Rick Huang — Applied AI Architect, Business Lead. Independent Advisor to FlowVision. Applied AI grounded in reliable data and measurable business outcomes.https://www.hzy230051.com/enhttps://www.hzy230051.com/tech/data-quality-at-every-layer/https://www.hzy230051.com/tech/data-quality-at-every-layer/A 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.Sat, 10 Oct 2026 00:00:00 GMTdata qualitydata pipelinesdbtdata observabilityenterprise AIdata foundations serieshttps://www.hzy230051.com/tech/before-you-build-the-agent/https://www.hzy230051.com/tech/before-you-build-the-agent/An 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.Wed, 07 Oct 2026 00:00:00 GMTdata pipelinesingestione-commerceenterprise AIdata foundations serieshttps://www.hzy230051.com/tech/data-models-agents-can-trust/https://www.hzy230051.com/tech/data-models-agents-can-trust/Analysts 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.Wed, 30 Sep 2026 00:00:00 GMTdata modelingagentsSalesforcesemantic layerdata qualityhttps://www.hzy230051.com/tech/chart-of-accounts-migration/https://www.hzy230051.com/tech/chart-of-accounts-migration/When 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.Wed, 23 Sep 2026 00:00:00 GMTchart of accountsgeneral ledgerdbtfinance datamigrationhttps://www.hzy230051.com/tech/certifying-data-models-with-an-agent/https://www.hzy230051.com/tech/certifying-data-models-with-an-agent/A 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.Sun, 19 Jul 2026 00:00:00 GMTdbtdata governanceClaude CodeBigQueryagentshttps://www.hzy230051.com/tech/regulatory-pdfs-to-agent-packs/https://www.hzy230051.com/tech/regulatory-pdfs-to-agent-packs/Models 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.Sun, 05 Apr 2026 00:00:00 GMTagentsregulatorydocument processingCPSCPythonhttps://www.hzy230051.com/tech/evals-for-analytics-agents/https://www.hzy230051.com/tech/evals-for-analytics-agents/If 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.Sun, 22 Feb 2026 00:00:00 GMTevalsagentsanalyticsCIfinance datahttps://www.hzy230051.com/tech/five-long-bets/https://www.hzy230051.com/tech/five-long-bets/Where I'm putting time and capital over the next decade, the signal I watch for each bet, and what would prove me wrong.Sun, 28 Dec 2025 00:00:00 GMTAIinvestingsemantic layerinfrastructurelong-term thinkinghttps://www.hzy230051.com/tech/semantic-layer-is-the-api-for-ai/https://www.hzy230051.com/tech/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.Sun, 12 Oct 2025 00:00:00 GMTsemantic layertext-to-SQLMCPagentsfinance datahttps://www.hzy230051.com/tech/modeling-basis-point-fees/https://www.hzy230051.com/tech/modeling-basis-point-fees/Custody 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.Sun, 03 Aug 2025 00:00:00 GMTfeespricingfinance datadbtcrypto custodyhttps://www.hzy230051.com/life/novelty-is-the-highest-yield-asset/https://www.hzy230051.com/life/novelty-is-the-highest-yield-asset/The best returns I get are on time spent learning something new or going somewhere unfamiliar. Why routine makes the years disappear, and why reading and travel belong in the budget, not the leftovers.Sun, 29 Jun 2025 00:00:00 GMTtimememoryreadingtravelliving deliberatelyhttps://www.hzy230051.com/tech/one-customer-five-systems/https://www.hzy230051.com/tech/one-customer-five-systems/CRM, 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.Sun, 18 May 2025 00:00:00 GMTentity resolutioncustomer datamaster datadbtfinance datahttps://www.hzy230051.com/tech/as-of-vs-as-was-bitemporal-finance/https://www.hzy230051.com/tech/as-of-vs-as-was-bitemporal-finance/Late 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.Sun, 09 Mar 2025 00:00:00 GMTbitemporalfinance datadbtdata modelingaudithttps://www.hzy230051.com/tech/ledger-first-data-architecture/https://www.hzy230051.com/tech/ledger-first-data-architecture/Every 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.Sun, 26 Jan 2025 00:00:00 GMTdata architectureledgercrypto custodydbtreconciliation