ARCHIVED · JANUARY 2026
January 2026
The Agentic Design Library as published in January 2026 — preserved exactly as it appeared on the homepage that month. Reading list of 9 essay-style pieces.
Hugo Bowne-Anderson · with Sebastian Raschka
January 15, 2026
LLM Architecture in 2026: What You Need to Know
Sebastian Raschka
Current state of LLM and agent architectures: what changed, what's stable enough to build on, and what to ignore. From the author of Ahead of AI.
architecturefundamentalsThe AI Corner
January 10, 2026
Andrej Karpathy: The AI Workflow Shift
Andrej Karpathy (interview recap)
Karpathy on the shift from typing code to specifying intent. Judgment — what to delegate, how to spec it, how to review fast — becomes the operative skill.
philosophyworkflowsVoltAgent
January 5, 2026
Awesome AI Agent Papers
VoltAgent Maintainers
Curated repository of 2026 agent research papers organized by topic: agent engineering, memory, evaluation, workflows, autonomous systems.
curationresearchOne Useful Thing
November 18, 2025
Three Years from GPT-3 to Gemini 3
Ethan Mollick
Mollick's retrospective on three years of frontier model progress. From chatbots to agents — what changed, what didn't, and what the gradient of capability looks like up close.
retrospectivefrontier modelsAnthropic
September 29, 2025
Effective Context Engineering for AI Agents
Anthropic Engineering
Context engineering as the primary lever for agent behavior. Structured note-taking, compaction, memory tools, and tool-result clearing — the techniques that keep long-running agents coherent without prompt thrash.
context engineeringmemorytool useAhead of AI
September 10, 2025
Beyond Standard LLMs
Sebastian Raschka
Deep-dive on what makes contemporary LLM systems different from the 2023 baseline — tool use, memory architectures, post-training on agent trajectories, and the shift in how agents are evaluated and tuned.
technicalLLMsarchitectureAnthropic
December 19, 2024
Building Effective Agents
Anthropic Engineering
The canonical production-agents essay. Five composable workflow patterns — prompt chaining, routing, parallelization, orchestrator-workers, and evaluator-optimizer. Core argument: simple patterns beat complex frameworks in production agent systems.
design patternsarchitectureproductionLil'Log
June 23, 2023
LLM Powered Autonomous Agents
Lilian Weng
The foundational essay on agent architecture. Decomposes the LLM-as-brain pattern into planning, memory, and tool use. Still the most cited single piece on the topic.
foundationalarchitectureAndrej Karpathy
November 11, 2017
Software 2.0
Andrej Karpathy
The essay that named the paradigm. Karpathy's argument that neural networks aren't another tool in the ML toolbox — they're a new programming paradigm. Foundational reading for anyone designing agentic systems.
foundationalphilosophyparadigm