Skip to content
§ Signals

What is worth reading beyond this lab.

A curated external reading layer for AI systems work. Selection is intentionally sparse: each signal earns its place by changing a question, sharpening an architecture decision, or challenging an assumption.

Filter / relevance over recency
Format / source + annotation
Cadence / irregular by design
SIG / 01 · Agents
Dec 19, 2024

Building effective agents

Anthropic Engineering

Why it matters

A durable architecture reference for deciding when workflows are enough and when agent autonomy is actually warranted.

SIG / 04 · Agents
Apr 15, 2026

The next evolution of the Agents SDK

OpenAI

Why it matters

A current production reference for agent harnesses that combine tools, memory, controlled sandbox execution, durability, and explicit separation between orchestration and compute.

SIG / 05 · Agents
Jun 24, 2026

Building effective human-agent teams

Claude by Anthropic

Why it matters

Extends the agent question beyond autonomy into coordination: how humans and agents divide work while retaining shared context and control.

Curation rule

Signals is not a breaking-news feed. Recency can make something visible; relevance is what keeps it here. Sources are selected for their usefulness to the lab's research, frameworks, systems, and build decisions.