decade
The Decade Advisory Tool · Case

Heard first.
Advised well.

Lucas PreviatoJune 2026
§ 01

The gap.

The US$1M–10M client has an advisor, pays for advice, and is not receiving it. That gap is the opportunity.

decade02 / 23
§ 01 · The Gap

A market that fails the middle.

Retail

No advisory at all

The individual is on their own: whatever the branch offers, the algorithm surfaces, or they learn themselves.

US$1M–10M · entry point

Product, dressed as advisory

Has an advisor. Pays for advice. Does not receive it. A book of ~250 clients, under an hour each per month.

Ultra-high-net-worth

The family office

Works, but expensive, complex, and demands dedicated staff most would rather not own.

The result, at scaleThe Banco Master case
R$30 biBanco Master-linked paper placed by XP alone
R$52 biplaced across all platforms
Example · the risk nobody chose

A client with 90% in CDI feels safe. In reality it is a concentrated emerging-market credit bet (one sovereign, one currency, roughly 1% of the global investable universe), indistinguishable from an EM sovereign bond fund.

decade03 / 23
§ 01 · The Gap

What AI changes.

The real constraint

The manual workload, per client

  • Reconciling statements across every broker
  • The balance sheet and the calculations behind it
  • Constructing and rebalancing the portfolio
  • Transcribing meetings; researching every product
The unlock

AI removes the manual work

  • Calculations, portfolio construction, transcripts, product analysis: automated
  • Done in minutes, for every client, not just the largest
  • The advisor reviews, decides, and signs off
  • Their hours move to judgment, trust, the relationship
decade04 / 23
§ 02

The tool.

The client must feel heard before they are advised. Every design decision is filtered through that one principle.

decade05 / 23
§ 02 · The Tool

One source of truth, two interfaces.

Source of TruthThe centralized client profile · version-controlled
The Engine · advisor

Dense. Full-depth.

  • Workbench
  • IT Feed
  • Recommendation Builder
  • Client Thread
  • Pre-call Brief
  • Audit Trail
The View · client

Calm. Narrative.

  • Plan Document
  • Scenario Builder
  • Live Dashboard
  • Communication Layer
Investment Team backbonePhilosophy · approved universe · active views · AI training
decade06 / 23
§ 02 · The Tool

The product flow, end to end.

0
Pre-call prepAI
1
First conversationHuman-led
2
Mirror SummaryAI + Advisor
3
DocumentsAI + Advisor
4
ConstructionAI + Advisor
5
Plan DocumentAI + Advisor
6
OngoingAI + Advisor
AI
Builds the brief from public data
Transcribes, extracts the inputs
Drafts the summary
Validates, discovers, builds the artifacts
Runs the analyses, drafts the recommendation
Generates the Hero + sections
Monitors, briefs before each touch
Advisor
Reads it
Leads the conversation
Edits, signs, sends
Reviews flags, sets the agenda
Reviews, overrides, decides
Confirms, delivers in person
Touchpoints; human at the crossroads
Investment TeamThe approved universe, philosophy, and active views feed Construction and the ongoing loop, always on, behind the Engine.
AI: present at every stage Advisor: hands-on Advisor: light touch
decade07 / 23
§ 02 · The Tool

The first conversation.

Not a questionnaire. The advisor leaves with nine inputs, captured through natural conversation.

1

Wealth source & trajectory

Where it came from, where it is going

2

Time horizon

When the money must start working

3

Income stability

How predictable the cashflow is

4

Concentration

Any single exposure that dominates the book

5

Loss tolerance

The number at which they would act

6

Life events

Exit, inheritance, purchase ahead

7

Near-term liquidity

Cash the portfolio must supply in 6–24 months

+

Tax exposure

Regimes, structures, offshore in place

+

Mental benchmark

What "doing well" is measured against

decade08 / 23
§ 02 · The Tool

How a recommendation is built.

01

Four parallel analyses

Risk, liquidity, concentration, and cost & tax, run together before any recommendation. The logic behind each: §03.

02

Built on the approved universe

Position by position, each with a thesis: its role, why this instrument, the transition path. Anything outside it escalates to the investment team.

03

Advisor review & override

Accept, modify, or reject. Every override is logged with the reasoning; the AI's original is kept for comparison.

04

Transition plan

Current → recommended is staged, never a jump: around illiquidity and psychological barriers, paired with the Behavioral Covenant.

The ideal portfolio is the destination; the transition plan is the route.
decade09 / 23
§ 02 · The Tool

Calibrated to the client, not the category.

Where we probe · diagnostic lenses

Each background hides risks clients don't volunteer. The lens tells the advisor where to look, then recedes once the real numbers are in.

Equity-comp executiveBusiness owner pre-exitPost-exit founderInheritorReal-estate-heavyScattered accounts
How the mix tilts · by time horizon

The longer the horizon, the more of the book starts in equity, the growth layer. A binding constraint (concentration, behavior, capacity) then pulls it back from this starting point.

< 3 yrs
85%
15%
3–7 yrs
60%
40%
7–10 yrs
38%
62%
10+ yrs
22%
78%
Fixed income Equity · the growth layer
Two clients with the same wealth origin can hold entirely different portfolios, built on their actual numbers, not their category.
decade10 / 23
§ 02 · The Tool

The same tool, as a system.

