Blog

A case study of how I built a hexagonal grid system for procedural territory generation.

How to distinguish between code that deserves comprehensive testing, and code that should be optimized for rapid iteration.

A practical guide to building a basic evaluation system for non-deterministic AI applications using LLMs and prompt engineering.

Discussing the limitations of traditional PERT and introducing my personal project estimation tool, Wagn Project Tracker, which uses a certainty-based approach.

Defining estimation uncertainty and explaining how PERT's Standard Deviation (SD = (P - O) / 6) quantifies the risk or confidence level in an estimate.

Defining Expected Duration (E) in PERT and explaining the calculation using the weighted average formula E = (O + 4M + P) / 6.

Defining PERT (Program Evaluation and Review Technique), a method using three-point estimates to manage project uncertainty and improve forecast reliability.

Explaining the three-point estimation technique, defining the Optimistic (O), Pessimistic (P), and Most Likely (M) estimates used in PERT.

Defining the Work Breakdown Structure (WBS) and explaining its crucial role in decomposing project scope into manageable tasks for effective estimation.

Defining Acceptance Criteria (AC) as the specific, objective, and testable conditions that determine when a user story is successfully implemented.

Defining the Definition of Ready (DoR) as a team-agreed quality gate ensuring user stories meet specific criteria before being considered for estimation or sprint commitment.

Defining Behavior-Driven Development (BDD) and its Given-When-Then (GWT) syntax for writing clear, example-based acceptance criteria that aid understanding and estimation.

Defining the INVEST mnemonic (Independent, Negotiable, Valuable, Estimable, Small, Testable) and its practical use as a quality checklist for user stories before estimation.

Defining a user story in Agile, highlighting its structure and purpose as the key input for development team understanding and estimation efforts.

Announcing @wagn/voice-ui, a React component library that makes it simple to add beautiful voice interfaces to web applications through a composable, event-driven architecture.

An example output from the DAFC CLI tool, demonstrating generated code for the wagn-voice-ui library.

Key lessons learned from building real-time AI chatbot systems, covering response time optimization, state management, context windows, and current ecosystem limitations.

Exploring how to leverage Gemini 2.5 Pro's massive context window to build software by dumping entire codebases into the LLM, and introducing the DAFC methodology.

Reflecting on my earliest childhood memories from Indonesia and Australia, and how they shaped who I am today.

A structured approach to capturing my life story through fifty-two questions for self-reflection and autobiography.

Non-Zero Days is a powerful concept for breaking out of productivity ruts by committing to doing at least one small thing every day that moves you toward your goals.

Frameworks are dying—or perhaps already dead. Here's why I believe this is happening.

Samification is the process where competing technologies, frameworks, or ideas gradually converge toward a single, widely accepted standard.

Canonical naming is a way for us to delineate the boundaries of entities in a vector space, particularly used for graph-based Retrieval-Augmented Generation (RAG).

Embeddings allow us to represent meaning in a vector space, allowing us to perform mathematical operations on it.

Model Context Protocol (MCP) is a new standardized communication protocol, allowing AI models and applications to interact with external data sources and tools in a structured format.

Retrieval-Augmented Generation (RAG) is a technique that enhances AI-generated responses by first retrieving relevant information before generating an answer.

Exploring the benefits of static sites and my vision for this blog

Vibe coding is a new skill set that allows non-programmers to build SaaS applications or software in general using plain text instructions instead of writing traditional code.

Exploring solutions to combat AI voice cloning scams through verification systems and AI-assisted call screening.