Stage 4AI agent · live
AI portfolio assistant
Users ask about their own assets in plain language. Valuation, concentration and diagnosis tiers are computed in code; the model only explains.
AI agents · data platforms
I build AI agents on real financial data, and the data platforms underneath them: governed access, correct numbers, checked output. Open to consulting and full-time roles.
7+ years on data platforms10 articles, one covered on the AWS Big Data Blog
| Holding (sample) | Value | Weight |
|---|---|---|
| Equity fund A | 43,673.00 | 34% |
| Bond fund B | 33,397.00 | 26% |
| Single stock C | 23,121.00 | 18% |
| Gold fund D | 15,414.00 | 12% |
| Cash E | 12,845.00 | 10% |
Your portfolio is moderately concentrated (HHI 2,400). The largest holding, Equity fund A, is 34% of value, and defensive assets are 36%.
One question kept pushing each step: is this number right, and who is allowed to see it?
2018–2020 · Stage 1
a consumer platform
Answered business questions and built the reports people relied on.
LearnedMost wrong answers come from definitions and upstream data, not from the analysis.
so → I moved upstream
2020–2021 · Stage 2
a consumer platform
Built a layered warehouse across the business domains, with scheduling generated from SQL dependencies, and worked on a cross-cloud change-data pipeline.
LearnedScale comes from automation and conventions, not from people watching jobs.
so → I went where a number must be exact
2021–now · Stage 3
a financial platform
Worked on the shared data platform and warehouse; merged two platforms into one and moved it to Kubernetes; built reconciliation, a live risk-feature service and security ID mapping.
LearnedCorrectness is a property of the system: data contracts, gates and human approval.
so → the users changed: agents began reading the data
Now · Stage 4
Gave agents correct, permitted data: a semantic layer, identity from the gateway, SQL that runs only after the user confirms. And built agents that ship: a portfolio assistant for real users, a public multi-agent harness.
LearnedThe model explains. The code counts.
Each case is shown the way it behaves when it runs. All figures in the interface previews are sample data.
Stage 4AI agent · live
Users ask about their own assets in plain language. Valuation, concentration and diagnosis tiers are computed in code; the model only explains.
Stage 4AI agent · in production
A semantic layer so an agent finds the right table and reads values correctly. Identity comes from the gateway, and SQL runs only after the user confirms.
Stage 3Data platform
External account balances against the internal ledger: one business day, counts before amounts, real differences go to manual approval.
Stage 3Data platform · public
A Hadoop-era stack rebuilt as Helm charts on Kubernetes, secured by one identity store and one policy store. Covered on the AWS Big Data Blog.
Three more places, depending on what you came for.
Ten articles from running data platforms, and two video tests of new AI models.
Three small engagements, each with a written deliverable.
The four stages in full, and what each one taught me.
I reply within two working days.