Antonio Poggi

Directory · 24 entries

Find the work behind the work.

Search every field guide and principal page on this site. Filter by subject, or browse the complete directory below.

Search and filter

What are you looking for?

Series 01 · 5 articles

Verifiable and private AI analytics

  1. 01 Article · 7 min What Is Verifiable AI Analytics? Verifiable AI analytics separates model planning from governed execution, preserving the queries, calculations, lineage and evidence behind every answer.
  2. 02 Article · 7 min Why an LLM Should Not Be Your Analytics Engine LLMs should plan and explain analytics, while governed data tools execute calculations, enforce definitions and preserve reproducible evidence.
  3. 03 Article · 7 min How AI Agents Can Operate Governed Data Tools A practical architecture for AI agents to use governed analytics tools through permissions, bounded operations, execution records and human review.
  4. 04 Article · 8 min Local LLM Analytics: Privacy, Cost and Deployment Trade-offs A practical comparison of local, cloud and hybrid LLM analytics across privacy, model quality, GPU cost, latency, reliability and operations.
  5. 05 Article · 7 min From Natural-Language Question to Inspectable Analytical Workflow Follow an AI analytics request from natural-language intent through schema context, governed execution, validation, evidence and a reusable workflow.

Series 02 · 5 articles

Building complete data products

  1. 01 Article · 8 min From CSV Prototype to Scheduled Data Application A practical maturity path from a CSV analytics prototype to a parameterised, monitored, permissioned and scheduled internal data application.
  2. 02 Article · 7 min Why Data Preparation, Analytics and Reporting Belong Together Keeping data preparation, analysis and reporting connected reduces semantic drift, duplicated logic and evidence lost at tool hand-offs.
  3. 03 Article · 7 min How to Turn an Analytical Workflow into an Internal Product Turn a working analytical workflow into an internal data product by designing users, state, actions, permissions, interfaces and operations.
  4. 04 Article · 7 min Lessons from Building Omniscope Across Multiple Technology Cycles Seven product lessons from more than two decades of building Omniscope through desktop, web, cloud, no-code and AI technology cycles.
  5. 05 Article · 7 min Where No-Code Ends and Custom Software Should Begin A practical decision framework for choosing visual no-code workflows, embedded Python/R/JavaScript or a separately engineered software service.

Series 03 · 5 articles

Citizen science and public evidence

  1. 01 Article · 12 min How to Build a Private AirGradient-to-Analytics Pipeline Build a private AirGradient analytics pipeline using custom ESP32-C3 firmware, local Android control and direct HTTPS ingestion into Omniscope.
  2. 02 Article · 7 min What I Learned from Analysing 80,000 Hourly Benzene Measurements Lessons from analysing more than 80,000 hourly benzene readings in Taranto: preserve peaks, define thresholds, expose gaps and version the evidence.
  3. 03 Article · 7 min Making Institutional Air-Quality Data Usable by Citizens How ARPA Puglia monitoring files became a public, Italian-language Omniscope instrument for citizens, classrooms, comparisons and civic investigation.
  4. 04 Article · 6 min Designing Alerts That Preserve the Evidence Behind the Claim Design data-driven air-quality alerts with station, time, units, averaging period, reference meaning, source status and links to inspectable evidence.
  5. 05 Article · 8 min Open Hardware, Private Infrastructure and Citizen-Owned Monitoring What citizen-owned air-quality monitoring requires across open hardware, firmware, local control, private transport, stored history and responsible interpretation.

Site guides · 9 pages

The principal routes through the site

  1. 01 Overview Home The quickest introduction to Antonio’s professional work at Visokio and civic air-quality projects.
  2. 02 Product guide Visokio and Omniscope The product story, complete data workflows, data applications and verifiable AI.
  3. 03 Product history The Omniscope timeline How Omniscope evolved through coordinated visualisation, workflows, web delivery, data applications and AI.
  4. 04 Capability guide The whole data journey Why data preparation, analysis, reporting, automation and delivery should stay connected.
  5. 05 Capability guide Data applications How workflows become internal tools, branded analytics, embedded experiences and automated services.
  6. 06 Capability guide Verifiable AI analytics How models can operate real analytics tools while transformations, evidence and review remain visible.
  7. 07 Project guide Air quality The living record of Taranto monitoring, benzene alerts, civic evidence and open sensor work.
  8. 08 Publication Writing All fifteen long-form field guides, organised into three connected editorial series.
  9. 09 Profile About Antonio Background, current focus, public profiles and ways to continue the conversation.