Rick Huang

Data architecture & applied AI

Better data models.
AI that does
real work.

I'm Rick Huang, an Applied AI Architect, Business Lead and Independent Advisor to FlowVision. I design the data models businesses run on and put AI to work inside them. Here I share what holds up in practice—and what I’m learning along the way.

Explore Tech Talk See my projects

Read Rick's BioGet in touch ↗

Start hereTech Talk

The semantic layer is the API for AI

Text-to-SQL demos well and fails quietly on finance data. Governed metrics, declared grain and semi-additive measures are what make an analytics agent trustworthy, and the semantic layer is how you hand them over.

· 9 min readRead the essay
01Tech TalkData architecture and modeling across industries, and AI that does real work inside the data stack.13 posts02Living LifeIdentity, belonging, time, and living deliberately.1 post

Putting AI to work

Browse Tech Talk
  1. 10 min readEvals for analytics agents: grading answers against the ledgerIf an AI answers finance questions, its accuracy should be a number you can report. How to build a golden question set, compute ground truth from certified models, score numeric and tabular answers, and catch regressions in CI.Tech TalkAI Native
  2. 4 min readData models agents can trustAnalysts fill gaps in a data model with tribal knowledge; AI agents fill them with confident guesses. Four ideas, with real Salesforce examples, for models an agent can answer from correctly.Tech TalkAI NativeData Architecture
  3. 8 min readCertifying data models with an agent in the loopA production pattern for deciding whether a dbt model is fit for finance reporting: deterministic gates first, sandboxed tests against production data, ticket traceability, and a coding agent used only for triage.Tech TalkAI Native
  4. 8 min readTurning regulatory PDFs into agent-ready packsModels are bad at 60-page government PDFs and good at well-shaped data. A recipe for converting one into the other, worked through on the public US product-safety eFiling documentation.Tech TalkAI Native
  5. 15 min readGreen pipeline, wrong numbers: data quality at every layerA pipeline that ran is not a pipeline that is right. Part 2 of a series on data foundations for enterprise AI: the checks that run at every layer, the SLA on the gold layer, and who gets told when something breaks.Tech TalkData Architecture
  6. 8 min readBefore you build the agent: working backwards to your data pipelineAn agent is only as trustworthy as the numbers under it. Part 1 of a series on data foundations for enterprise AI: getting every channel's data in, and modeling it so it agrees with itself.Tech TalkData Architecture
  7. 2 min readFive long bets on AI, data and financial infrastructureWhere I'm putting time and capital over the next decade, the signal I watch for each bet, and what would prove me wrong.Tech TalkAI Native

Finance data, done properly

Five essays on the definitions, ledgers and histories that make the numbers agree.

  1. 9 min readLedger-first: a data architecture for a crypto custodianEvery finance number should be derivable from one immutable, double-entry ledger. How to model custody, balances and valuation so that dashboards are just views and reconciliation is a test.Data Architecture
  2. 9 min readOne customer, five systems: entity resolution and survivorship for finance dataCRM, contracts, ERP, billing and KYC each have their own idea of who the customer is. How I model a canonical party, match records without guessing, pick survivorship rules per attribute, and prove the result is right.Data ArchitectureBusiness Logic
  3. 8 min readBasis points on a moving balance: modeling asset-based feesCustody and asset-management fees are charged in basis points on balances that change every block. Average daily balance, tiered vs. banded pricing, minimums, valuation cutoffs, and reconciling the model to the invoice.Business Logic
  4. 8 min readAs-of vs. as-was: bitemporal modeling for financial reportingLate prices, backdated deposits and restatements mean "what was the balance on December 31?" has two right answers. How to model both, and why auditors care which one you show.Data ArchitectureBusiness Logic
  5. 9 min readMigrating a chart of accounts without breaking a single reportWhen finance re-cuts the general ledger, every dbt model, metric and dashboard downstream is exposed. A playbook: crosswalks, dual-running, zero-tolerance reconciliation, and treating the account hierarchy as a data contract.MigrationBusiness Logic

Things I've built

All projects →
Data engineering · at work · 2026Agent-in-the-loop data certificationA Claude Code plugin that certifies dbt models against team data standards before they reach dashboards.View project AI × regulation · 2026CPSC eFiling agent packTurned a stack of US product-safety PDFs into an agent-ready corpus, plus a test harness for the Product Registry API.View project Company site · bilingual · 2026WayAnalyticsA bilingual (English and Chinese) analytics and e-commerce compliance studio, built as a monorepo with shared tokens and validated content.View project