RAG
What's The Best Chunking Strategy For RAG Retrieval in 2026?
Start RAG retrieval with recursive or sentence-based splitting, then use evaluation results to decide whether semantic chunking is worth the cost.
5 min read
Read articleInsights
Ideas for faster, more reliable finance operations.
Articles on reducing turnaround times, preventing errors, increasing capacity, and choosing software, automation, or AI based on the problem.
Featured insight
Latest insights
voice AI
Options for Moving STT and TTS Pipelines to Australia in April 2026
Compare managed, self-hosted, colocated, and air-gapped options for moving speech-to-text and text-to-speech workloads to Australia.
6 min read
AI engineering
Should You Use LangChain When building a New AI chatbot or Just Write From scratch?
Compare LangChain with provider SDKs for new AI chatbots, including when framework overhead becomes worthwhile.
4 min read
All insights
37 articlesRAG
What's The Best Chunking Strategy For RAG Retrieval in 2026?
Start RAG retrieval with recursive or sentence-based splitting, then use evaluation results to decide whether semantic chunking is worth the cost.
5 min read
voice AI
Options for Moving STT and TTS Pipelines to Australia in April 2026
Compare managed, self-hosted, colocated, and air-gapped options for moving speech-to-text and text-to-speech workloads to Australia.
6 min read
AI engineering
Should You Use LangChain When building a New AI chatbot or Just Write From scratch?
Compare LangChain with provider SDKs for new AI chatbots, including when framework overhead becomes worthwhile.
4 min read
LLM evaluation
Your LLM-As-A-Judge Might Be Lying to You
Detect positional bias and ranking cycles in pairwise LLM judges, then use balanced comparisons to improve evaluator reliability.
4 min read
voice AI
What Is Actually Blocking Voice From Becoming the Default Interface?
Voice interfaces face structural limits involving memory, precision, privacy, and error recovery even as speech models improve.
7 min read
voice AI
Inference Options for Hosting a Sovereign Voice AI Stack in Australia
Compare models, GPUs, providers, latency, and costs for hosting a production sovereign voice AI inference stack in Australia.
7 min read
LLM evaluation
Stop Scoring. Start Ranking.
Learn why pairwise ranking gives more useful LLM evaluation results than numeric scoring, and how to infer relative quality.
6 min read
AI agents
CLI vs MCP: Which one should you use in 2026?
Compare CLI tools and MCP servers for AI agents across token use, context cost, reliability, security, and developer experience.
3 min read
artificial intelligence
How do you turn time with your Subject Matter Expert into a long term asset?
Turn subject matter expert feedback into reusable evaluation criteria, durable knowledge, and faster AI system improvement loops.
4 min read
AI agents
Why your agent can confidently do the wrong thing
Use deterministic routing, explicit agent skills, and evals to stop AI agents from confidently selecting the wrong workflow.
5 min read
artificial intelligence
How I stopped fighting prompts and started building feedback loops
Use a generate, evaluate, and revise loop to improve AI output more reliably than repeated prompt changes alone.
4 min read
artificial intelligence
Reducing AI-Slop with Logit Bias
Learn how logit bias can reduce repetitive AI writing patterns, where it fails, and how to test it without causing token loops.
8 min read
artificial intelligence
RED framework for binary AI evals. Stop debugging in the dark
Use the RED framework to make binary LLM evaluations explain their reasoning, cite evidence, and return a clear decision.
4 min read
Case Study - Hexagonal Grids for Terracotta RPG
game development
Case Study - Hexagonal Grids for Terracotta RPG
A case study of how I built a hexagonal grid system for procedural territory generation.
13 min read
Building Your First Evaluation System for LLM Applications
ai
Building Your First Evaluation System for LLM Applications
A practical guide to building a basic evaluation system for non-deterministic AI applications using LLMs and prompt engineering.
6 min read
Rethinking PERT, Introducing Wagn Project Tracker
estimation
Rethinking PERT, Introducing Wagn Project Tracker
Discussing the limitations of traditional PERT and introducing my personal project estimation tool, Wagn Project Tracker, which uses a certainty-based approach.
