Latest articles.
Hands-on writing on local LLMs, reasoning models, and the practical edges of applied AI.
Prompting
Precise Prompting Is Context Specification
June 20, 2026 · 10 min read
A literature-backed hypothesis on why precise prompting is less about adding detail everywhere and more about selecting the context that changes model behavior.
E-Learning
How to Turn Procedures and Instructions Into Training
May 23, 2026 · 8 min read
A practical guide to turning SOPs, procedures, checklists, playbooks, and step-by-step instructions into useful workplace training.
E-Learning
How to Create Training from Source Material
May 22, 2026 · 13 min read
A practical workflow for turning product briefs, SOPs, manuals, onboarding decks, policies, and expert notes into structured training, with and without AI assistance.
AI Governance
Tool Permissions Are The New Access Control Layer For AI Agents
May 17, 2026 · 9 min read
A practical guide to allow, deny, approval-required, and constrained tool permissions for safer agent operations in production workflows.
AI Governance
How To Assess AI Agent Risk Before Production
May 10, 2026 · 10 min read
A practical pre-production assessment model covering use-case intake, autonomy, tool access, data sensitivity, human oversight, business impact, and final risk tier.
AI Governance
The AI Agent Risk Taxonomy: 12 Risks Every Enterprise Should Track
April 19, 2026 · 11 min read
A practical agent risk taxonomy mapped to OWASP Agentic AI, NIST AI RMF, EU AI Act, GDPR, ISO 42001, and MITRE ATLAS.
AI Governance
AI Agent Risk: Why Agents Need A New Governance Model
April 12, 2026 · 8 min read
Why agent governance should be based on actual agentic behavior, not vendor labels, and how low-agentic tools differ from autonomous workflow agents.
E-Learning
Visible vs. Cognitive Interaction in eLearning
April 5, 2026 · 3 min read
Why clicking and dragging are not enough: effective eLearning balances visible screen actions with deliberate mental effort.
Reasoning Models
The S1 Model running locally — Reasoning made transparent
February 14, 2025 · 4 min read
A look at the S1 reasoning model that matches top-tier performance while being trained on just 1,000 examples — and how it runs on a laptop.
Local AI
3 Ways to Run DeepSeek and Llama Locally
February 11, 2025 · 4 min read
Three practical paths to running Llama 3.3 or DeepSeek on your own hardware — and which one fits which use case.
AI Crafters
Welcome to AI Crafters
February 12, 2025
What we're building, why we're building it, and what to expect on this site.