Work

Built for real problems.

Open-data systems anyone can use, research on models that survive the field, assistants built in the open, and the methods behind enterprise platforms in production. One thread runs through all of it: from the raw table to the decision it informs, every number has to hold up.

How my work fits together.

How my work fits togetherSources (ERP and accounting systems, legacy desktop databases and spreadsheets, satellite archives, AIS shipping data and field photos) feed a data layer (safe reads from live systems, batch and incremental ETL and ELT pipelines, lakes and warehouses with dimensional models, data quality and reconciliation), then models (machine learning and deep learning, statistics and anomaly detection, geospatial analysis, evaluation under real-world conditions), then delivery (governed AI agents, dashboards and management packs, production platforms, public dashboards), which serve decisions in operations, finance, sales, risk, site selection and crop monitoring. Each item links to the case study that shows it.SourcesERP and accountingsystems (SAP BusinessOne, Sage, aPostgreSQL-based ERP)Legacy desktopdatabases andspreadsheetsSatellite archivesAIS shipping dataField photosDataSafe reads from livesystemsBatch and incrementalpipelines (ETL and ELT)Lakes and warehouses,dimensional modelsData quality andreconciliationModelsMachine learning anddeep learningStatistics and anomalydetectionGeospatial analysisEvaluation underreal-world conditionsDeliveryGoverned AI agentsDashboards andmanagement packsProduction platformsPublic dashboardsDecisionsOperations, finance,sales and riskSite selectionCrop monitoringHow my work fits togetherSources (ERP and accounting systems, legacy desktop databases and spreadsheets, satellite archives, AIS shipping data and field photos) feed a data layer (safe reads from live systems, batch and incremental ETL and ELT pipelines, lakes and warehouses with dimensional models, data quality and reconciliation), then models (machine learning and deep learning, statistics and anomaly detection, geospatial analysis, evaluation under real-world conditions), then delivery (governed AI agents, dashboards and management packs, production platforms, public dashboards), which serve decisions in operations, finance, sales, risk, site selection and crop monitoring. Each item links to the case study that shows it.SourcesERP and accounting systems (SAP BusinessOne, Sage, a PostgreSQL-based ERP)Legacy desktop databases and spreadsheetsSatellite archivesAIS shipping dataField photosDataSafe reads from live systemsBatch and incremental pipelines (ETL andELT)Lakes and warehouses, dimensional modelsData quality and reconciliationModelsMachine learning and deep learningStatistics and anomaly detectionGeospatial analysisEvaluation under real-world conditionsDeliveryGoverned AI agentsDashboards and management packsProduction platformsPublic dashboardsDecisionsOperations, finance, sales and riskSite selectionCrop monitoring

Enterprise delivery

How I build at AI Creative Solutions, written as methods rather than client systems. Client work spans manufacturing, agriculture, healthcare and distribution.

Patterns I build in

  • The source is the truth.Mirror the source system and reconcile against it. A disagreement is reported as a finding, never quietly fixed.
  • Prove it before it goes live.Shadow runs compared column by column, and finance packs whose checks must tie.
  • Unknown is not zero.A missing price or feed shows as unknown, in words, and never becomes a zero inside a total.
  • Change and audit commit together.Every write records its audit event in the same database transaction, so the log cannot miss a change.
  • People make the final call.Agents analyse, suggest and draft; decisions and approvals stay with a person, and AI actions are permission-checked and audited.