5 min read
Estimation Uncertainty and Quantifying Risk
estimation uncertainty
Estimation Uncertainty and Quantifying Risk
Defining estimation uncertainty and explaining how PERT's Standard Deviation (SD = (P - O) / 6) quantifies the risk or confidence level in an estimate.
1 min read
Expected Duration
Expected Duration
Expected Duration
Defining Expected Duration (E) in PERT and explaining the calculation using the weighted average formula E = (O + 4M + P) / 6.
1 min read
PERT - Program Evaluation and Review Technique
PERT
PERT - Program Evaluation and Review Technique
Defining PERT (Program Evaluation and Review Technique), a method using three-point estimates to manage project uncertainty and improve forecast reliability.
1 min read
Three-Point Estimation
three-point estimation
Three-Point Estimation
Explaining the three-point estimation technique, defining the Optimistic (O), Pessimistic (P), and Most Likely (M) estimates used in PERT.
1 min read
Work Breakdown Structure (WBS)
WBS
Work Breakdown Structure (WBS)
Defining the Work Breakdown Structure (WBS) and explaining its crucial role in decomposing project scope into manageable tasks for effective estimation.
1 min read
Acceptance Criteria (ACs)
acceptance criteria
Acceptance Criteria (ACs)
Defining Acceptance Criteria (AC) as the specific, objective, and testable conditions that determine when a user story is successfully implemented.
1 min read
Definition of Ready (DoR) - Protecting Estimation Quality
Definition of Ready
Definition of Ready (DoR) - Protecting Estimation Quality
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.
1 min read
Given-When-Then - Applied BDD
BDD
Given-When-Then - Applied BDD
Defining Behavior-Driven Development (BDD) and its Given-When-Then (GWT) syntax for writing clear, example-based acceptance criteria that aid understanding and estimation.
2 min read
INVEST Criteria - How do you know a user story is ready for estimation?
INVEST criteria
INVEST Criteria - How do you know a user story is ready for estimation?
Defining the INVEST mnemonic (Independent, Negotiable, Valuable, Estimable, Small, Testable) and its practical use as a quality checklist for user stories before estimation.
2 min read
Defining a User Story
user story
Defining a User Story
Defining a user story in Agile, highlighting its structure and purpose as the key input for development team understanding and estimation efforts.
1 min read
Introducing @wagn/voice-ui: A Component Library for Voice Interfaces in React
react
Introducing @wagn/voice-ui: A Component Library for Voice Interfaces in React
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.
3 min read
Building Real-Time AI Chatbots - Hard Lessons Learned
chatbot
Building Real-Time AI Chatbots - Hard Lessons Learned
Key lessons learned from building real-time AI chatbot systems, covering response time optimization, state management, context windows, and current ecosystem limitations.
6 min read
The Death of Frameworks
framework
The Death of Frameworks
Frameworks are dying—or perhaps already dead. Here's why I believe this is happening.
3 min read
Samification
samification
Samification
Samification is the process where competing technologies, frameworks, or ideas gradually converge toward a single, widely accepted standard.
1 min read
Canonical Naming
canonical naming
Canonical Naming
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).
1 min read
Embeddings
embedding
Embeddings
Embeddings allow us to represent meaning in a vector space, allowing us to perform mathematical operations on it.
1 min read
Model Context Protocol (MCP)
mcp
Model Context Protocol (MCP)
Model Context Protocol (MCP) standardizes how AI models and applications connect to external data sources and tools.
1 min read
Retrieval-Augmented Generation (RAG)
retrieval-augmented generation
Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) is a technique that enhances AI-generated responses by first retrieving relevant information before generating an answer.
1 min read
The Value of Static Sites and My Blog Vision
static site
The Value of Static Sites and My Blog Vision
Exploring the benefits of static sites and my vision for this blog
1 min read
Vibe Coding
vibe coding
Vibe Coding
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.
1 min read
Securing Phone Calls in the Age of AI Voice Cloning
security
Securing Phone Calls in the Age of AI Voice Cloning
Exploring solutions to combat AI voice cloning scams through verification systems and AI-assisted call screening.
3 min read