Every touchpoint updates the Source of Truth AI across the pipeline: extraction · analysis · drafting · monitoring AI Pre-call brief from public data AI Meeting notes from the conversation AI Documents ingested & validated AI · SYSTEM Source of Truth the versioned profile AI + ADVISOR Recommendation four analyses (risk, liquidity, concentration, cost & tax) built on the approved universe HUMAN-LED · THE ENGINE Advisor reviews · decides · delivers CLIENT · THE VIEW Client plan · dashboard · scenarios HUMAN · INVESTMENT TEAM Investment Team approved universe · philosophy · active views
AI AI + Advisor Human-led Client-facing AI = artificial intelligence
decade11 / 23
§ 03

The logic.

The logic the recommendation is built on: how the tool reads risk, sizes the portfolio in layers, and weighs concentration. The reasoning that makes every position defensible.

decade12 / 23
§ 03 · The Logic

Risk is what you do, not what you say.

1

Behavioral history

What they did in 2008, March 2020, 2022

Heaviest
2

Capacity for loss

The drawdown the plan can absorb

High
3

Mental benchmark

What "well" is measured against, often CDI

Medium
4

Stated tolerance

What they say about risk

Lightest
decade13 / 23
§ 03 · The Logic

The portfolio, in four layers.

Layer 1

Liquidity reserve

6–12 months of obligations, same-day liquidity.

Layer 2

Stability

Extends protection from months to years: NTN-B, high-grade credit.

Layer 3

Growth

The residual, globally diversified by default.

Layer 4

Opportunistic

Bounded, only on an active investment-team view.

Gross income / inflow
Non-discretionary expenses
Tax obligations
Pre-committed cash flows
=Investable surplus
1Reserve: fund first
2Stability: fund second
3Growth: once protected
4Opportunistic: when warranted
decade14 / 23
§ 03 · The Logic

Concentration, in four dimensions.

Securitya single instrument
The tightest line: single-company risk does not diversify away.
Tolerance · low
Sectorone sector or theme
More room: names inside a sector still carry some internal diversification.
Tolerance · moderate
Illiquidreal estate, private business
Judged against the liquidity reserve, not punished outright.
Tolerance · contextual
Geographiccountry or currency block
The most permissive line, and the one almost every Brazilian client already sits past.
Tolerance · high
When a line is crossed, the response escalates →
Awareness flag

Documented and raised at the next touchpoint. Baseline unchanged.

Hard flag

Allocation modified to reflect the exposure. Advisor action logged.

Pre-condition

The portfolio is built around the position, not despite it.

decade15 / 23
§ 03 · The Logic

What you keep, not what it yields.

Every position is judged net of fees and tax. A lower headline yield with a cleaner structure can keep more than a higher one that leaks.

Product AHigher headline yield
Kept
Fees & tax
Product BLower headline · cleaner structure
Kept
Product B's headline is lower, but after fees and tax, the client keeps more.
How we cut the leakAsset location · tax-loss harvesting · structure (holding / offshore) · surfacing every embedded fee the client never saw.
We build tax efficiency into the recommendation to lift net return; it is not a substitute for the client's tax counsel.
decade16 / 23
§ 03 · The Logic

A benchmark worth holding to.

What clients measure

CDI

  • The cost of short-term EM liquidity
  • A 12-month lens
  • Punishes global diversification in good local years
What we measure

IPCA + 4–5%, rolling 10 years

  • The NTN-B real-return floor
  • Real purchasing power, preserved
  • The right horizon for the plan
We do not change the portfolio to chase CDI. We change the comparison.
decade17 / 23
§ 03 · The Logic

Built for the long run.

The Crossroads · life decisions

Decisions, framed in advance

  • Business exit · education funding · inheritance · real estate · liquidity events
  • Each path modeled in expected-value terms; the non-financial surfaced
  • The client decides; the plan adapts
The Behavioral Covenant

Volatility, pre-agreed

  • Client pre-commits: no selling in a drawdown without a call; 48 hours before any change
  • Advisor commits: outreach at defined drawdown thresholds, not optional
  • Judged over a rolling 10 years, not 12 months
Most failure in this segment is behavioral, not analytical. The plan is built to be held.
decade18 / 23
§ 04

Human + AI.

AI does what scales. The human does what matters. The split is deliberate.

decade19 / 23
§ 04 · Human + AI

The division of labor.

AI handles
  • Pre-call briefs & transcript extraction
  • Balance sheet, P&L, projections
  • Risk, liquidity, concentration, cost & tax analysis
  • Draft recommendations & monitoring
The human handles
  • The first conversation
  • What the inputs mean for this client
  • The override, the call
  • The relationship through volatility
Investment TeamApproved universe · investment philosophy · active views · the signal that trains the AI.
decade20 / 23
Why it works

Three reasons it holds.

01

Capacity

150+ clients, each actually advised, not fewer. Protecting quality caps today's advisor near 150; the AI removes the manual work behind that ceiling, so 150 × 4 conversations at ~1.5h each ≈ 900 of an advisor's ~1,700 yearly hours.

02

Compliance

A byproduct, not a module. Every thesis, override, and version is already documented by the workflow.

03

Flywheel

Improves with use. More clients → better-trained AI → better outcomes. A moat that compounds.

decade21 / 23
The trajectory

One tool, three wrappers.

US$50M and beyond

Thicken the human layer

Succession, alternatives, life-encompassing advisory. Same tool, more service density.

US$1M–10M · entry

The validation segment

Where the pain is sharpest. AUM-based, advisor-led, and where the model is proven.

Below US$1M

Thin the human layer

AI-first, subscription / SaaS, a personal financial operating system.

Same architecture. Proportional human density.
decade22 / 23
In closing

Heard first.
Advised well.

CandidateLucas Previato
DateJune 2026
decade23 / 23