📂
Category Archive

Category: Agentic AI

Articles

4 stories
Agentic AI

Why I’m Betting on a Minimal Agent Harness

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.

Dominic Plouffe · 6 min Oct 5, 2026
Abstract editorial illustration of a small core module connected by thin lines to several plug-in blocks, in flat teal and amber vector style on a navy background, suggesting a minimal core you extend yourself.
Agentic AI

Open-weight decision models: Clef vs Strands Decider

Abstract editorial illustration of a path forking into two outcomes, one a solid filled circle and one an empty outlined circle, with small confidence-score tick marks near the solid circle, in flat teal and amber vector style on a navy background.

Clef and Strands Decider 2B are open-weight decision models that return a calibrated score, not text. Here's what shipped and why it…

Dominic Plouffe · 6 min Oct 4, 2026
Agentic AI

The Bug Was Reproducible. My Logs Weren’t.

A paper record tape unspooling across a dark desk, its printed rows fading to blank partway along, with a magnifier over the last legible section.

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 Sep 4, 2026
Agentic AI

Agent design patterns for production

TL;DR: Build agents by composing small, well-instrumented capabilities, enforcing runtime controls, and designing for predictable state transitions. These patterns reduce surprises in…

Dominic Plouffe · 3 min Mar 16, 2026