Skip to content
BUILT / ASH
Menu
Executive product case studyProduct strategy · Financial intelligence

Portfolio AI

From fragmented holdings to explainable investment decisions.

From a list of holdings to a clearer understanding of what you own—and how a decision changes it.

Independently conceived and built by Ashraf Vallur.
Product strategy, AI architecture, and AI-assisted engineering.

AI interpretations shown: supervised local tests.

Synthetic portfolio · Hypothetical scenariosNo trade execution or investment recommendations↓
01 / The product opportunity

Different holdings.
Shared exposure.

A holdings list separates NVIDIA from QQQ, VOO, and VTI. Their underlying company exposure can overlap.

The product connects those ownership paths, makes the known exposure inspectable, and shows how a hypothetical change affects it.

HoldingsCompany exposureDecision context
02 / The product journey

Four steps. One connected decision.

A $545,450 synthetic portfolio · 7 accounts · 22 positions.
Move from visibility to a hypothetical decision without skipping the evidence.

01 / SEE

Start with the
whole portfolio.

Bring accounts, holdings, and allocations into one view. Establish the financial context for the observations and scenarios that follow.

Synthetic data · fixed snapshot
Synthetic portfolio overview showing $545,450, seven accounts, 22 positions, allocations, and holdings.
Authentic product capture · synthetic portfolio snapshot. View original ↗ (opens in a new tab)
02 / UNDERSTAND

Turn a finding into
a question to investigate.

Rocket Lab’s known exposure exceeds the synthetic investor’s 7% company guideline. The observation connects its explanation to inspectable portfolio facts.

The guideline is a synthetic input. The observation prompts investigation; it does not recommend a transaction.

The product judgment

Make the interpretation reviewable, with the supporting facts close at hand.

Captured local AI observation

Rocket Lab exceeds the stated company guideline.

Known portfolio weight10.8534%
Synthetic guideline7.0%

Readable editorial summary of the supplied local-test capture.

Open original Rocket Lab capture (opens in a new tab) ↗
View Rocket Lab evidence
Supervised local AI observation of Rocket Lab concentration above a synthetic 7% guideline, with expanded evidence references.
Supervised local-test evidence · synthetic data. Image ends within Rocket Lab evidence; the NVIDIA observation is outside the image. View original ↗ (opens in a new tab)

Local interpretation evidence is distinct from hosted availability. Reference checks do not establish semantic correctness.

03 / INVESTIGATE

Follow the exposure,
not just the ticker.

One company. Direct shares and multiple ETF ownership paths. A reproducible calculation makes the known exposure visible.

Direct NVIDIA$33,300
ETF-mediated NVIDIA$8,944
=
Known NVIDIA exposure$42,2447.7448% of total synthetic portfolio value

Known exposure reflects supplied constituents. Partial ETF coverage can leave additional exposure uncounted.

Open original NVIDIA capture (opens in a new tab) ↗
View NVIDIA exposure evidence
NVIDIA exposure detail showing $33,300 direct plus $8,944 ETF-mediated ownership, totaling $42,244 known exposure with partial ETF coverage.
Authentic product capture · partial ETF coverage. The original contribution-table clipping is preserved. View original ↗ (opens in a new tab)
04 / DECIDE

Less Rocket Lab.
More known NVIDIA exposure.

A hypothetical $20,000 RKLB → VTI move reduces one holding while adding indirect ownership of another. The total portfolio value stays fixed.

Fixed synthetic illustration · $20,000 RKLB → VTI
Holding / exposureBeforeAfter
RKLB$59,200$39,200
VTI$68,400$88,400
Known NVIDIA$42,244$43,244
Portfolio total$545,450$545,450

Fixed illustrative 5% NVIDIA weight in VTI. Excludes fees, taxes, slippage, and market movement. Hypothetical analysis; no recommended or executed trade.

Explore the scenario calculation

Adjust the hypothetical.

$0
Additional known NVIDIA+$1,000
Known exposure after$43,244
Share of synthetic portfolio7.93%

Case-study illustration; no application or model API calls. VTI uses a fixed 5% NVIDIA weight; RKLB contributes no NVIDIA exposure. Portfolio value stays $545,450.

