BestHub
Sign in
Data Bricklaying Diary
Author

Data Bricklaying Diary

Records practices, thoughts, and pitfalls on the data grunt-work journey, sharing content on data platforms, data analysis, data processing, data governance, knowledge graphs, and more. Less theory, more hands‑on, making complex data technologies simple.

165
Articles
0
Likes
383
Views
0
Comments
Recent Articles

Latest from Data Bricklaying Diary

100 recent articles max
Data Bricklaying Diary
Data Bricklaying Diary
Oct 24, 2026 · Artificial Intelligence

Why AI Success Metrics Become Business Rework: Measuring Real Delivery in Agent Triage

This article argues that technical success metrics for AI agents (like API success rates) misrepresent business value, and proposes a framework for measuring actual delivery: define qualified outcomes per pre-agreed contracts, fix the task denominator, track human effort and rework across auto/collaborative/escalation paths, and feed verified operational feedback into knowledge, model, and regression improvements.

AI agent evaluationafter-sales triagebusiness metrics
0 likes · 26 min read
Why AI Success Metrics Become Business Rework: Measuring Real Delivery in Agent Triage
Data Bricklaying Diary
Data Bricklaying Diary
Oct 23, 2026 · Artificial Intelligence

Agent Workflow Runtime Governance: Classify Failures, Evidence Packages, and Escalation Paths

The article analyzes why agent workflows that succeed in demos fail in production, proposing a runtime governance framework that classifies failures into technical, data, business uncertainty, and controllable progression categories, mandates evidence-based human-in-the-loop with evidence packages, and defines a state machine with escalation paths for reliable execution.

AI productionAgent workflowError classification
0 likes · 21 min read
Agent Workflow Runtime Governance: Classify Failures, Evidence Packages, and Escalation Paths
Data Bricklaying Diary
Data Bricklaying Diary
Oct 23, 2026 · Information Security

Why External Content Must Not Override Agent Permissions: Defending Against Indirect Prompt Injection

This article analyzes how AI agents can be manipulated via indirect prompt injection hidden in external materials, and proposes a layered defense: distinguish source from authority, validate every execution step, bind confirmations to specific actions, and test with adversarial scenarios to ensure boundaries hold without breaking legitimate tasks.

AI securityOWASPadversarial testing
0 likes · 10 min read
Why External Content Must Not Override Agent Permissions: Defending Against Indirect Prompt Injection
Data Bricklaying Diary
Data Bricklaying Diary
Oct 22, 2026 · Frontend Development

Continuous GUI Verification: Ensuring Users Complete Tasks, Not Just Open Pages

This article presents a practical framework for continuous GUI verification in AI development, stressing end-to-end task completion over page rendering, correlating frontend feedback with backend results, isolating test data, making critical paths reproducible, and preserving failure evidence for debugging.

AI developmentGUI verificationPlaywright
0 likes · 10 min read
Continuous GUI Verification: Ensuring Users Complete Tasks, Not Just Open Pages
Data Bricklaying Diary
Data Bricklaying Diary
Oct 21, 2026 · Artificial Intelligence

AI-Generated Ontologies: What Experts Must Review Beyond Syntax

This article outlines a structured review process for AI-generated ontology drafts, emphasizing that experts must verify business meaning, evidence sources, and high-risk judgments — not just technical correctness — and demonstrates how to trace rejections, revisions, and version-specific approvals using a supply-chain quality case study.

AI-generated ontologySHACLbusiness rules
0 likes · 17 min read
AI-Generated Ontologies: What Experts Must Review Beyond Syntax
Data Bricklaying Diary
Data Bricklaying Diary
Oct 21, 2026 · R&D Management

AI Code Review: Why Two Agents Miss the Same Bugs and How to Fix It

The article explains why simply adding a reviewer AI agent after a developer agent fails when both share requirement misunderstandings, and proposes a structured multi-agent review process: independent judgment against acceptance criteria first, automated mechanical checks, risk-based review division, actionable findings with trigger conditions and verification steps, reverse test validation via mutation and negative testing, and review conclusions tied to specific commits with expiration tracking.

AI code reviewGoogle engineering practicescode review best practices
0 likes · 10 min read
AI Code Review: Why Two Agents Miss the Same Bugs and How to Fix It
Data Bricklaying Diary
Data Bricklaying Diary
Oct 20, 2026 · Backend Development

Before AI Refactors Legacy Code: Lock Down These Behaviors First

The article outlines a safe approach for AI-assisted legacy refactoring: define behavioral baselines with stakeholders, capture repeatable test samples covering normal and edge cases, compare old and new outputs in isolation, refactor incrementally with continuous regression, and verify rollback compatibility for data and interfaces.

AI refactoringDanilo SatoMartin Fowler
0 likes · 10 min read
Before AI Refactors Legacy Code: Lock Down These Behaviors First
Data Bricklaying Diary
Data Bricklaying Diary
Oct 20, 2026 · R&D Management

Organizing Maintenance Knowledge: Start from a Concrete Work Order, Not Document Piles

The article describes a methodology for organizing maintenance knowledge by starting from a specific work order, distinguishing regulatory requirements, system records, and expert experience, preserving provenance with W3C PROV, building a judgment basis checklist, modeling with OPM, and validating with independent work orders to ensure traceable, gap-aware knowledge for AI assistants.

AI assistantOPMProvenance Tracking
0 likes · 15 min read
Organizing Maintenance Knowledge: Start from a Concrete Work Order, Not Document Piles