- First Signal acted onWeek 5 to 8
- WEEK 8A decision on the record
- ReviewWeek 9 to 13
- DAY 90Written review