Inspect scenario AI interpretation and fallback
Supervised local AI scenario interpretation showing Rocket Lab's reduced weight and remaining synthetic guideline exceedance.
Supervised local AI evidence · hypothetical scenario. A NVIDIA heading appears at the bottom; its explanation is outside the capture. View original ↗ (opens in a new tab)
Deterministic hypothetical scenario results remain available when AI interpretation is unavailable.
Authentic deterministic fallback capture · synthetic data. The image ends within a company-exposure table. View original ↗ (opens in a new tab)
03 / Product leadership

Three decisions behind
the experience.

Product judgment becomes concrete in what the system calculates, what it explains, and what remains useful when interpretation fails.

01

Keep financial calculations reproducible.

I separated exposure and scenario calculations from AI interpretation, keeping the baseline inspectable.

See the exposure example ↗
02

Make interpretations inspectable.

I connected observations to exact evidence references. Those checks support review; they do not establish semantic correctness.

See the observation ↗
03

Preserve useful results when AI fails.

I kept deterministic scenario results available when interpretation is unavailable. The explanation narrows; the calculation remains accessible.

See the scenario ↗
Deterministic calculations→AI interpretation→Evidence-reference checks→Inspectable experience

Investor intent and final decisions remain human responsibilities.

04 / Supporting depth

The experiments
behind the judgment.

Three historical experiments connect development decisions to product judgment. Explore the supporting depth behind the executive story.

01When a plausible response failed the evidence contractContract design · traceability

In a reported development experiment, a useful AI response was rejected because its evidence references failed validation. The product decision was to improve the AI contract while preserving the validator.

Reported incorrect path/snapshot/top_holdings/0/portfolio_weightRequired path/top_holdings/0/portfolio_weight
02Better supplied facts through ETF look-throughSystem boundaries · trusted inputs

The design moved company-level exposure into deterministic calculations rather than asking the model to infer ETF composition. The NVIDIA example above shows the supplied financial baseline.

Return to the exposure example ↗
03Known exceedance versus indeterminate exposureInvestor intent · uncertainty

The historical experiment compared known company exposure with an explicit synthetic guideline. A known exceedance and a below-guideline value with incomplete coverage support different conclusions.

Inspect supporting rule-based observations
Rule-based observations for the synthetic portfolio with evidence paths and values, without a live AI request.
Authentic rule-based capture · synthetic data · no live AI request. View original ↗ (opens in a new tab)
05 / Capabilities & boundaries

Demonstrated scope.
Open questions.

Demonstrated prototype

A connected decision journey.

Portfolio visibility, company-level exposure, a hypothetical scenario, and useful deterministic fallback.

AI interpretations are documented in supervised local tests, separately from the hosted experience.

Current boundaries

Useful within explicit limits.

Synthetic data. Partial ETF coverage. Exact reference checks do not prove semantic correctness. No execution or investment recommendations.

Future evaluation

Broaden coverage and evaluation.

More scenarios, missing-data handling, semantic evaluation, provider resilience, and production AI readiness.

Unbuilt future directions

Market & Regime Intelligence and Opportunity Intelligence remain product directions, not demonstrated capabilities or delivery commitments.

Synthetic data · hypothetical scenarios

Explore the product
behind the case study.

Portfolio analytics and hypothetical scenario analysis, with inspectable exposure insights.

Explore Live Demo (opens in a new tab)

Hosted demo: portfolio analytics and scenario analysis. AI-generated interpretations are demonstrated separately.

Optional technical notes & evidence boundaries

Portfolio analytics and hypothetical scenario calculations are deterministic. AI interpretation is optional and subject to server configuration and request limits. The AI interpretations shown in this case study were captured during supervised local tests. Rule-based observations are supported separately. No transactions are executed.

Evidence-reference checks validate paths and values against supplied facts. They do not establish overall semantic accuracy. Original screenshots remain unchanged, including their documented capture boundaries.