Skip to main content
Pixelmojo Field Notes

The archive, page 9.

Older notes, newest first. Every one is the same research, methods, and build logs as the front page.

9 notes · Page 9 of 12100 total
thread based engineering · 6 min74

Lakbay AI: What We Built and What We Withdrew (Dated Note)

A dated note on our February 2026 Lakbay AI case study: what the travel concierge is, what its repository history shows, and the timeline, speed and security claims we withdrew.

Building AIRead article →
vibe coding · 17 min77

84% of Developers Use AI Tools. 45% of AI Code Has Flaws.

84% of developers use or plan to use AI tools, yet only a third trust their accuracy, and 45% of AI-generated code samples failed security tests. The 2026 research data, the risks, and governance patterns that work.

Building AIRead article →
thread based engineering · 17 min78

Thread-Based Engineering: The Framework for Scaling AI Development

The definitive guide to Thread-Based Engineering: 7 thread types, governance alignment, a production case study (Lakbay AI), and the research on AI code quality, including the Veracode finding that models failed to write XSS-safe code 86% of the time.

Building AIRead article →
agentic ai 2026 · 14 min79

The Dawn of Agentic AI: From Chatbots to Co-workers in 2026

AI is no longer just answering questions; it is taking action. The shift from assistive chatbots to agentic AI co-workers is the defining technology transition of 2026. What this means for businesses and why self-verification changes everything.

Building AIRead article →
multi agent ai systems · 19 min81

Multi-Agent AI Systems Explained: When One AI Is Not Enough

Why single AI agents fail at scale and how multi-agent orchestration solves it. Architecture patterns, shared intelligence, and why 95% of AI pilots show no measurable impact.

Building AIRead article →
Read enough? Check your own

Does AI get your business?

Run Radar's six free technical checks on your domain, then follow the evidence behind each finding.