Systems Research

Recent publications from TZD Labs Systems Research, an ongoing investigation into how AI capital flows through the physical economy.

Loading articles…

Blog Posts

 

Sub-Agent Orchestration: Cost-Aware Delegation With Work Attribution

Not every task needs Opus. I built a 5-agent orchestration system that matches task complexity to model tier, tracks what each agent produces, and merges results with quality gates.

Apr 18, 2026
Thandolwethu Dlamini
 

YOLO Mode: Autonomous AI Development With Engineering Guardrails

Claude Code’s auto mode guards against security threats. I built YOLO mode to guard against bad engineering: untested commits, unresearched changes, and oversized diffs.

Apr 16, 2026
Thandolwethu Dlamini
 

Plan Mode: From Freeform Text to Structured, Critiqued, Human-Reviewed Plans

Claude Code’s plan mode produces text that vanishes after the session. I built a structured alternative with YAML schemas, dual-agent critique, and interactive human review.

Apr 14, 2026
Thandolwethu Dlamini
 

Why I Switched from Python to Go for AI Development Tooling

It wasn’t just the cold start latency. The project outgrew Python, and the switch to Go was faster than I expected.

Apr 11, 2026
Thandolwethu Dlamini
 

Introducing wipnote: Local-First Observability for AI-Assisted Development

Every AI coordination tool I looked at stored state in SQLite. I wanted something I could diff in a PR, read in a browser, and traverse like a graph.

Apr 8, 2026
Thandolwethu Dlamini
 

AI Valuations vs. Infrastructure Spending

The seven largest US tech companies added trillions in market value since 2023. Against that, six of the biggest AI infrastructure builders are spending hundreds of billions on capex. Is the spending backed by real revenue?

Feb 15, 2026
Thandolwethu Dlamini
No matching items