Cover Story — October 2026

Why I’m Betting on a Minimal Agent Harness

Dominic Plouffe · Oct 5, 2026 · 6 min read

Pi 1.0's own release notes claim a 40% prompt-token cut from Codemode. Here's the arithmetic I'd run before trusting a minimal agent harness.

Read the full story →
01

Open-weight decision models: Clef vs Strands Decider

Agentic AI · 6 min · Oct 4, 2026
02

The Hidden Risk of Letting AI Manage Ad Campaigns

AI Marketing · 17 min · Sep 5, 2026
03

Your Agent A/B Test Was Broken Before You Ran It

Evals · 6 min · Sep 4, 2026

Latest

Today
Evals

Half My Agent’s Budget Goes to Checking Its Own Work

I built the quality gate last, in an afternoon, as the cheap safety rail. Then I added up the API bills by phase. Across four runs it took 51.5% of…

Dominic Plouffe · 5 min
Evals

I Rewrote the Test Until My Writing Passed It

Five commits in four days, every one adjusting the grader that judges this blog's drafts, every one triggered by a verdict I…

Dominic Plouffe · 5 min
Agentic AI

The Bug Was Reproducible. My Logs Weren’t.

A post on this site ended in a raw API payload for 151 days. Fixing it took two minutes. Explaining it took…

Dominic Plouffe · 5 min
Security

Credential Scanners Are Wearing Crawler Costumes

71.9 percent of traffic claiming to be Googlebot was hunting for .env files. Of 13,670 credential probes wearing a named crawler user…

Dominic Plouffe · 7 min Aug 14, 2026
Data Analytics

Crawled, Indexed, or Cited: How to Read AI Traffic in Your Server Logs

Training, indexing, and live answering are three different things happening to your site. Here is how to tell them apart — and…

Dominic Plouffe · 10 min Aug 10, 2026
Startup Agents

I Tried to Replace a Startup Team With Three AI Agents. Here’s What Happened in Week One.

431 commits. 31 live leaderboards. About 245 outbound emails. $0 in revenue. The code was not the interesting part. I’ve spent a…

Dominic Plouffe · 17 min Aug 8, 2026

Analysis

04

A scheduled task is not a returning user

Uncategorized · Dominic Plouffe · 5 min · Aug 5, 2026
05

Shortcut scored 5.9, Claude scored 5.5, both failed

AI Tools · Dominic Plouffe · 6 min ·
06

The 28,000 Jobs a Month Nobody Can Pin on AI

Uncategorized · Dominic Plouffe · 5 min · Aug 4, 2026
07

The EU’s New AI Disclosure Rule Is Not a 7% Fine

AI Strategy · Dominic Plouffe · 6 min ·
08

41 percent of workers use AI, 18 percent of firms adopted it

Enterprise AI · Dominic Plouffe · 5 min · Aug 3, 2026
09

Does Claude understand your audience better than you think?

AI Marketing · Dominic Plouffe · 15 min · Apr 9, 2026
10

Is Vibe Coding’s $12B Market Built on Broken Foundations?

Software Development · Dominic Plouffe · 13 min · Apr 7, 2026
11

Does OpenClaw Really Work for Non-Programmers? The Truth Hurts

AI Tools · Dominic Plouffe · 13 min · Apr 6, 2026