Your AI Agent Needs Skills, Not an Org Chart

Start with one owner and a library of skills. Add other agents when they buy you something real—not because the workflow looks more impressive with…

Oct 9 • Eloi Tay

Cosplay Prompting Validity

Telling an AI it is a world-class expert is not a capability upgrade. Giving it a concrete job still can be useful.

Oct 5 • Eloi Tay

September 2026

Why New AI Models Feel Brilliant—Until We Promote Them

Sometimes the model has not become less capable. We have quietly given it a different job—and far more of it.

Sep 30 • Eloi Tay

June 2026

The AI Layoff Story Is Too Convenient

Big tech is not simply replacing workers with bots. It is using AI, higher rates, and a colder labour market to redraw which people count as scarce.

Jun 14 • Eloi Tay

The Benchmark Is Also Hallucinating

DeepSWE is a serious test of coding agents. The silly bit is pretending any one leaderboard can tell you whether software work is safe.

Jun 11 • Eloi Tay

The Moat Moved Up the Stack

Open models can catch a leaderboard. That is not the same thing as catching the product.

Jun 9 • Eloi Tay

The High Performer Trap

Why the person who saves the day can become the manager who blocks the team.

Jun 4 • Eloi Tay

GPT-5.5 Is Expensive Only If You Ask the Wrong Question

Price per token is the spreadsheet answer. Cost per useful outcome is the production answer.

Jun 2 • Eloi Tay

Free Tools to Help You Stretch Your Tokens

RTK cuts terminal noise before it enters context. Caveman cuts the agent’s visible chatter. The useful trick is knowing which tokens each one actually…

Jun 1 • Eloi Tay

April 2026

AI Is Cheap. Good Ideas Still Aren't.

The useful question is not whether AI saves hours. It is whether it lets teams buy more serious attempts without lowering the bar.

Apr 28 • Eloi Tay

Your Agent Isn't Tired. It's Drowning in Context

The useful analogy between humans and LLMs is not consciousness. It is that both fall apart when active memory, compression, and management are sloppy.

Apr 25 • Eloi Tay

Your Org Chart Is Not Your Operating Model

Why healthy software teams keep accountability close to the product, centralize leverage, and design for knowledge resilience

Apr 23 • Eloi Tay