Journal

AI Workflow

43 posts tagged “AI Workflow”

Size the Fuse to the Furnace, Not the Candle

A global safety limit must be calibrated against your heaviest known run before you trust it. The dangerous default is the one too tight to survive your normal worst case.

2026-07-05 · 5 min read · Teh Kim Guan, ACMA, CGMA

Architecture

The Cheapest Architecture Is the One You Discover You Do Not Need

Most over-engineering is not a failure of restraint. It is designing against an imagined system instead of the one you shipped. Grounding killed two days of work.

AI Workflow

Size the Fuse to the Furnace, Not the Candle

The Cheapest Architecture Is the One You Discover You Do Not Need

AI Gives You Plausible Defaults, Not Correct Answers

Loop Engineering: What Running Fifty-Odd Agents Taught Me About the Verifier

The Two-Tier Staff Agent Pattern: Strategic Ara, Operational Deeno

Telemetry-First Sub-Agent Dispatch Saved Me 18 Minutes on a Quota Cliff

Why I Deleted the Anthropic SDK From My Workflow

I Measured My AI Router This Week. It Hit 94 Percent Top-1 Versus a 48.9 Percent Baseline.

Description Disambiguation Is the Highest-Impact Router Intervention I Have Tried

Your Role Is Becoming a Skill (and the Org Chart Hasn't Caught Up)

Your Company Is a Graph of Algorithms (and AI Is About to See It)

Token Economy as Cash Economy: Treating Model Selection as a Staffing Decision

The Compounding Agent in Production

Brief-then-Fire: A Two-Stage Architecture for AI-Augmented Consulting Workflows

The Delegate Reset: When a Team Member's Scope Dies and How to Restart Cleanly

Reverse-Engineering Malaysian Government Portals: A Reusable Crawl Pattern

The 95% Margin Workflow: How One Consulting Engagement Compressed RM 30,000 of SEO Work into RM 800

The Intent Gap: What Nielsen's AI UX Framework Gets Right and Misses for Regulated Software

Why I Stopped Launching Background Agents for File Creation

The Eval Harness Is Load-Bearing Infrastructure

When Your Team Outgrows Intuition: Building a Delegation Routing Layer

Token Economics for Solopreneurs: Build Once With Tokens, Run Forever

The 67/27 Problem: When Your AI System Becomes Its Own Overhead

Delegation Without a Team: The 3-Tier Classification System

Brief Before Build: The Hidden Cost of Produce-Then-Constrain

Background Queue Friday: The 30-Minute Monthly Reset

The Verification Loop: Why AI Skills Without Evals Are Prompts With Delusions of Permanence

Three Layers Every AI Agent Stack Needs: Memory, Routing, Execution

Phase-Gated Pipelines: Why the Best AI Tools Separate Inspection from Construction

The Auto-Research Stack: From Karpathy's Experiment to Production Pipelines

The Task Cascade Protocol: Why Most Knowledge Work Systems Leak Tasks

Self-Evolving Skills: The New Infrastructure for Reliable AI Agents

In-Page AI Agents: Why This Becomes the Standard Way to Deploy AI Copilots

Topical Authority and AI: Rank Page 1 in 45 Days

Satellite AI Foundation Models: The Democratization Trap

Prompt Engineering as Defensible IP: The New Excel Model

The One-Person Operating Model: Integration Beats Collection

LLM Councils: Why Ensemble AI Makes Professionals More Defensible

Hybrid SQL+Vector Search: The Architecture Behind Trustworthy AI Valuations

Five Models, Five Jobs: A Framework for Choosing the Right AI

Computer Vision in Property Valuation: Precision at Scale

AI and Crypto: The Infrastructure Nobody Saw Coming

The Unblock Pattern: Why a 15-Minute Validation Saves 15 Hours of Wasted Build